Product & Planning

hekmon8 Skill

Use when searching public YouTube videos for creator research, launch monitoring, topic discovery, and normalized video evidence through Vernclaw CLI.

ihudak Skill

Architecture-authoring workflow (Product Architect phase, sub-project 3 of the VI-creation flow). Grounds on the mounted implementation repos (architect-driven discovery — no PRs) and authors an ARD for a VI (create-ard: <VI-KEY>) or an Epic (create-ard: <VI-KEY> <Epic-KEY>, inheriting the VI-level ARD), against _shared/ard-format.md, gated by the Opus ard-reviewer, written to $SPECS_PATH/specifications/<KEY>-<slug>/. Optional; scoped; product-architecture level (no code writing). Introduces the pa role. Activated when the user prompt starts with "create-ard:".

ihudak Skill

Dynatrace corporate style guide rules for writing Epics, PRDs, ARDs, product documentation, and other planning documents. Load this skill when writing or editing content that must follow Dynatrace terminology, trademarks, voice/tone, and formatting standards. Triggers on: Dynatrace style, DT terminology, write epic, write PRD, write ARD, Dynatrace content, style guide, corporate writing.

kanfu-panda Skill

创建 PRD 文档（自动化生成 + 自检 + handoff）

kanfu-panda Skill

全自动 PDLC 新功能开发（串联 PRD→设计→TDD→实现→评审→发布）

archive-dot-com Skill

Calculate influencer campaign ROI and build a leadership-ready narrative summary from raw performance data. This skill should be used when calculating ROI for a creator campaign, building a campaign performance report for leadership, turning raw influencer metrics into an executive summary, computing CPM CPE ROAS and EMV for a creator program, summarizing campaign spend versus revenue for a stakeholder meeting, proving influencer marketing ROI to a CMO or VP, creating a campaign wrap report with financial metrics, or comparing influencer channel efficiency against paid social. For setting KPI targets before a campaign launches, see performance-benchmark-setter. For tracking creator posting compliance, see creator-posting-compliance-tracker. For full end-of-campaign reporting with qualitative analysis, see post-campaign-creator-scorecard. For building UTM links to enable attribution, see utm-parameter-builder.

archive-dot-com Skill

Analyze an influencer's audience demographics to determine whether their followers match your target customer, with a clear pass/fail verdict. This skill should be used when evaluating audience fit, checking influencer demographics, analyzing audience data, reviewing an audience breakdown, assessing demographic alignment, vetting an influencer's audience, determining if a creator's followers match your target demo, reviewing a platform export or stats screenshot, pasting influencer stats, grading audience quality, deciding whether an influencer's audience is a good fit, checking if this creator is worth it, running an audience report, comparing creator audiences, or evaluating audience overlap with target demo. For overall creator vetting beyond demographics, see creator-vetting-scorecard. For finding new creators, see creator-discovery.

automattic Skill

Manage a remote WordPress.com site with wpcom_request, including API namespace selection, endpoint discovery, content/template/theme/plugin operations, response-size limits, and visual verification.

davidvujic Skill

[Internal sub-skill of `polylith-migrate-orchestrator`. Do not load directly — load `polylith-migrate-orchestrator` first, which drives all phases.] Verify that the migration did not break the project by running test discovery, checking for circular imports, and ensuring the compatibility shim covers all necessary symbols.

leadupofficial Bundle

Audit a LeadUp client website or SaaS site and produce a clear SEO action plan covering technical SEO, on-page fixes, meta titles and descriptions, internal linking, schema, content gaps, and a 30/60/90 day roadmap for Indian and international audiences. Use when the user says "seo audit", "improve seo", "technical seo", "meta title", "search ranking", "seo roadmap", or "on page seo".

leadupofficial Bundle

Bootstrap a new LeadUp project from an idea, spec, or client requirement. Produces PROJECT.md, CLAUDE.md, STATUS.md, DEPLOY.md, SECURITY.md, README.md, a placeholder .env.example, plus a stack recommendation, database plan, MVP roadmap, and deployment plan. Use when the user says "start new project", "new SaaS idea", "build new app", "create project", "project kickoff", or "new LeadUp project".

leadupofficial Bundle

Plan a paid SaaS MVP for a LeadUp client or LeadUp's own product — target users, first paid feature, MVP modules, user roles, tenant model, admin panel scope, subscription pricing ideas, database plan, integrations, and launch roadmap. Tuned for Indian small-business SaaS plus international startups. Use when the user says "saas mvp", "build saas", "mvp plan", "paid mvp", "saas idea", or "subscription app".

