Product & Planning

zhouzilai626 Skill

将模糊想法、需求、产品请求、工具改造想法、内容计划、工作流改进，或“我不知道怎么讲清楚”的表达，整理成清晰、可执行、可验收的需求说明。 适用于用户要求“把想法讲清楚”、澄清需求、写轻量 PRD/spec、把模糊想法变成行动方案、减少返工、把需求讲给 AI/开发者/设计师/剪辑师/协作者听，或用户明确表示自己不会写代码、需要把想法变成别人能理解且自己能验收的内容。 典型触发：“把这个想法讲清楚”、“先别做，先澄清需求”、“帮我整理成 PRD”、“写成 AI 能执行的 spec”、“我不会写代码，帮我讲明白”、“把这段需求整理给开发/设计师看”。 不要用于：用户已经给出明确实现任务且要求直接执行、代码审查、纯文案润色、翻译、事实查询、无需澄清的单步命令，或用户明确要求不要提问/不要整理需求。

matsuni-kk Bundle

新規エージェント作成のためのヒアリング・要件定義を実施し、draft_requirements.mdとframework_research.mdを生成する。「エージェント作成」「新規Agent」「ヒアリング開始」を依頼されたときに使用する。

lambdatest Bundle

Browser automation + AI test authoring via kane-cli - run browser objectives, generate & refine test scenarios/cases from a description, design requirement-linked test suites from a PRD/spec (assurance), parse NDJSON output, inspect logs, save runnable _test.md. Use for any task requiring a real browser (navigate, click, fill forms, test web UI, take screenshots), or to author test cases, quick cases from a description via kane-cli generate; a designed, coverage-accounted suite from requirement documents via the assurance commands. Never write test cases by hand. Also runs mobile app tests on macOS Apple Silicon - native Android app on a virtual emulator or iOS app on a simulator via --target emulator|simulator (desktop browser stays the default target).

q00 Skill

Use when the user wants a Warden review from an SSOT issue, roadmap, RFC, or brief. Turns a canonical source link plus active work surfaces into an evidence-backed alignment review without implementing, approving, merging, or force-closing work.

riadchaban994-bot Bundle

Walk any app hands-on and build or update a real product-analytics tracking plan from what you actually see. Use this whenever someone needs an event taxonomy, a tracking plan, a measurement plan, an analytics spec, an event dictionary, instrumentation for GA4 / Firebase / Amplitude / Mixpanel / Segment / PostHog, or wants to audit or extend tracking that already exists. Use it when the ask is "what should we track", "our analytics are broken", "we have no funnel data", "design the events for this feature", "map the user journeys", or "the dev team needs a spec". It drives an Android emulator, an iOS simulator, a browser or a Figma file, screenshots every surface, groups parameters into reusable attribute packs, grades every event by how strong the evidence for it actually is, and ships a phased, buildable Excel workbook with embedded screenshots. Works for any app in any industry. Reach for it even when the person only says "events" or "instrumentation" and has not used the words tracking plan.

sahiltolani30 Bundle

Product and feature evaluation. Use when (1) Evaluating product/feature feasibility and market viability (2) Assessing product-market fit before investment (3) Comparing opportunities for roadmap prioritization (4) Competitive analysis to identify gaps (5) User asks "should we build X?" or "is this viable?" (6) Risk assessment for product decisions

serenakeyitan Skill

Prompt-native HTML docs. Generate a self-contained HTML document from a prompt (SVG diagrams, CSS-toggled models, explainers, strategy docs, research write-ups, product specs, explainer pages, design docs, RFCs, case studies, post-mortems, technical proposals, vision docs, one-pagers, decision frameworks), publish it to a free shareable link on tdoc.dev, and collect text- and artifact-anchored comments that regenerate the next version. Readers need nothing installed. Self-hosting on your own Cloudflare or Vercel is optional. Use when asked to "write a doc", "draft this", "publish this", "design doc", "PRD", "one-pager", "research write-up", "case study", "explainer", "interactive explainer", "post-mortem", or any /tdoc command. Proactively invoke this skill (do NOT answer directly) when the user wants to write, draft, create, edit, publish, or share ANY document, write-up, explainer, or web page — EVEN IF THEY NEVER SAY THE WORD "tdoc". If the request is about producing a document-like artifact, this skill IS

