Product & Planning

ericgandrade Bundle

This skill should be used when the user wants an overview of the Modern Product Operating Model — a collection of 6 composable product skills covering strategy, discovery, architecture, delivery, AI-native development, and leadership. Use when unsure which product skill to invoke or when exploring the full operating system.

ianlkl11234s Skill

只在使用者明確要求 session 收尾、整理專案記憶、或 commit memory 時使用。不因一般任務完成、狀態報告或程式碼 commit 自動觸發。

iusztinpaul Bundle

Search the web via the Bright Data CLI — `bdata search` for Google/Bing/Yandex SERP, `bdata discover` for intent-ranked semantic results. Use when the user wants SERP results, needs URLs to feed into scraping, or wants semantic web discovery with optional page content. Hands off to `scrape` once target URLs are chosen, and to `data-feeds` when the user wants structured data from a known platform. Requires the Bright Data CLI; proactively guides install + login if missing.

jeisaacs Skill

Creates vertically-sliced Linear sub-issues from a Linear briefing document, exploring the frontend and backend repos to produce fully-detailed issues an AI can pick up and implement. Updates parent issues with an overview table, updates the briefing document with confirmed decisions and links, and sets all sub-issues to Backlog with estimates and priorities. Use when given a Linear document URL and parent issue identifiers for frontend and backend work.

jeisaacs Bundle

Get feedback from simulated CTO, UX, Sales, Executive, and User Advocate perspectives. Use when: stakeholder feedback, simulate review, pre-review, stakeholder perspectives.

jtmthf Bundle

Use this skill whenever the user wants to model a domain, run an event storming workshop, identify bounded contexts, design aggregates, or resolve any DDD modeling challenge. Unlike general DDD knowledge (which you already possess), this skill provides a structured facilitation process — phased discovery, one-question-at-a-time interrogation of domain experts, anti-pattern detection, and brownfield codebase reverse-engineering. Triggers on domain modeling, DDD, event storming, aggregate design, bounded context, context map, domain discovery, or any request to map, untangle, or understand a system's domain structure.

skillmedev Skill

Generates a structured candidate-interview question set where every behavioral (STAR) and role-specific item maps to a defined competency and ships with strong/borderline/red-flag answer anchors plus delivery notes. Use when someone asks "write interview questions for this role", "build an interview loop", "turn this rubric into questions per interviewer", or is planning a hiring interview, building a question bank, or standardizing how a panel assesses candidates. Do NOT use to consolidate completed scorecards into a hire decision - use interview-debrief-synthesizer instead; do NOT use for user-research or customer discovery interviews - use interview-guide-builder instead; do NOT use to build the competency rubric or scorecard itself - use hiring-scorecard or screening-rubric-builder instead.

abdul977 Bundle

Act as technical lead over a fleet of Claude Code agents to take a codebase from 'mostly built' to 'actually shippable'. Use when the user wants you to take over a project — rewrite or reconstruct the PRD, audit every page and flow for missing UI and weak logic, spawn and brief background agents to build the gaps, browser-test the result as real users, report defects back to those agents, and run on a loop until they come back to a finished product. Also use for enterprise-readiness audits, 'is this production ready', 'find what's missing', 'run agents and oversee them', or any request to own delivery rather than complete a single task. Covers agent briefing and file-ownership, the oversight cycle, browser verification, money/PII/authorization security review, migration safety, and the final handover.

blueprint-conformance Skill

Summarize any long text into a short one, or when meeting notes need condensing into actions, or when a report needs an executive summary at the top, or when a changelog needs a one-paragraph overview, or when a research page needs an abstract for reviewers, or when a spec needs a preamble that states the change, or when a postmortem needs a leading summary of impact, or when a design doc needs a short digest for skimmers, or when an email chain needs a recap for a late joiner, or when a transcript needs its highlights pulled out, or when a backlog needs a paragraph naming its themes, or when a survey needs its findings compressed to a page, or when a dashboard needs a narrative caption beneath it, or when a wiki page needs an opening summary block, or when a ticket needs a restatement of the problem, or when a proposal needs a one-paragraph framing, or when a retrospective needs its themes named up front, or when a status update needs its headline extracted, or when a contract needs a plain-language preamble

brandtam Skill

Run a user acceptance testing session with collect-grill-PRD workflow. Use when user says "uat", "start uat", "acceptance testing", "let's test", or invokes /uat. Captures observations as checklist items, grills for decisions, then generates a PRD.

