Helps teammates find the right skill among the 159 skills of the library and chain them for bigger workflows.
This file is generated by scripts/build.py. Do not edit it by hand.
When to use
- The user asks what skills exist or which one fits their task.
- The user describes a job or role and wants to know how Gemini can help.
- A task needs several skills in sequence.
- Not for: doing the task itself. Once the skill is chosen, invoke it with
/or@.
Inputs
- The task, role or question (required). If it is vague, ask one question about the expected deliverable.
Sources
- The catalog below is the only source. Recommend only skills that are listed in it.
- If a source is not connected or returns nothing, say so in one line and continue with what you have. Never announce a search without giving its result in the same answer.
Workflow
- Restate the task in one line.
- Choose the 1–3 best matching skills from the catalog. Match on the deliverable first, then on the domain.
- If the task has several steps, propose a chain, for example
meeting-notes-to-actions→email-reply-drafter. - For each recommendation, give the exact invocation (
/skill-name) and a ready-to-paste first prompt. - If nothing fits, say so and suggest
skill-builderto create a new skill.
Output format
**Best fit:** `/<skill-name>` — <why, one line>
**Try:** "<ready-to-paste prompt>"
**Also useful:** `/<skill>` (<when>) · `/<skill>` (<when>)
**Chain (if multi-step):** `<skill>` → `<skill>` → `<skill>`Quality checks
- Every recommended skill name exists in the catalog below.
- The ready-to-paste prompt contains the user's real context.
Guardrails
- Never claim that a skill exists if it is not in the catalog.
Catalog
Productivity
back-from-leave-catchup— Gets the user back on track after an absence: what changed while they were away (decisions, docs, tickets, org news), what still needs them versus what was already handled by others, the threads that can be archived in bulk, and a plan for the first three days, starting with a sync with their backup.daily-briefing— Builds a one-screen morning briefing from today's calendar, unread priority emails, Google Chat and Slack mentions, Jira issues assigned to the user and open GitHub review requests, with a ranked top-3 for the day and prep notes per meeting.email-reply-drafter— Drafts a reply to a specific Gmail thread in the user's own voice: answers every question asked, in order, offers a short and a full version, and checks each date, number and commitment against Calendar, Drive and the thread before the user sends.focus-time-planner— Builds a realistic time-blocking plan for the day or the week from Google Calendar and the user's tasks: checks real capacity against estimates, places deep-work blocks where energy and gaps allow, protects buffers, and lists meetings to decline, shorten or delegate with ready-to-send messages.follow-up-tracker— Finds the user's open loops across Gmail, Chat, Slack and Jira: sent emails still waiting for an answer, promises the user made and has not delivered, and what others owe the user, then drafts tactful nudges graded by age and importance.handover-before-leave— Prepares the user's absence: inventories open work, deadlines and meetings that fall during the leave, builds a handover doc with a delegate map and the decision rights of each backup, proposes what to decline or reschedule in Calendar, and drafts a bilingual out-of-office reply.inbox-triage— Processes the Gmail inbox down to what matters: classifies every thread as reply, delegate, defer or archive, drafts the quick replies, proposes bulk actions and filters for recurring noise, and lists what is left with a time estimate.meeting-agenda-builder— Builds a meeting agenda that produces results: purpose and target outcomes, items typed inform, discuss or decide with an owner and a timebox, pre-reads, roles, the right attendee list, and the invite text ready to paste in Google Calendar.meeting-notes-to-actions— Turns meeting notes or a Google Meet transcript from Drive into a clean record: decisions with who decided, actions with one owner and a date, open questions and parking lot, plus a recap email ready to send and optional Jira issue drafts.meeting-prep— Prepares the user for one upcoming meeting: who will be there and their recent context, the history of the topic across emails, docs, Jira and past meeting notes, the probable goal, the user's position, the questions to ask and the outcome to aim for, on one page.prioritization-coach— Turns a messy task list into clear choices: sorts tasks with the Eisenhower matrix, scores impact and effort, adds cost of delay, then says what to do now, schedule, delegate or drop, with a one-line rationale each and ready messages to say no or renegotiate.thread-catchup— Summarizes a long Gmail, Google Chat or Slack thread into what a late joiner needs: the current state in two lines, decisions taken, open questions, who owes what by when, where people disagree, and a suggested reply.weekly-review— Runs an end-of-week review: what got done (Jira, GitHub, Calendar, Drive), what slipped and why, what carries over, and a plan for next week with a Big 3, a calendar health check and the focus blocks to protect.
Communication
change-communication-plan— Builds a communication plan for a change (new tool, process, organization, store concept, policy): impact map by audience, ADKAR stage per audience, key messages, channel and messenger choice, a week-by-week timeline from pre-announcement to reinforcement, manager toolkit, feedback loops and adoption indicators.document-reviewer— Reviews a Google Doc, Confluence page or pasted draft like a demanding senior editor: verdict first, then numbered comments by severity on purpose, structure, logic and evidence, clarity, gaps and risks, with rewritten versions of the weakest key passages and a readiness score.executive-summary-writer— Turns a long document, email thread, Meet transcript, Jira epic or analysis into a one-page executive summary built on BLUF and the pyramid principle: the answer or ask first, three supporting points with evidence, risks, decisions needed and next steps, every figure sourced.faq-builder— Builds a sourced FAQ from documents, email and chat threads, Jira or support tickets and meeting notes: finds the questions people really ask, groups them by theme, answers each one in plain language with a citation, and lists the questions with no official answer yet and who should answer them.internal-announcement-writer— Writes an internal announcement in three ready-to-post versions (email, short Google Chat or Slack post, intranet or Confluence article) plus an anticipated FAQ and a pre-send checklist: what changes, why, who is affected, what to do and by when, who to ask.message-rewriter— Rewrites a message, email or post for a target audience and goal: clearer, shorter, firmer, warmer or more diplomatic, adapted to a manager, an executive, a store team, a supplier, a customer or a partner, and returns two variants with a short list of what changed and why.presentation-storyline— Builds the storyline of a presentation before anyone opens Google Slides: governing message, SCQA opening, a slide-by-slide outline where each slide title is a full-sentence takeaway, the evidence and chart type per slide, speaker notes and timing, and a horizontal-logic check that the titles alone tell the story.talking-points-writer— Writes talking points or a short speech meant to be spoken: town hall, store opening, team kickoff, season launch, award or farewell, partner or club event.team-newsletter— Compiles a periodic team newsletter from what actually happened: wins and results, what shipped or went live, upcoming dates and events, decisions taken, recognition of teammates, and one useful tip, pulled from Drive, Jira, GitHub, Calendar, Chat and Slack, each item with its source, in an email-ready and a Chat-ready version.translation-localizer— Translates and localizes text between languages while keeping meaning, tone and format: keeps Company brand and product names as written, applies a team glossary found in Drive or Confluence, adapts units, dates, currencies and formality to the target country, and lists ambiguities and terms to validate.