shuguang1994 Bundle

为新项目快速建立完整 AI 编程规范体系（AGENTS.md、文档目录、CI/CD、Git规范、测试制度）。自主发现引擎：扫描项目→分类文件→推断技术栈，覆盖 7 语言 15 框架 70+ 组件，未知栈三层递进联网回退。Establish AI coding conventions for new projects — autonomous discovery engine with heuristic dep classification, 7 languages 15 frameworks 70+ components, web search fallback for unknowns.

leonvanzyl Bundle

Interview the user in depth about what they actually want to build, then scaffold a working full-stack web app around it. Use when the user wants to start a new app, website, prototype, or SaaS; when they don't know what tech stack to pick; or when they want a solid working starting point fast. Covers requirements discovery, project setup, database (SQLite or Postgres in Docker), sign-in, file uploads, payments, AI features, and a real landing page and dashboard.

leonvanzyl Bundle

Create, read, update, and delete features and projects in LocalForge via its REST API. Use this skill whenever the user wants to manage features in LocalForge — create a feature backlog, plan features, update existing features, break down an app into tasks, or populate a kanban board. Also trigger when the user mentions LocalForge, feature planning for local AI coding agents, or writing detailed feature descriptions — even if they don't explicitly say "create features." LocalForge is the app that uses local AI models to build software autonomously.

linearis-oss Skill

Manage Linear.app work from the command line with the linearis CLI (bins linearis / linear), which outputs JSON: issues/tickets, projects, cycles (sprints), milestones, initiatives (roadmap), documents, labels, teams, users, and issue discussions/comments. Use when the user mentions Linear, a ticket identifier like ENG-42 or ABC-123, sprints, triage, or the roadmap, or asks to create, read, search, update, assign, comment on, or otherwise manage Linear issues and projects.

luyu2026 Bundle

产品经理 Skill 库全局总控。管理 20 个 PM Skill：13 个执行工具（PRD、评审、优先级、路线图、数据分析、实验、埋点、问卷、竞品、复盘、原型×3）+ 7 个专家顾问团（Cagan、Torres、俞军、Mom Test、Story Mapping、Build Trap 及其总控）。 能力：(1)根据用户描述的问题自动路由到最合适的 Skill (2)编排多 Skill 工作流链路，把上一步产出接力给下一步 (3)判断类问题转交 pm-advisory-board 组织专家评审。 触发词：「pm-master」「产品总控」「我该用哪个 Skill」「帮我推进这个需求」「从头到尾走一遍」「完整链路」， 或者用户描述了一个产品工作场景但没有指明用哪个 Skill、或一个任务明显需要多个 Skill 接力完成时，优先使用本 Skill。

mallarylabs Bundle

Use this skill only when the user explicitly asks to inspect, set up, or act through Mallary, the Mallary CLI, the Mallary API, Mallary MCP, or an existing Mallary workflow. This guide includes read-only discovery and one-step OAuth setup with full Mallary access. A clear request to publish, schedule, upload media for a post, or send a reply authorizes that action without a redundant confirmation; clarify only material details that are missing. Executable write syntax is intentionally omitted.

masumi-network Bundle

Use this skill WHEN monetizing AI agents with autonomous payments, listing agents on decentralized marketplace, or deploying at scale. OUTCOMES: agents earning revenue automatically (50+ USDM/day), trustless escrow protection (95%+ success rate), marketplace discovery (50+ available agents), scalable execution (1000+ concurrent jobs). Triggers on: 'monetize my agent', 'setup agent payments', 'list on marketplace', 'A2A transactions', 'deploy agent at scale', 'MIP-003 implementation'. NOT for: general chatbots, simple REST APIs, centralized payments. Framework-agnostic (CrewAI, AutoGen, PhiData, LangGraph), self-hosted, MiCA compliant.

