Product & Planning

product-on-purpose Bundle

Reviews markdown or plain-text prose for clarity against the Federal Plain Language Guidelines and Williams' Style: readability, passive voice, sentence length, and nominalization density. Judges sentence- and passage-level readability, not whether an argument's claim is supported or its structure holds together (critique-argument covers that). Use when the user asks for feedback, a second opinion, a red-line pass, or a quality check on a memo, PRD, proposal, or any prose document before it goes out.

provos Skill

Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or triaging findings against C/C++ code with sanitizer support (ASAN/UBSAN/TSAN/MSan). Not applicable to managed runtimes (JVM, .NET) or scripting languages — those have their own skills.

provos Skill

Reference vocabulary for interpreting vulnerability findings — detector-vs-impact distinction, severity anchoring on demonstrated evidence, the eleven-item interpretation rubric, delegation transparency, primitive-extent scaling, the disqualifier taxonomy (D-0..D-4), CVSS Achievable / Environmental framing, hedging-phrase elimination, and falsification asymmetry. Read when interpreting a finding to decide whether the demonstrated evidence supports the severity it would warrant. Surface-neutral; pulls in the relevant surface skill (e.g. `memory-safety-c-cpp`) for bug-class-specific exploitability factors.

provos Skill

Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit), existing-fuzzer selection (libFuzzer / AFL++ / Jazzer / atheris / `go test -fuzz`), seed-corpus discipline, diagnostic checkpoints, common pitfalls, and design-document scope. Read when designing or reviewing a harness specification. Stays neutral on language and stack — pulls in the relevant surface skill (e.g. `memory-safety-c-cpp`) for bug-class taxonomy.

purong-huang-1121 Skill

This is the main on-chain DeFi skill. Use it for ALL of the following: Strategy discovery: 'how to make money on-chain', 'any profitable strategies', '链上有什么赚钱机会', '有什么盈利机会', '有什么套利机会', '怎么赚钱', '有什么好的策略', '帮我理财', '有什么收益机会', 'yield opportunities', 'how to earn', 'investment strategy', 'DeFi 策略推荐', '有什么自动化策略', 'automated strategies', 'passive income on-chain'. Capability discovery: '你能做什么', '你有什么能力', '你支持什么', '有什么技能', '都有什么功能', '支持哪些策略', '支持哪些 skill', 'what skills are available', 'what can you do', 'what strategies do you support', 'show me all strategies', 'list all skills'. Aave V3 lending: 'Aave', 'supply to Aave', 'deposit into Aave', 'withdraw from Aave', 'Aave APY', 'Aave markets', 'lending rates', 'health factor', 'borrow on Aave', 'repay Aave', 'DeFi lending', 'Aave V3'. Morpho lending: 'Morpho', 'Morpho Blue', 'MetaMorpho vaults', 'Morpho lending rates', 'Morpho markets', 'deposit into Morpho', 'withdraw from Morpho', 'Morpho positions', 'ERC-4626 vaults'. Uniswap swaps: 'Uniswap', 'swap on Uniswap', 'U

r007b34r Bundle

Decide whether material should become a stable, reusable, linkable Obsidian note. Load when user asks to upgrade, promote, or stabilize material into a formal note. Do NOT use for inbox triage, link discovery, or weekly synthesis.

ruhedanghaoyigexuesheng Bundle

根据需求文档或 PRD 生成可导入 XMind 的测试用例思维导图大纲。可从本 Skill 的 requirements 目录读取需求文件（PRD/PDF 等），或根据用户提供的路径/粘贴内容生成。按功能/模块拆分，每项下挂测试点（标题+简要步骤/预期）。未提及接口/性能时默认按通用测试规范（边界值、等价类、场景法等）生成；提及接口/性能测试时加载 references 内对应规范。当用户说「读取需求文件并生成测试用例」「生成思维导图测试用例」等时使用。支持 .docx、.pdf、.txt、.md。

ruhedanghaoyigexuesheng Bundle

基于需求文档、PRD 或接口文档自动生成结构化测试用例文档。默认采用通用测试用例设计策略（正向、反向、边界值、等价类等）；当用户提到参考 Excel/Word 模板时从 assets 加载模板，提到接口/性能/功能等专用标准时从 references 加载对应说明。适用于从各类文档设计功能、接口、性能及自动化候选用例。