Management Leadership
decision-memo— Writes a decision memo that gets a clear yes or no: context and the exact question, 2-4 real options including do-nothing, weighted criteria and a scored comparison, recommendation with the trade-off accepted, DACI roles, reversibility (one-way vs two-way door), risks with mitigations and the date by which the decision is needed.difficult-conversation-prep— Prepares a hard workplace conversation (repeated performance gap, behavior issue, refused request, conflict between teammates, bad news such as a role change): objective and acceptable outcomes, verified facts vs stories, a 30-second opening line, likely reactions with responses, a plan B, a follow-up note and clear signals for when HR must be involved.feedback-sbi-writer— Turns raw observations into clear, fair feedback using Situation-Behavior-Impact (plus Intent when constructive): one recognition or improvement message, written and spoken versions, a question to open dialogue, an agreed next step and delivery tips (timing, channel, tone).new-manager-90-day-plan— Builds a 30-60-90 day plan for a manager taking a new team, store, department or project: situation diagnosis (STARS - start-up, turnaround, accelerated growth, realignment, sustaining success), listening tour with stakeholder list and questions, first 1:1 guide, early-wins candidates, what not to change too early, learning goals and milestones per phase.okr-builder— Drafts OKRs for a team, store, department or project from strategy documents and the parent OKRs: 1-3 inspiring objectives, 2-4 measurable outcome key results each with baseline, target, data source and owner, a committed vs aspirational tag, an alignment map to the level above and an anti-pattern check (tasks disguised as KRs, sandbagging, unmeasurable targets).okr-progress-review— Scores progress on a team's OKRs mid-period or at period end: pulls current KR values from Databricks, Tableau, Jira and status updates, computes linear progress vs expected pace, sets a confidence level (on track, at risk, off track) with the reason, names the blockers and the decisions or help needed, and drafts the update for the next level up.one-on-one-prep— Prepares a manager's 1:1 with a direct report: what changed since the last 1:1 (past notes in Drive, Jira, GitHub, Calendar, threads), open commitments on both sides, a prioritized agenda that leaves the report's topics first, coaching questions (GROW) and a running-notes block ready to paste.team-health-check— Designs a short team pulse survey (8-12 items on psychological safety, clarity, workload, dependability, meaning, impact, recognition, growth) as a Google Form outline, then analyzes the answers with strict anonymity (no result for groups under 5), favorability scores, trend vs last pulse, comment themes and 2-3 actions to co-build with the team.team-retrospective— Prepares and synthesizes team retrospectives: picks the right format for the moment (Start-Stop-Continue, 4L, Sailboat, Mad-Sad-Glad, Starfish, timeline), writes the facilitation plan with prompts and timings, pre-fills the period's facts from Jira, GitHub and Calendar, then turns retro notes or a Meet transcript into themes, root causes and 1-3 owned actions with a check on last retro's actions.workshop-designer— Designs a workshop, offsite, seminar or team day from its objectives: expected outputs, diverge-converge flow (double diamond), minute-by-minute agenda with proven activities (1-2-4-All, crazy 8s, dot voting, how-might-we, impact-effort matrix, fishbone), energy curve, roles, materials list for on-site or remote, pre-work and invitation text, and the follow-up plan.