mr-karan Bundle

Query logs from the terminal with the Logchef CLI. Covers LogchefQL search filters (`query`, `tail`), raw ClickHouse SQL and VictoriaLogs LogsQL (`sql`), seeing the generated query without running it (`explain`), field and value discovery (`fields`, `schema`), counts-over-time (`histogram`), finding which source holds a service/host/message (`find`), saved queries and collections, live follow, output formats and piping to jq, config/contexts/auth, and troubleshooting query errors. Use whenever the user mentions logchef, LogchefQL, LogsQL, log search, or wants to investigate logs from a ClickHouse- or VictoriaLogs-backed source.

theyahia Skill

The back-of-napkin senior. Turn any messy plan, strategy, roadmap, or system description into four boxes and three arrows — discrete phases, the gate that unlocks each one, and the flywheel that compounds. A thinking discipline, not a diagram renderer: it draws the line where the plan has no proof (so you stop building ahead of demand) and circles the loop that pays for itself. Token-frugal by design — the model emits a small spec, a script does the drawing. Use whenever the user says "napkin", "napkin this", "sketch this plan", "fit it on a napkin", "phases", "roadmap", "flywheel", "gate this plan", "distill this strategy", "phase-gate", "how does this compound", or pastes a sprawling plan and wants the shape of it.

tolimarchuk Bundle

Goal Prep for GoalBuddy. Use for broad, long-running, stalled, vague, detailed, planned, or unhealthy Codex or Claude Code work that needs a structured /goal intake, autonomous task discovery, role-tagged Scout/Judge/Worker delegation, one active task, durable receipts, and a PM-owned rolling board that maximizes the chance of a successful goal run.

us Bundle

Scrape, crawl, map, and search the web using fastCRW's native /v1 API. Use when the user needs web page content, site-wide extraction, URL discovery, or web search results. Single binary, 14 MB RAM; /v2 exists separately for Firecrawl migration.

whb786200 Bundle

Find, evaluate, and download low-level common standard CAD parts from step.parts, such as screws, bolts, nuts, washers, bearings, standoffs, electronics parts, motors, connectors, and other off-the-shelf components. Use when Codex needs to search the hosted step.parts catalog, resolve fuzzy part names, standards, aliases, or dimensions, choose a matching part, fetch a canonical .step file, verify checksums, or use the step.parts API/OpenAPI/catalog endpoints for standard part discovery.

xeonvs Bundle

Audit, scaffold, verify, update, or migrate a repository engineering workflow while preserving existing document ownership, user scope, validation safety, and durable execution state. Use for AGENTS/PLANS/backlog/pitfalls setup, workflow upgrades, workflow-structure verification, and prompts such as Refresh Loaded Skill, Update Installed Skill, or Upgrade A Target Workflow.

nomadamas Skill

MUST use Jikji find first for bounded local file/folder/document discovery; return the machine-readable answer contract and never raw-crawl after a successful Jikji result.

nxxxsooo Bundle

Deeply grill an idea, decision, design, plan, or implied approach through evidence, failure modes, and user-owned decisions. Use discovery mode for raw ideas, clarification, "grill me", or an unfinished Product Brief; use audit mode for a formed target that needs a verdict or revision. Continue every reply in an active deep-grill session until its Product Brief or verdict is confirmed, without requiring the user to name the skill again.

yangchuansheng Bundle

Patch Codex App to enable Fast/Speed mode and Plugins in API key mode, or optionally enable Zed as an SSH-capable remote open target. Supports macOS and Windows with backup, rollback, and bundle pattern discovery.