leadupofficial Bundle

Plan the feature roadmap for a LeadUp SaaS or client product. Splits ideas into must-have, premium, and AI-powered features, defines user roles, sorts MVP vs Phase 2 vs Phase 3, scores monetization impact and complexity, and recommends the next feature to build. Use when the user says "feature planning", "feature ideas", "premium features", "what features to add", "saas features", "future roadmap", or "more intelligent options".

leek Bundle

Turn the current conversation into a spec (PRD) and save it as markdown under .scratch/: no interview, just synthesis, with Laravel test seams chosen from the tdd ranking rules rather than asked about.

leek Bundle

Two-axis review of the diff since a fixed point: Standards (repo conventions) and Spec (ticket/PRD fidelity). Use when the user wants to review a branch, PR, WIP changes, or asks to "review since X".

team-attention Skill

Hoyeon implementation reference discovery workflow for Codex. Use when the user invokes "$hoyeon-reference-seek" or asks for internal patterns, open-source references, GitHub examples, official docs, or comparable implementations. This adapter loads the canonical reference-seek skill and follows its Codex runtime surface.

trycomp-io Bundle

Gera um kit completo de onboarding (plano 30/60/90, checklist IT, stakeholder 1:1s, email de boas-vindas, script do buddy, template de 1:1 do manager) em HTML printable + Markdown editável. Receba inputs do CHRO/manager (cargo, nível, start date, contexto da empresa) e produza o kit personalizado. Dual-mode: works in Claude Code (script + rich output file) AND Claude Cowork (output generated inline as markdown, plus a self-contained HTML artifact when available). Trigger em "onboarding kit", "plano 30/60/90", "checklist de onboarding", "kit de integração", "preparar onboarding de novo colaborador", "boas-vindas para novo funcionário". Mantida pela Comp.

trycomp-io Bundle

Gera um assessment HTML interativo de maturidade de dados de RH em 5 níveis (Ad-hoc, Operacional, Reporting, Analytics, AI-native) × 5 dimensões (Coleta, Governança, Reporting, Análise, Tech & AI). 15 perguntas, ~5 minutos, output com nível por dimensão + roadmap personalizado pra avançar. 100% client-side. Dual-mode: works in Claude Code (interactive HTML assessment via script) AND Claude Cowork (conversational assessment + markdown scorecard, plus a self-contained HTML artifact when available). Trigger em "maturidade de dados de RH", "HR data maturity", "diagnóstico de people analytics", "qual o nível do meu RH em dados", "avaliação de people ops", "como estamos em analytics". Mantida pela Comp.

trycomp-io Bundle

Constrói a estratégia de People + OKRs amarrados à estratégia de negócio. Coleta conversacionalmente prioridades de negócio, dores de people, contexto de headcount/crescimento, horizonte e restrições, e gera um one-pager: 3-5 prioridades estratégicas, cada uma ligada a um objetivo de negócio, com Objective, 2-4 Key Results mensuráveis, iniciativas, owner e métrica, mais riscos e dependências e um roadmap trimestral. Output HTML one-pager + markdown. Dual-mode: works in Claude Code (Python script renderiza HTML rico) AND Claude Cowork (coleta conversacional + markdown output, plus a self-contained HTML artifact when artifacts are available). Trigger em "estratégia de people", "people strategy", "construir OKRs de RH", "OKRs de people", "estratégia de RH na uma página", "people strategy on a page", "amarrar RH à estratégia". Mantida pela Comp.

vchirrav-eng Skill

Run Nmap for network discovery and security auditing. Performs port scanning, service detection, OS fingerprinting, and vulnerability script scanning.

stephenrogan Bundle

Tracks customer org charts, contact roles, engagement frequency, and relationship coverage across accounts. Maintains a structured stakeholder map that identifies champions, economic buyers, influencers, and coverage gaps. Use when asked to map stakeholders, track customer contacts, build an org chart, identify relationship gaps, assess stakeholder coverage, or when any workflow needs to know who matters at an account and how recently they have been engaged. Also triggers for questions about contact mapping, multi-threading assessment, stakeholder analysis, single-thread risk, or relationship breadth.

stephenrogan Bundle

Logs customer feature requests from calls, tickets, and emails, links them to the product roadmap, tracks their status, and surfaces updates to CSMs when requested features ship or are declined. Use when asked to log a feature request, track product requests, link customer needs to the roadmap, monitor when a requested feature is available, or when any customer interaction surfaces a product enhancement need. Also triggers for questions about feature request management, roadmap tracking, customer-requested product changes, or product backlog from the CS perspective.