Hr People
calibration-prep— Prepares a talent or performance calibration session for a group of teammates: one-page evidence summaries per person from the managers' reviews, a distribution view of the proposed ratings by manager and team, consistency flags (rating vs evidence, leniency or severity by manager, recency), a bias checklist for the facilitator and an agenda.candidate-communication-writer— Drafts clear, warm and legally careful emails and messages to candidates at every step: application acknowledgement, interview invitation and scheduling with Calendar slots, status update or delay notice, respectful rejection with optional job-related feedback, offer-call follow-up and talent-pool keep-in-touch.career-development-plan— Builds an individual development plan with a teammate or for themselves: aspirations and target role, a gap analysis against the role framework, 3 development goals, 70-20-10 actions (on-the-job stretch, mentoring and exposure, training), milestones with dates, support needed and a review rhythm.engagement-survey-analyzer— Analyzes official company engagement survey results (HR-run waves such as the baromètre social, eNPS) and free-text comments for a team, store, warehouse or department: scores vs previous wave and benchmark, key drivers, themes and sentiment from comments with representative anonymized verbatims, anonymity protection (no group under 5 respondents, no re-identification), and a focused action plan with 2-3 commitments and a team feedback session.exit-interview-synthesizer— Synthesizes exit interviews and leaver feedback across a team, store, warehouse or job family into anonymized themes: primary and contributing reasons for leaving, controllable vs uncontrollable, regretted vs non-regretted patterns at aggregate level, early-tenure signals, retention risks for current teams and 3-5 targeted actions.hr-policy-qa— Answers questions about HR policies and rules (leave, working time, remote work, expenses, training, mobility, parental leave, benefits, code of conduct) strictly from official policy documents found in Drive and Confluence, with a citation for every statement, the scope (country, entity, population) and the document date, and escalates to HR when the policy is missing, unclear or the case is personal.interview-debrief-synthesizer— Consolidates interviewer scorecards and notes for one candidate into an evidence grid per competency, shows where interviewers agree or diverge, flags non-job-related comments and missing evidence, and lists the open questions to settle in the hiring debrief.interview-kit-builder— Creates a structured interview kit for a role: competencies from the job description, behavioral and situational questions with follow-ups, a 1-4 rating rubric with observable anchors per competency, an interviewer split across the loop and a candidate-facing agenda.job-description-writer— Writes an inclusive, skimmable job description and job ad for a store, warehouse, HQ, tech or sourcing role: mission, outcomes for the first year, responsibilities, a short must-have list kept apart from nice-to-haves, gender-neutral wording, a bias-word scan and channel-ready versions.learning-path-designer— Designs a training program or learning path for a group of teammates: needs analysis, learning objectives written with Bloom's verbs, modules sequenced from basics to practice, blended formats (on-the-job, e-learning, workshop, peer coaching) sized for store, warehouse, HQ or tech constraints, an assessment and Kirkpatrick 4-level evaluation plan, and a rollout timeline.offer-letter-drafter— Drafts an offer letter or promise of employment from the official company template found in Drive, filling only facts provided by the user or approved sources, with visible placeholders for anything missing, a consistency check across title, dates, pay, working time and contract type, and a cover email.onboarding-plan-builder— Builds a complete onboarding plan for a new teammate in a store, warehouse, HQ or tech team: pre-boarding checklist before day 1, a day-by-day first week, 30-60-90 day goals, a buddy brief, mandatory and role trainings found in Drive or Confluence, an access and equipment checklist, and check-in rituals with the manager.performance-review-writer— Helps a manager write a fair, evidence-based performance review for one teammate: gathers work evidence from goals, Jira, GitHub, Drive and feedback received, maps it to goals and competencies, drafts strengths and growth areas with concrete examples, checks the wording for bias and vague labels, and prepares the review conversation.self-assessment-coach— Coaches a teammate through their own self-assessment for an annual, mid-year or promotion review: pulls their own work evidence from Jira, GitHub, Drive, Calendar and kudos in Gmail or Chat, turns it into STAR achievements tied to goals and competencies, helps name growth areas honestly, calibrates tone (no under-selling, no inflation) and prepares their questions for the review meeting.team-skills-matrix— Builds a skills matrix for a team from the role framework and teammates' self-declared levels: a people-by-skills grid on a 0-4 scale, coverage per skill against the target, bus-factor and single-point-of-failure alerts, cross-training pairs and a prioritized training plan.
Sales B2B
account-plan— Builds a strategic plan for a key B2B account such as a large club or league, a school network, a multi-site company or a local authority: account snapshot from real history, customer goals, whitespace matrix of sites and offers, stakeholder map with relationship coverage, 12-month objectives, action plan with owners and dates, risks and a review rhythm.account-research— Builds a one-page research brief on a B2B prospect or customer organisation (sports club, school, company, municipality, association): profile, sport and equipment needs, buying calendar, decision makers by role, relationship history found in Gmail, Drive and Airtable, trigger events and the best entry point, with every fact sourced.b2b-proposal-builder— Builds a B2B commercial proposal for sports equipment and services, such as team kits with customisation, school or company equipment, wellbeing programmes or event supplies: executive summary in the customer's words, solution by need, implementation plan (size collection, proofs, delivery, after-sales), options, a pricing table filled only from user or source data, assumptions and terms to confirm.competitive-battlecard— Creates a one-page sales battlecard against a named competitor in a B2B segment (team sport apparel brands, local sports shops, general office or wellbeing suppliers, distributors in public tenders): where they win, where we win, fair landmine questions, answers to their typical claims, proof points and quick wins, built only from sourced and dated facts.discovery-call-prep— Prepares a B2B discovery call or first meeting with a club, school, company or local authority: call objective, hypotheses to test, a 30-minute agenda, SPIN questions in the right order, MEDDICC-lite qualification gaps, likely objections and the next step to secure.objection-handler— Prepares answers to B2B sales objections such as price too high, lead time, quality or durability doubts, happy with the current supplier, no budget, must go through a tender or need to think about it: diagnoses the real objection, gives exploring questions, a sourced response with proof, a reframe in total cost or value per player, and the next step, for calls and written replies.pipeline-review— Reviews B2B pipeline health from Airtable, Databricks (SQL or Polco) or Tableau: coverage versus target, stage conversion and aging against median cycle time, slipped close dates, deals without next step, concentration risk and data hygiene, then gives a ranked next action per deal at risk.prospect-outreach-sequence— Writes a personalised multi-touch B2B outreach sequence (emails, call scripts with voicemail, LinkedIn connection and message texts) for a prospect or a segment such as sports clubs, schools, companies or local authorities, with a cadence, one clear ask per touch and GDPR-compliant B2B prospecting (lawful basis, opt-out, source of data).sales-call-recap— Turns B2B sales call or meeting notes, or a Google Meet transcript in Drive, into three drafts: a recap email to the customer confirming needs, agreements and dated next steps; an Airtable CRM update mapped to the base's real fields with qualification status; and an internal action list.sales-forecast-commentary— Writes the narrative for a B2B sales forecast: forecast versus target and versus last period, commit, best case and pipeline categories, the drivers behind the gap by segment, the deals that move the number, risks and upside with probabilities, the call and the asks to leadership, built from Airtable, Databricks or Polco and Tableau numbers that are cited, never invented.tender-response-builder— Builds the response pack for a public tender or private RFP (municipality, school, region, sports federation, large company): bid/no-bid check, requirement compliance matrix from the tender documents, draft answers for the technical proposal, award-criteria scoring logic, administrative and missing-documents checklist, Q&A questions for the buyer and a reverse schedule to the deadline.win-loss-analysis— Analyses won and lost B2B deals and tenders over a period, from Airtable, Databricks, tender score sheets and deal emails: win rate by segment, size and source, decision-reason coding with evidence, the share of 'no decision', patterns by stage of loss, lessons and concrete actions, with sample-size caveats.