pingcap Skill

Generate a Product Requirements Document (PRD) as JSON for Ralph. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

plausibleba Skill

Use this skill whenever a business analyst, architect, or project team needs to produce a Capability Map — even if they don't use that exact term. Trigger on phrases like: "map out what the business does", "identify our capabilities", "build a capability model", "what capabilities do we need for this initiative", "capability assessment", "business capability map", "organisational abilities", or when someone uploads a project charter, discovery transcript, existing Excel capability model, or industry reference model and asks for structured analysis. Also trigger when someone wants to prepare for a VCC (Value Cognition Canvas) session or asks what capabilities a value stream requires. The skill handles any input format — raw transcripts, structured documents, Excel files, or verbal descriptions.

theorcdev Skill

Cut an existing plan into ordered, self-contained slices (execution phases) sized for an AI agent to pick up and run one at a time. Each slice is dependency-ordered, independently verifiable, and leaves the codebase working. Use when the user has a plan, spec, PRD, or approved design and says "cut it", "cut-it", "slice this plan", "break this into phases", "split into workable parts", or invokes /cut-it.

wenyuchiou Bundle

Operating harness for working on the method-harness-compiler project (or reviewing its artifacts). Use when starting ANY task on that project — phase reviews, tool discovery, PR review, eval design, memory updates, runtime export, repo maintenance, or A/B test design. Routes the agent to a minimal per-task file set instead of whole-repo reading. For work on ANY OTHER project, activate only when the task is long / multi-step, multi-agent, expensive-if-wrong, makes a completion claim (done / passing / fixed / ready / safe / staged), or touches governance (permissions, hooks, cron, CI, routing) — the portable entry is then core/GLOBAL_BOOTSTRAP.md. Skip for one-line / typo / format edits and pure capability asks.

wyrtensi Bundle

Use when operating, automating, debugging, reviewing, or extending paperang-cli for Paperang P1 or P2 printers: BLE support, experimental P2 USB discovery/readiness, JSON output, configuration, dry-run validation, paper-use approval, image or compose printing, self-test caution, CLI contracts, rendering, drivers, protocol changes, tests, or release automation.

zaks-io Bundle

Use to turn a spec, PRD, or epic ticket into dependency-ordered one-PR implementation tickets, adopting any hand-created tickets, applying the agent-ready body contract, configured estimates, and kind labels, and emitting a dependency graph and predicted file footprint.

zaks-io Bundle

Grills an idea, plan, PRD, ADR set, or existing spec one question at a time and produces authoritative specs ready for ticket slicing. Use when the user asks to be grilled or material product, domain, scope, or architecture ambiguity blocks safe progress.

holobiomicslab Skill

Use when after generating a corpus/features JSON file from raw MS2 fragmentation spectra or similar document-term data, when the goal is unsupervised discovery of latent topics (e.g., metabolite families or spectral motifs) without ground-truth labels.

holobiomicslab Skill

Use when you have generated candidate peptide-spectrum matches from a spectral library search (especially open modification searches using cascade strategies) and need to assign statistical confidence to those matches. Use it whenever the scoring metric (e.

holobiomicslab Skill

Use when you have raw tandem mass spectrometry data in one or more of the vendor formats (MGF, mzML, or msp) and need to apply unsupervised topic modeling (LDA-based motif discovery) or comparative fragmentation analysis.

holobiomicslab Skill

Use when after LDA-based Mass2Motif discovery has generated a set of recurring fragmentation patterns (motifset_optimized.

holobiomicslab Skill

Use when when performing untargeted metabolomics annotation at scale and you need to estimate false discovery rates for candidate metabolite identifications.

holobiomicslab Skill

Use when when you need to reconstruct or validate the control-flow architecture of a spectral search system that must handle both exact-match library lookups and analogue discovery in a single pass, particularly when the system uses pre-computed embeddings for efficiency and machine learning for.