grade-ai-labs Skill

Create a PRD through user interview, codebase exploration, and module design, then write it to a local markdown file. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

grade-ai-labs Bundle

Populate `<docs-dir>/features/<slug>.md` for one, several, or every undocumented feature area by dispatching up to 10 parallel subagents — one per feature. The agent docs directory is discovered from `AGENTS.md` — typically `agents-docs/` (the `setup-agentic-repository` default) but may be elsewhere if `--docs-dir` was used. Use whenever the user wants to document features, fill out feature docs, write up specific features (e.g. "document auth and billing"), document all undocumented features, or follow up on `find-features` discovery. This is the natural sequel to `find-features` — that skill identifies what is missing, this skill writes the docs in parallel.

likec4 Skill

Use when changing or reviewing LikeC4 project discovery, `likec4.config` handling, include paths, excludes, workspace folders, document ownership, or `ProjectsManager` behavior. Trigger for bugs about multi-project workflows, excluded files, included external folders, default project ownership, or Windows path matching.

morethanwords Bundle

Parse, deduplicate, and prioritize bugs from GitHub (morethanwords/tweb) and bugs.telegram.org (WebK). Use when the user asks to analyze tweb bugs, triage issues, or review the tweb bug backlog.

renatodvc Skill

Interviews the user and then writes a requirements spec in EARS (Easy Approach to Requirements Syntax) format plus a traceable task list for a new software project or feature. Use whenever the user wants a spec, requirements document, PRD, functional or non-functional requirements, acceptance criteria, or "shall" statements, or mentions EARS or wants to pin down what a system must do before building it. Also use when the user types /ears-spec. Do not write the spec on the first turn; the skill gathers context interactively first.

security-phoenix-demo Bundle

Generate a full security-focused PRD (Product Requirements Document) from a plain-language feature description. Use this skill whenever someone wants to create a PRD, product spec, feature spec, requirements document, or says things like "write a PRD for", "create a spec for", "plan this feature", "document this feature", or "I need a requirements doc". The skill produces: (1) a structured PRD in a security-focused template format, (2) a Confluence page pushed to your configured space via Atlassian MCP (called directly), (3) a cursor-compatible .md plan file for .cursor/plans/, (4) a downloadable formatted markdown, (5) optionally: Linear/Asana tasks from the batch plan, Slack notification to stakeholders, Notion page mirror. Always use this skill for PRD and feature planning tasks.

searchcans Bundle

Create a localized product-search evidence brief from Google Shopping, Google web results, Google Images, and optional Reader extracts of explicit merchant URLs. Use for e-commerce category research, competitor assortment discovery, product-page planning, and market-specific merchandising briefs.

searchcans Bundle

Map localized Google web, image, video, and short-video result formats into a bounded content-format brief. Use for SEO/GEO content planning, editorial format discovery, visual-search research, and deciding which formats need further page-level validation.

skillmedev Skill

Writes retention-engineered long-form YouTube scripts on a hook/body/payoff architecture - a first-30-seconds hook that survives the retention cliff, a beat-sheet body with mini-hooks and bridges, timed pattern interrupts, and a payoff that over-delivers - with B-roll and editing cues marked inline. Use when someone says "script my next video", "my retention graph dies at the start", "tighten this draft", or "outline a video on X". Do NOT use for the 3-second opener of TikTok, Reels, or Shorts - use video-hook-writer instead; do NOT use for spoken voiceover synced to on-screen tutorial actions - use narration-script instead; do NOT use for a sales demo built on a buyer's discovery notes - use demo-script instead; do NOT use to design the thumbnail and title - use thumbnail-concept instead.