stephenrogan Bundle

Monitors for stakeholder changes at customer accounts including champion departures, new executive hires, reorganisations, and role changes. Detects changes from CRM updates, LinkedIn signals, and engagement pattern shifts. Use when asked to track contact changes, monitor for champion departure, detect reorgs at customer accounts, set up stakeholder change alerts, or when any workflow needs early warning of relationship disruption. Also triggers for questions about contact monitoring, org change detection, stakeholder continuity, or relationship risk from personnel changes.

wei18 Bundle

Generate a single-file HTML iOS design mockup from a written spec (PRD / requirements / user stories) — a designer-style user-flow canvas: iPhone frames, SVG navigation arrows, a design-tokens panel. Use when asked to "turn this spec into a mockup", "show me the screens", "design this", "visualize this app", "make a Figma-like flow", or to communicate iOS designs to PMs/stakeholders without a working prototype. Not a clickable prototype, not Figma files, not SwiftUI/production code. Do NOT fire when merely discussing/planning/reviewing screens conceptually, or when no visual artifact was requested.

wei18 Skill

For repos using the `spec-phase-orchestration` doc layout (design.md / foundations.md / plan.md / methodology.md), route mid-discussion stray ideas to the matching file's §Backlog section by topic — product → design.md; tooling → foundations.md; implementation step → plan.md; collaboration → methodology.md; unclassifiable → today's meeting log §Open questions. Invoke when a stray idea pops up during focused work, when reviewing a meeting log for parking lot items, or when asked "where does this idea go".

wei18 Skill

How to distribute Claude Code skills for reuse across repos and how to install them — as a plugin via a marketplace, a pinned git-submodule with committed project-scope settings, or globally. Covers the depth-1 discovery rule (why a bare folder/submodule of skills is NOT found), the `settings.json` schema, aggregating other skill repos, and the gotchas. Invoke when sharing skills across projects, wiring a skill plugin into a repo, choosing flat-skills vs plugin, or asked "why aren't my submodule'd skills showing up / how do I install project skills".

zfinix Skill

Create and execute structured plans for multi-step tasks. Use when the user gives a complex task spanning multiple files, asks for a plan or roadmap, says "break this down", or when a task cannot be completed in a single turn. Also use when the task touches several subsystems or the user wants to review the approach before you act.

rubyeyedreaper Skill

Use when work must continue past the item in hand rather than stop with it — an unattended or overnight run, a /loop or /autoloop iteration, a session told to keep going until the roadmap is empty, a checkpoint reached with work still queued, or a run whose context is filling before the work is done. Also use when the next thing to do must be chosen and started without a human in the turn.

rubyeyedreaper Bundle

Use when the user asks what to work on next, wants to start the next thing, adds or tracks a feature, page, function or integration, initializes a project, asks what is left to build, wants work batched into parallel waves or phases, wants competing items prioritized or ranked, or the roadmap needs reconciling against reality.

rubyeyedreaper Bundle

Use when work must be driven to exhaustion across many delegated sessions rather than one at a time — an endless gauntlet, a campaign that re-arms instead of ending, "keep going until every issue and roadmap item is done", a batch that finished while new work kept arriving, or a coordinator asking what is left across the roadmap and the tracker at once. Also on "re-arm", "rearm", "next wave", "quick wins first", and when a campaign looks finished and the loop must decide whether to start another.

rubyeyedreaper Bundle

Use when starting or switching to a project subtree, when a project's own README, changelog, ADR set, decision ledger, roadmap or data-provenance manifest may be missing, or when deciding whether a project is initialized, active, dormant or completed.

rubyeyedreaper Bundle

Use when one roadmap item is too big for a single plan — a feature spanning multiple PRs, sessions or agents. Decomposes an objective into cold-start-executable construction steps with a dependency graph, registers them as roadmap children, and gates the result on a mechanical check. Not for single-PR work (superplan) or for choosing what to build (roadmap).

rubyeyedreaper Bundle

Use when a loose idea is too big for one agent session and the way to the finish line is not visible yet — "where do I even start", "we need to figure out X before we can plan", a space with several open questions that hang on each other. Charts a committed markdown decision map: a named destination, explicit out-of-scope, typed tickets (research / prototype / grilling / task, each HITL or AFK), blocking edges, and a fog frontier that advances one resolved ticket at a time. Produces decisions, not deliverables. Not for scoring options against criteria (`decision-matrix`) or for sequencing work already decided (`roadmap`, `blueprint`).

kehwar Skill

Write a development log entry capturing implementation decisions, bug findings, insights, or implementation details. Entries are saved as Markdown files in docs/development-log/. Use when user says "write a dev log", "log this decision", "document this", "write a dev journal entry", "record what happened", or after completing a plan phase, PRD, session, or set of commits.

kehwar Bundle

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

kehwar Bundle

Review the current code state along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when a feature or implementation needs a holistic review of current code against a spec and standards.