Retail Store Ops
local-sport-event-planner— Plans a local sport event or community activity run by a store: concept tied to a sport universe and the local community, partners such as clubs, schools and associations, run sheet, logistics and equipment, safety and risk assessment, registration and consent, communication plan, budget lines from user data, KPIs and a debrief template.seasonal-operation-planner— Plans a store seasonal operation such as winter sports, back to school, spring cycling, summer outdoor, sales period or Black Friday: objectives from N-1 data, a retro-planning from J-90 to J+14, stock and implantation readiness, staffing and training needs, visual merchandising, services (workshop, rental, second-hand), local communication, risks and a debrief plan.sport-universe-review— Reviews one sport universe or department (rayon) of a store: sales and margin vs N-1 and target, traffic share and conversion where available, stock, availability and weeks of cover, sell-through of the season range, top and flop products, customer reviews, competitor signals, layout and visual merchandising, and a prioritized action list for the department manager.staff-planning-assistant— Drafts a store staffing proposal from traffic and ticket curves and the team's constraints: hour-by-hour need for the floor, checkouts, workshop and logistics tasks, coverage gaps against the current schedule, labor productivity, and a draft rota by role, with a checklist of labor-law and contract points for a human to verify.stock-availability-analysis— Analyzes store stock health from Databricks: out-of-stock rate on the active range weighted by sales, estimated lost sales, broken size runs, phantom stock suspects, overstock and weeks of cover, sell-through, then classifies root causes (forecast, replenishment, supply, receiving, shelf filling, data accuracy) and proposes actions per item group.store-action-plan— Turns store findings from performance reviews, visits, audits, incidents, customer feedback or team ideas into a focused action plan: problem statements, root cause, prioritization by impact and effort, SMART actions with owner roles and deadlines, a KPI and check method per action, follow-up rituals, and an optional tracker draft for Airtable or Jira.store-daily-brief— Builds a store manager's one-screen morning brief: yesterday's sales, traffic, conversion rate and average basket versus N-1 and target, the main driver of the gap, today's agenda, deliveries and the three priorities for the day, from Databricks, Tableau, Calendar and mail.store-incident-report— Writes a factual, privacy-safe store incident report: what happened, a timestamped timeline, people affected described by role only, impact on customers, teammates, sales and operations, immediate actions taken, notifications made, evidence retained and follow-up actions with owners, for safety events, customer or teammate accidents, theft, aggression, equipment failure, IT or till outage.store-performance-analysis— Produces a weekly, monthly or seasonal store performance deep dive: like-for-like revenue vs N-1 and target, the traffic × conversion × average basket decomposition, the split by sport universe and by hour or weekday, labor productivity, availability and margin signals, the root causes and a short list of actions with expected impact.store-visit-report— Prepares and writes a store visit report for an area, regional or store manager: a pre-visit data pack, a customer-path checklist (outside, entrance, sport universes, checkout, workshop, stock room, safety, team), then a structured report with strengths, gaps rated by impact, photos referenced, and an action plan with owners and dates, plus a follow-up email draft.team-huddle-brief— Writes a ready-to-say 5-minute floor team huddle: yesterday's numbers in plain words, today's focus and target, one safety point, one customer story, one piece of recognition and the day's practical info, with a short version for the team chat.workshop-service-review— Reviews a store repair workshop and after-sales service: job volume by type, turnaround time vs promise, on-time rate, backlog in days of capacity, comebacks and rework, attach rate of services to product sales, customer satisfaction and complaints, seasonal peaks such as spring bike servicing or autumn ski prep, and a capacity and action plan.
Customer Service
complaint-escalation-brief— Builds a one-page escalation brief for a serious customer complaint: verified facts, timeline, customer impact, severity rating, applicable policy with sources, resolution options with cost and risk, a recommended resolution for a human decision-maker, and a holding reply to the customer.customer-policy-qa— Answers questions about customer policies such as returns, exchanges, refunds, warranty, repair and workshop services, second-hand buy-back, rental, delivery and click-and-collect, strictly from the official policy documents found in Drive or Confluence, with the exact quote, link, country scope and version date, and says clearly when no source covers the case.customer-reply-drafter— Drafts a reply to one customer message (email, chat, marketplace message, app or store review, social comment) that acknowledges the emotion, states only policy that is sourced, proposes a concrete solution and next step, and adapts length and tone to the channel, with a short and a full variant.kb-article-writer— Writes a knowledge base or help-center article from resolved cases, tickets, workshop notes or product documentation, following Knowledge-Centered Service (KCS): issue in the customer's words, environment, step-by-step resolution, cause, edge cases and when to contact support, in an internal agent version and a customer-facing version.product-review-insights— Mines customer ratings and reviews of a product or range to give product teams evidence they can act on: rating distribution and trend, pros and cons by sport usage and context, suspected defects with counts and first-seen dates, sizing and fit signals, information gaps on the product page, and prioritized actions for design, quality, product page and service.response-template-library— Builds or refreshes a library of reusable customer-service response macros for the top contact reasons: each macro has a usage rule, personalization fields, channel variants for email, chat and public review, a policy source link and an 'if not' branch, and the set comes with a naming convention and a review owner.ticket-triage— Triages a batch of customer tickets or messages: assigns a contact reason, a priority from an impact x urgency matrix, a routing team, flags duplicates and safety or legal cases, and detects emerging issues such as a spike on one product or delivery zone, then outputs a sorted queue and proposed field updates.voice-of-customer-report— Produces a Voice of the Customer report from tickets, reviews, survey verbatims and store feedback over a period: contact-reason volumes and trends, themes with representative anonymized verbatims, root-cause coding (product, information, process, delivery, store service, policy), impact sizing and an owner-assigned action list.