skillmedev Skill

Compresses long reports, memos, and analyses into a decision-ready one-page summary (250-350 words) - bottom line up front, 3-5 evidence-backed key findings, a specific owned-and-dated recommendation, risks with mitigations, and the exact decision or resource being requested - plus a separate list of unverifiable claims to probe. Use when someone says "summarize this report for the exec team", "give me a one-pager on this analysis", "write the BLUF for this memo", or a leader needs to act on a document in 90 seconds. Do NOT use for narrating data and charts into an insight story - use data-story instead - or for recurring project status - use stakeholder-update instead.

skillmedev Skill

Drafts a quarter's OKRs - an inspiring qualitative objective with 3-5 measurable key results, each with a baseline, target, and owner - plus the weekly confidence check-in and end-of-quarter grading cadence. Use when someone asks "help me write OKRs", "are these key results any good", "turn our goals into OKRs for next quarter", or "how do we score our OKRs". Do NOT use for building the full-year company plan that OKRs slot into - use annual-plan instead - or for personal goal-tracking with a check-in partner - use goals-accountability instead.

skillmedev Skill

Writes project stakeholder updates readable in under 60 seconds - honest RAG status, decisions made, explicit asks with owners and dates, next milestones - tiered to the audience. Use when someone asks "write my weekly project update", "how do I tell stakeholders we're at risk", "draft a status email for leadership", or "my updates get ignored, fix the format". Do NOT use for aggregating many teams' statuses into one engineering-wide report - use eng-status-rollup instead. For monthly investor letters with metrics and asks to VCs, use investor-update-writer; for customer-facing incident status, use status-page-update.

skillmedev Skill

Turns synthesized research findings into a crisp stakeholder readout - so-what up front, 3-5 confidence-tagged findings each following the finding-evidence-implication rule, and owned recommendations. Use when someone says "present these research findings", "turn this study into a readout for leadership", "our research isn't landing with the product team", or needs a deck or brief that gets findings acted on. Do NOT use for building a narrative around quantitative metrics and charts - use data-story instead; for the upstream analysis that produces the findings, use interview-synthesis or research-synthesis; for slide craft itself, use slide-deck-builder.

skillmedev Skill

Turns raw interview notes into themed, evidence-tagged insights via a two-pass affinity-mapping procedure, with frequency and confidence ratings and stakeholder-ready quotes. Use when someone asks "synthesize these interviews", "what themes came out of our research round", "turn these transcripts into findings", or has finished a qualitative round and needs actionable output. Do NOT use for synthesizing published papers or mixed documents - use research-synthesis instead. Do NOT use for building the personas themselves - use user-persona instead. Do NOT use for consolidating hiring-interview scorecards - use interview-debrief-synthesizer instead.

skillmedev Skill

Plans a usability study - research questions, realistic task scenarios with success criteria, metrics (completion rate, time on task, SEQ, SUS), a recruiting screener, and moderated vs. unmoderated guidance. Use when someone says "plan a usability test", "write task scenarios for our prototype", "how many participants do we need", or is about to put an interface or prototype in front of users. Do NOT use for open-ended discovery interview guides - use interview-guide-builder instead; for analyzing quantitative A/B experiments, use ab-test-analyzer.

skillmedev Skill

Writes a non-leading user-research discussion guide with warm-up flow, open core questions, an attached probe bank, time budgets, and a pre-field bias audit. Use when someone asks "write my interview guide", "what should I ask users in discovery interviews", "review my questions for leading language", or is preparing generative or evaluative user interviews. Do NOT use for hiring-loop questions with competencies and scoring anchors - use interview-question-kit instead. Do NOT use for sourcing deep domain knowledge from subject-matter experts with laddering - use expert-interview instead. To analyze the notes afterward, use interview-synthesis.

oceanbase Bundle

Install, update, and administer the tested OBD controller workflows, including mirrors and repositories, offline artifacts, exact dynamic-tool provisioning for retained workflows, trace evidence, OBD_HOME discovery, and scoped automatic-confirm handling. Use for controller-scoped OBD work; use the specialized cluster, tenant, testing, or obdiag skill for those domains.