Marketing Ecommerce
ab-test-readout— Reads out a completed A/B test on a site, app, email or campaign: validity checks first (sample ratio mismatch, test duration and full weeks, pre-registered metric, peeking, novelty), then effect size with confidence interval and p-value on the primary metric, guardrail metrics, segment results flagged as exploratory, and a ship, iterate or stop decision with its risk.brand-voice-checker— Checks marketing or product copy against the brand and tone guidelines found in Drive or Confluence, never invented ones: scores each guideline rule pass or fail with the exact passage, flags risky claims (superlatives, unproven performance, green claims, health promises), readability and inclusive language, and returns a rewritten version with changes explained.campaign-brief— Writes a one-page creative and media campaign brief: business and communication objective, audience with a job-to-be-done, one consumer insight, a single-minded proposition with reasons to believe, mandatory elements, channel role per funnel stage, KPIs with baselines, budget split and retro-planning.competitor-watch— Produces a dated competitive watch digest from the sources the user provides or that exist in Drive, Gmail, Slack and Confluence: competitor moves (launches, prices and promotions, campaigns, store openings, services, partnerships), each with date, source and confidence, ranked by impact, with implications and suggested responses for marketing and category teams.customer-persona-builder— Builds evidence-based customer personas from research, reviews, survey answers, customer service themes and aggregated purchase data, framed around jobs-to-be-done and sport practice rather than stereotypes: context and triggers, functional, emotional and social jobs, barriers, decision criteria, channels, with each trait linked to evidence and a confidence level.email-newsletter-writer— Writes a customer email or newsletter ready for the CRM team: goal and segment, 3 to 5 subject lines with an A/B test plan, preheader, scannable structure with one primary CTA, plain-text version, alt text, and a compliance and deliverability checklist (consent, unsubscribe link, sender identity, spam triggers).marketing-performance-report— Builds a campaign or channel performance report from Tableau and Databricks: KPIs vs target and vs last year, funnel breakdown (reach, clicks, conversion, revenue), cost efficiency (CPM, CPC, CPA, ROAS), attribution caveats, incrementality evidence, three insights and next actions.product-page-copy— Writes e-commerce product page copy from the product data sheet: SEO title, short pitch, benefit bullets by sport usage, technical specifications copied only from the source, usage and care tips, FAQ and meta title and description.promo-calendar-planner— Plans a promotional and commercial calendar for a season or a year: sport seasonality peaks, sport events and school holidays, regulated sales periods, promo sequencing with cooling-off gaps, cannibalization and conflict checks, stock and margin guardrails, and a retro-planning per operation.seo-content-brief— Produces an SEO content brief for a writer: target query and search intent, SERP format analysis, keyword cluster with a pillar and supporting pages, H1 to H3 outline, questions to answer, internal links to product and category pages, E-E-A-T evidence from real sport expertise, and on-page specs.social-media-post-pack— Creates a ready-to-review social media post pack for one message across several networks (Instagram, Facebook, LinkedIn, TikTok, X, YouTube Shorts): hook-first copy variants per network, hashtags, call to action, visual or video brief, WCAG-compliant alt text and captions, and a posting plan.
Product Design
competitive-product-teardown— Compares competitor products with our own, feature by feature and benefit by benefit, using only the sources provided or found (product pages, data sheets, lab or field test reports, team teardown notes, reviews, app screenshots): claimed versus measured specs, price observed with date, design and construction choices, user experience, durability and repair signals, then table stakes, differentiators, gaps and opportunities.eco-design-review— Reviews a sport product concept or an existing product through eco-design levers: materials and their mix, material efficiency and weight, durability, repairability and spare parts, disassembly and mono-material choices, packaging and transport volume, use phase and end of life (second-hand, rental, take-back, recycling).field-test-protocol— Designs a field or user test protocol for a physical sport product or prototype: testable hypotheses with pass criteria, tester profiles and screener, test conditions and the conditions log, objective and subjective measures with scales, comparison and blinding design, safety risk assessment with stop rules, informed consent, logistics and a ready-to-print test sheet.prd-writer— Writes a product requirements document for a digital feature (Company app, e-commerce site, store or teammate tool): problem and evidence, target users and jobs, goals with metrics, non-goals, user stories, functional and non-functional requirements with priorities, UX notes, analytics events, dependencies, risks, rollout and open questions.product-brief— Writes a product brief for a physical sport product: the target practitioner and practice level, use conditions, jobs-to-be-done and pains with evidence, the benefits to deliver, hard constraints (norms, safety, price target, timing), success metrics and the open questions to close before design starts.release-notes-writer— Writes release notes from Jira fix versions and GitHub releases, merged pull requests or tags, in two versions: user-facing notes in plain benefit language (app store text, website or in-app what's new, store teammate tool update) and internal notes for support, stores and engineering (changes, known issues, rollout, how to report problems).research-synthesis— Synthesizes user research material (interview notes, Meet transcripts, diary entries, usability test notes, field test sheets) into evidence-backed insights: coded observations, affinity clusters, insight statements with evidence strength and counter-evidence, then opportunities framed as an opportunity solution tree.roadmap-update— Prepares a product roadmap update for stakeholders in now, next, later format: outcomes rather than feature lists, what shipped and what it changed, what moved and why, confidence per item, dependencies, risks and explicit asks, adapted to the audience (leadership, business teams, stores, partner teams).sprint-planning-assistant— Prepares a Scrum sprint planning from the Jira backlog: capacity from availability (absences, ceremonies, run and support load) and past velocity, a proposed sprint goal, a selection of ready stories that fits the forecast, readiness gaps, dependencies and risks, and the questions for the team.user-research-plan— Plans a user research study for a sport product or a digital product: decision to inform, research questions, the right method for the question (interviews, contextual inquiry in the practice place, diary study, usability test, survey, data analysis), sample and recruiting screener, discussion guide, consent and data handling, timeline and roles.user-story-writer— Turns a PRD, an epic, a workshop output or a rough idea into Jira-ready user stories: vertical slices with a clear persona and value, INVEST check per story, Gherkin acceptance criteria (Given, When, Then) including edge and error cases, definition-of-ready gaps, dependencies and a suggested order.
Data Analytics
dashboard-spec-writer— Writes a build-ready specification for a new or redesigned dashboard (Tableau or other): audience and decisions, the questions it must answer, KPI list with definitions and source tables, layout wireframe in text, filters and drill-downs, comparison bases, refresh and freshness rules, access and row-level security, acceptance tests.data-dictionary-builder— Builds a data dictionary for one or more Databricks Unity Catalog tables: table purpose, grain, primary key, partitioning, owner and freshness, then for every column its type, business definition, example value pattern, allowed values or range, NULL share, PII flag and join keys, drawn from DESCRIBE, information_schema, column comments, profiling queries and existing documentation, with gaps marked to confirm.data-quality-check— Audits a Databricks table or dataset on the six data-quality dimensions (completeness, uniqueness, validity, consistency, freshness, accuracy against a reference) with ready-to-run read-only SQL checks, thresholds, results, a severity per finding and a fix owner, plus reusable monitoring queries.data-question-answerer— Answers a business question with real data from Databricks (SQL MCP or the Polco natural-language data assistant) or Tableau: finds the right source, runs read-only queries, and returns the number with its definition, comparison base (N-1, target, previous period), the query or view used, the date the data was pulled and the caveats.databricks-sql-builder— Writes, explains and optimizes read-only Databricks SQL on Unity Catalog from a business question: discovers the right catalog, schema and tables, checks columns with DESCRIBE, builds a commented query with CTEs, adds validation queries (row counts, duplicates, totals) and explains every assumption.experiment-design— Designs an A/B test or controlled experiment before launch: hypothesis, primary metric and guardrail metrics, unit of randomization, minimum detectable effect, sample size per arm (two-proportion formula, alpha 0.05, power 0.8, with the 16·p(1−p)/δ² rule of thumb) and duration from real baseline traffic, assignment and exposure rules, pre-registered decision rule and pitfalls (peeking, novelty, sample ratio mismatch).insight-storyteller— Turns analysis results (query outputs, dashboard figures, spreadsheets, notebook findings) into a decision-oriented data story: one headline that states the so-what, three supporting insights each with its number and source, the recommended decision, chart suggestions with the right chart type and title, caveats and confidence, in formats for a slide, an email or a Chat or Slack message.kpi-definition-card— Produces a KPI definition card that removes ambiguity: business question, exact formula with numerator and denominator, grain, filters and exclusions, source table in Unity Catalog, reference SQL, owner, refresh, edge cases, known pitfalls and related metrics, checked against existing definitions in Confluence, Drive and Tableau.metric-anomaly-investigator— Investigates an unexpected drop or spike in a business metric with a disciplined method: first rules out data issues (freshness, duplicates, definition or tracking changes), then checks calendar and seasonality against aligned N-1 weeks, decomposes the metric into its drivers (e.g.tableau-dashboard-explainer— Explains a Tableau dashboard or view in plain language: what question it answers, what each chart, KPI tile, color and filter means, how the metrics are defined, how to read it correctly, the three to five takeaways visible right now, and the caveats (data freshness, filters applied, definitions, small bases).
Engineering It
architecture-decision-record— Writes an Architecture Decision Record in Nygard or MADR format: context and forces, decision drivers, options considered with honest pros and cons, the decision and its rationale, positive and negative consequences, reversibility and a revisit trigger, and links to the decisions it supersedes.backlog-grooming— Grooms a Jira backlog before refinement: finds duplicates, stale and zombie tickets, vague stories without acceptance criteria, oversized items to split, missing dependencies and bugs without severity, scores each item against INVEST and a Definition of Ready, and produces a refinement agenda with sizing questions and proposed edits.bug-report-writer— Turns a vague problem report, Slack thread, support ticket, screenshot description or log excerpt into a Jira-ready bug report: clear title, reproducible steps, expected versus actual, environment, impact, severity separated from priority, evidence links, a duplicate check and open questions.code-explainer— Explains a code file, function, pull request or area of a GitHub repository for a newcomer, a non-developer or a reviewer: what it does in plain words, where it sits in the system, the main flow step by step with file and line references, key concepts and jargon, data in and out, side effects and dependencies, gotchas, and where to start reading or changing it.engineering-standup-summary— Builds an engineering team standup summary from real activity in Jira and GitHub (plus Slack or Chat): per person or per work item, what moved since the last standup, what is planned today, blockers and items waiting on someone, PRs waiting for review, aging work in progress, and risks to the sprint goal.incident-postmortem— Writes a blameless SRE-style incident postmortem from the incident channel, tickets, alerts and meeting notes: summary, customer and business impact, SLO and error budget consumed, minute-by-minute timeline with detection and mitigation times, root cause through 5 whys, contributing factors, what went well, where we got lucky, and prioritized action items with owners.incident-status-update— Drafts incident status updates during an ongoing outage or degradation, in three versions from the same facts: technical update for the incident channel, plain-language update for business and store teams, and a customer-facing status message for approval, each with severity, impact, current status, next steps and the time of the next update, at a cadence matched to severity.pr-description-writer— Writes a reviewer-friendly GitHub pull request description from the diff, commits and linked Jira issue: a Conventional Commits title, what changed and why, how it was tested, risks and rollback, deployment notes and a review guide that tells reviewers where to look first.pr-review-assistant— Reviews a GitHub pull request like a staff engineer: checks the diff against the linked Jira ticket, then lists findings by severity (blocker, major, minor, nit) across correctness, security (OWASP Top 10, leaked secrets), performance, tests and readability, each with file and line, why it matters and a suggested fix, plus a verdict and ready-to-paste review comments.release-readiness-check— Runs a go/no-go readiness check for a release from Jira and GitHub: scope done versus planned, open blockers and critical bugs, CI and test status as reported, database migrations and backward compatibility, feature flags, rollback plan, monitoring and on-call, change freeze and peak-period risk, and stakeholder communication, ending with a Go / Go with conditions / No-go recommendation and the exact conditions.runbook-writer— Writes an operational runbook for a service, alert or recurring operation: when it applies (alert names, symptoms), prerequisites and access, fast triage, diagnosis branches, numbered remediation steps each with an expected result and a verification, rollback, escalation path and communication hooks, built from code, configs, past incidents and team docs.tech-spec-writer— Writes a Google-style technical design document for a feature or system change: context and scope, goals and non-goals, the proposed design with APIs, data model and sequence, alternatives considered with trade-offs, cross-cutting concerns (security, privacy, reliability with SLOs, cost, observability), migration and rollout plan, and open questions for reviewers.