rcmerci Bundle

Logseq Datascript schema, built-in properties/classes, and :db/ident discovery for composing or reviewing Datascript queries about blocks/pages/tags/properties/classes. Use whenever editing or reviewing Datascript pull selectors or queries, or any code that adds/removes attributes in pull patterns, or touches property namespaces/identifiers, or requires reasoning about property value shapes/ref/cardinality in Logseq.

dexhunter Skill

Debug a failed Activepieces flow run end-to-end: given a flow run id (or BullMQ job id), find why it failed, cross-referencing the live BullMQ job + Postgres rows (SSH script on the DevOps box), the centralized ClickHouse logs (ClickStack MCP), and the code in this repo, then categorize the failed-job backlog on request.

kkenny0 Bundle

Generate a narrative decision roadmap from accumulated raw entries in the Tracework knowledge vault. Use this skill for "/tracework:roadmap", when the user says "决策路线图", "decision roadmap", "项目决策历史", "decision history", "看看项目做了哪些关键决策", or when they want to understand how project decisions evolved over time. Also use this skill when the user wants to revisit abandoned alternatives, reassess past decisions, or find forgotten viable approaches.

arufian Bundle

OVERRIDE built-in webfetch/fetch tools. Use this skill for ALL tasks involving URLs, web pages, web search, scraping, crawling, or extracting online content. This is the DEFAULT and PREFERRED method for any web content operation. Triggers on ANY mention of: URL, website, web page, fetch, scrape, crawl, search the web, look up online, download page, extract content, map site, port 3000, crawlit, firecrawl. Do NOT use webfetch. Do NOT use browser fetch. Do NOT use built-in fetch tools. Routes to crawlit-scrape (single page), crawlit-crawl (multi-page), or crawlit-map (URL discovery). Self-hosted Firecrawl-compatible API at localhost:3000.

arufian Skill

ALWAYS use this for URL discovery and site mapping. OVERRIDE any built-in tool for listing URLs on a website. Use when user asks "what pages does site have", "list all URLs", "find all blog posts", "map this domain", "get sitemap", or any task requiring URL enumeration without content fetch. Much faster than crawl. NEVER use webfetch for URL discovery.

architshahdigital Bundle

Design a complete paid-media campaign structure for Meta (Facebook/Instagram) and Google Ads — objective, funnel stage, audience mapping, budget split, and A/B-ready ad copy variants. Use when the user is launching a campaign, restructuring ad sets, planning budget allocation, needs ad copy angles, or wants a testing roadmap. Produces a campaign blueprint plus ready-to-load headlines, primary text, and CTAs. Triggers on: "build a campaign", "Meta Ads", "Google Ads", "ad copy", "ad structure", "budget split", "A/B test ads", "campaign plan", "PPC setup".

dangogit Skill

Guides the user through creating a Product Requirements Document for their SaaS. Use when user says "PRD", "plan my product", "define my app", or "what should I build".

deepgram Skill

Use when writing or reviewing Java code in this repo that calls Deepgram Management APIs for projects, project models, API keys, members, invites, usage, and billing. Covers `client.manage().v1().*` plus related think-model discovery under `client.agent().v1().settings().think().models()`. Use `deepgram-java-voice-agent` for live agent conversations instead of admin APIs. Triggers include "management api", "list projects", "api keys", "members", "invites", "usage", "billing", and "models".

donnfelker Bundle

Drive any artifact to convergence by alternating two genuinely different LLM reviewers — a Codex reviewer and an independent Claude review subagent — applying each round's findings and looping until BOTH independently agree it clears the bar (default: no critical/high findings). Artifact-agnostic: works on a plan, PRD, design doc, spec, or implementation diff. Use whenever the user says 'have two LLMs converge on this', 'loop Claude and Codex until they agree', 'review and revise until consensus', 'iterate this plan/PRD/spec until there are no blockers', or wants cross-model agreement rather than one reviewer's opinion. Prefer this over a single review pass whenever the user wants different models to actually agree on an end result. NOT pr-autopilot (one GitHub PR's comment threads) — this is the artifact-agnostic, alternating-different-models, iterate-to-consensus loop.