Project Management
lessons-learned— Produces a project lessons-learned report at a phase end or project close: objectives achieved vs planned (scope, time, cost, outcome KPIs), what worked to repeat, what did not with its root cause, and actionable recommendations owned by a process or a team, plus a facilitation guide for the review session and a reusable summary for future projects.process-improvement-kaizen— Runs a Lean improvement of an operational or office process: SIPOC to frame it, current-state map with time and volume data, waste hunt with the 8 wastes (DOWNTIME), root-cause analysis with Ishikawa and 5 whys, future state, quick wins vs projects ranked by impact / effort, and a PDCA plan with before / after KPIs.project-charter— Drafts a one-page-to-three-page project charter in a PMI / PRINCE2-lite structure: business justification, SMART objectives, scope in and out, deliverables, stakeholders and roles, milestones, budget envelope, top risks, tolerances and governance, with every gap flagged instead of invented.project-plan-builder— Builds a project plan from a scope or charter: a deliverable-oriented WBS that respects the 100% rule, work packages with owners and duration estimates, milestones, dependencies (finish-to-start etc.), a forward / backward pass to find the critical path and float, and a timeline table ready for Google Sheets or Jira.project-status-report— Writes a weekly or bi-weekly project status report with an evidence-based RAG rating per dimension (schedule, scope, cost, risks), using explicit thresholds rather than gut feeling: progress vs plan from Jira, milestone forecast, top risks and issues, decisions and help needed, next steps.raid-log-builder— Builds or refreshes a RAID log (risks, assumptions, issues, dependencies) for a project: each risk written as cause, event, effect, scored probability × impact on 1-5 scales with defined anchors, a response strategy (avoid, reduce, transfer, accept), owner, trigger and review date, plus assumptions to validate, open issues by severity and cross-team dependencies.sop-writer— Writes a standard operating procedure (SOP) that people can follow on the job: purpose, scope, roles (RACI), prerequisites, numbered steps written as one action per step with the expected result, control points and records, safety and quality warnings, exceptions and escalation, revision table, plus suggestions for visuals and a one-page job aid.stakeholder-map— Maps the stakeholders of a project or change on a power / interest grid, assesses current vs desired engagement level (unaware, resistant, neutral, supportive, leading), and builds an engagement plan per stakeholder: what they care about, key message, channel, frequency, owner and next touchpoint.steering-committee-pack— Prepares the content of a steering committee (COPIL) pack: one-slide executive status with RAG, progress against milestones and budget, the decisions required framed as question, options with trade-offs, recommendation and deadline, top risks and escalations, and a pre-read email plus the minutes template.
Finance Procurement
budget-variance-analysis— Analyzes actuals vs budget, forecast or last year for a P&L, cost center, store, sport or project: variance table with favorable / unfavorable signs, materiality filter, price / volume / mix decomposition for sales and margin, rate vs volume for costs, timing vs permanent split, root-cause explanations and corrective actions with owners.business-case-builder— Builds an investment or project business case from the user's own figures: problem and strategic fit, options including do-nothing, cost (CAPEX, OPEX, one-off, run) and benefit model per year, NPV, IRR, payback and discounted payback with formulas shown, sensitivity and break-even on the key drivers, scenarios, non-financial benefits, risks and a recommendation.monthly-finance-commentary— Writes the monthly financial commentary for management on a P&L (company, country, region, store, sport or business unit): headline, KPI table vs budget, forecast and last year for the month and year to date, sales and margin bridge, cost and operating result drivers, one-offs and timing effects, cash and stock if available, outlook, risks and opportunities, and the asks.price-positioning-analysis— Analyzes price positioning against competitors from provided or connected price data: like-for-like product matching with match quality, price index per product (own price / competitor price × 100), weighted index per family and sport, gap distribution, regular vs promotional prices, key value items, price ladder coherence, and recommendations for the pricing team.purchase-request-justification— Writes a short, approval-ready justification for a purchase request: the need and what happens without it, alternatives considered (reuse, rent, cheaper option, do nothing), quotes compared, total cost of ownership over the useful life, budget line and remaining budget, approval path and required documents found in the internal procurement policy, and the text to paste in the purchase request tool.supplier-evaluation— Evaluates and compares suppliers with a weighted scorecard: knock-out criteria first (social compliance, mandatory certifications, sanctions), then quality, total cost of ownership, delivery and lead time, capacity, social and environmental performance, innovation and risk (financial, concentration, geopolitical), each scored 1-5 on written anchors with evidence, plus weight sensitivity, risk view and development actions.supplier-rfq-builder— Builds a buyer-side RFQ, RFP or RFI pack for goods or services: context and scope, functional and technical requirements (must vs should), indicative volumes, commercial terms and Incoterms, a cost breakdown template, quality and social and environmental requirements, the evaluation grid with weights announced upfront, timeline, Q&A and submission rules, plus the bidder list check and a fair-process checklist.
Legal Compliance
ai-use-case-risk-screen— Screens an AI use case, tool or agent against the EU AI Act (Regulation (EU) 2024/1689): checks Art.contract-summary— Summarizes a contract or amendment into a one-page brief: parties, purpose, term and renewal, obligations of each side, price and payment terms, service levels, liability caps and indemnities, IP, data protection, termination rights, governing law, key dates and a RAG list of clauses that deserve legal attention, every point cited to its clause number.gdpr-processing-check— Screens a new or changed process, tool, project, data flow or vendor for GDPR before launch: personal data and special categories (Art.nda-triage— Checks a non-disclosure agreement against a standard checklist and gives a green, amber or red verdict per clause and overall: mutual or one-way, definition of confidential information, carve-outs, permitted disclosures, term and survival, return or destruction, residuals, non-solicit or non-compete riders, remedies, governing law, with suggested fallback wording and the questions for Legal.policy-compliance-check— Checks a document, process, project, campaign or practice against one or more internal policies found in Drive or Confluence: breaks each policy into testable requirements, maps the evidence, rates each requirement compliant, partial, gap or not assessable with exact citations on both sides, and proposes remediation actions with owners.regulatory-watch-digest— Produces a dated regulatory watch digest on a topic (for example consumer law, product safety, data protection, AI, sustainability reporting, packaging, labour) from the sources the user provides or that are found in Drive, Gmail newsletters, Confluence and Slack: what changed, legal status and stage, key dates, who is affected inside Company, impact rating, actions and owners, each item linked to its source.
Sustainability
circular-offer-ideas— Generates and screens circular economy offers for a product category, sport, store or B2B segment: repair and maintenance, second-hand buyback and resale, rental and subscription, take-back and recycling, durability and spare parts.csr-data-request— Builds a sustainability or CSRD-related data request for internal teams, stores, warehouses or suppliers: the indicator list mapped to ESRS topics or GHG Protocol scopes and categories, precise definitions, units, reporting period and boundary, calculation method, evidence required, data quality flags, owners, deadline, a ready-to-fill template and the cover email, plus a check of returned data.green-claim-checker— Reviews environmental and sustainability claims in product pages, labels, packaging, ads, social posts or press releases against EU consumer law as amended by the Empowering Consumers for the Green Transition directive (EU) 2024/825: flags generic claims (eco-friendly, green, responsible), offset-based neutrality claims, whole-product claims based on one aspect, unverified labels and future pledges, rates each claim red, amber or green, lists the evidence needed and proposes compliant rewrites.
Knowledge Search
cross-source-search— Searches across Drive, Confluence, Jira, Slack, Google Chat, Gmail and GitHub with a deliberate strategy (query reformulation, French and English synonyms and acronyms, recency filters, source authority ranking), then returns one consolidated answer where every claim is cited, conflicting sources are shown side by side, and a confidence level is given.document-comparison— Compares two documents or two versions of the same document (Google Docs, PDFs, Confluence pages, contracts, policies, specs, price lists) and reports what changed section by section: additions, deletions, modified wording with before and after quotes, changed numbers and dates, contradictions between the documents, and the practical impact of each change, ranked by importance.expert-finder— Finds the teammates most likely to know about a topic from work signals the user can see (authors and editors of Drive and Confluence pages, Jira assignees and commenters, GitHub committers and reviewers, active participants in Chat and Slack channels, meeting organizers), explains the evidence behind each suggestion, and drafts a short, respectful contact message.glossary-builder— Builds a team or domain glossary of acronyms, internal jargon, project code names and business terms from the documents, pages, tickets and channels the user points to: each term with its expansion, a plain-language definition taken from the sources, FR and EN equivalents, an example of use, related terms and a citation, with ambiguous or conflicting meanings flagged.knowledge-capture-page— Turns scattered knowledge (Chat or Slack threads, email chains, meeting notes, Meet transcripts, Jira comments) into a clean, reusable Confluence or Google Docs page: a decision record (context, options, decision, rationale, consequences) or a how-to (prerequisites, numbered steps, troubleshooting), with owner, review date, sources and open points, after checking that no page already exists.long-document-digest— Digests a long document (report, study, strategy deck, standard, tender file, regulation, thesis, meeting transcript) into a navigable brief: a one-paragraph bottom line, a structure map with page or section references, key points per section, every number and date worth keeping with its location, defined terms, open questions and what it means for the reader's role.topic-digest— Builds a digest of everything that happened on a topic, project or initiative over a period across Gmail, Chat, Slack, Drive, Confluence, Jira, GitHub and Calendar: a dated timeline, decisions made and by whom, current status, open issues and risks, who owes what, and what to watch next, with a citation for every item.
Ai Adoption
ai-use-case-finder— Maps the recurring tasks of a role or team to concrete AI opportunities in Gemini Enterprise: task inventory with frequency and time spent, AI pattern per task (summarize, draft, search, analyze, classify), value and feasibility scores, which existing library skills already apply, data and connector needs, risk tier, and a prioritized 30-day adoption plan with quick wins.prompt-improver— Rewrites a user's prompt for Gemini Enterprise into a precise, reusable instruction: role, goal, context, which connected sources to search (Drive, Gmail, Calendar, Jira, Confluence, Slack, Databricks, Tableau…), constraints, output format and quality bar, with a diagnosis of what was missing and a short and a full version.skill-builder— Interviews the user about a recurring task and writes a new, ready-to-upload SKILL.md for Gemini Enterprise that follows this library's standard: valid frontmatter, a pushy description with English and French triggers, the seven required sections, concrete method, sources per connector, an exact output template, testable quality checks and guardrails, plus test prompts.