ruhedanghaoyigexuesheng Bundle

以 10 年经验资深测试工程师视角进行需求分析与质量架构。支持文本或单图/多图（需求截图、原型图、流程图）输入，穿透 UI 到数据流、接口、微服务与性能边界，产出业务解构、状态机、深度测试点与风险预警；按图片序号整理成完整需求分析文档，并同步输出可直接给开发看的需求测试点 Checklist。当用户提到需求分析、PRD 解构、测试点设计、图片需求分析、截图需求、质量架构、风险预判、状态机梳理时使用。

rwcod Bundle

Authorized, conservative security assessment of the HTTP/API endpoints beside an MCP server. Covers route discovery, OpenAPI/Swagger leakage, auth bypass, IDOR/BOLA, broken function-level authorization, mass assignment, excessive data exposure, SSRF, injection, file upload, webhook signature bypass, CORS, CSRF, rate limiting, and error/debug leakage. Safe-by-default and read-only. Use when testing REST/HTTP APIs in an authorized environment.

rwcod Bundle

Authorized security assessment of REMOTE MCP servers that use browser-based OAuth/OIDC login (Jira/Rovo-style). Drives an 18-phase review of the OAuth flow, discovery metadata, token validation, scope-to-tool mapping, per-tool and per-tenant authorization, API-token fallback, consent boundaries, and audit logging. Safe-by-default, read-only, deny-by-default. Use when auditing a remote MCP server reached over HTTP with an OAuth login step.

rwcod Skill

Semi-autonomous orchestrator for authorized MCP security assessment. Drives the deterministic probe_runner (read-only battery) plus optional parallel read-only sub-agents (discovery / authz-sweep / injection-probe), holds engagement state (tokens, discovered IDs), reasons over structured results, and produces the report. Safe-by-default: read-only, write/destructive tools are human-gated, scope-locked to one host. Use to run the kit with minimal manual curl.

theexperiencecompany Bundle

Produce an Apple-keynote-quality motion-design video in HyperFrames (HTML + GSAP compositions) — kinetic typography plus real product UI, scored to a real music track, rendered at 4K. Use when asked to make a motion-design video, an Apple-style launch/product film, a feature-announcement video, a hype/promo reel or sizzle, ESPECIALLY in HyperFrames, or when porting motion-studio/Remotion components into a HyperFrames video. The engine is HyperFrames — `npx hyperframes` lint/inspect/render, one paused GSAP timeline on window.__timelines, sub-compositions, a reusable component library, and a 4K scale-stage. Covers the full pipeline — discovery, a binding creative brief, a music beat grid, an agent team (scriptwriter, reviewer, component porter, video builder, UX and craft auditors), faithful component porting, the Apple aesthetic and exact palette, sourcing a real royalty-free music track beat-matched to the edit, 4K export, frame-by-frame verification, and the hard-won pitfalls that cost real iterations.

thinkyou0714 Bundle

Score and prioritize all open GitHub Issues by Impact x Effort x Urgency. Outputs a triage matrix (TRIAGE.md), applies priority labels, and suggests a sprint plan. Use when your issue backlog is overwhelming, you don't know what to work on next, or you want a structured sprint plan. Triggers on: "issue 整理", "バックログ整理", "何から手をつける", "issue優先度", "sprint plan", "issue-triage", "issue triage". DO NOT USE FOR: closing issues, writing code, or creating new issues.

timothyhoughton Skill

Write a tight, commercially watertight Scope of Work under 500 words, using the client brief and your scoping answers as input. Use when discovery questions have been answered and you're ready to lock in what's in, what's out, and who's doing what. Triggers: 'write the SoW', 'draft scope of work', 'turn this into a SoW', 'write a statement of work'.

tmusser Skill

Use for dense or messy workplace source material - Slack threads, email chains, memos, transcripts, policy docs, vendor writeups, research notes, strategy notes, or customer escalations - before replying, deciding, escalating, or acting when context is long, ambiguous, stakeholder-sensitive, high-stakes, contradictory, or easy to misread. Use source-expanded mode only when the user explicitly asks to verify, fact-check, expand sources, support or refute claims, or use outside sources; not for simple catch-ups or straightforward reply drafting unless uncertainty needs to be preserved first.

tympanix Skill

Synology Download Station Web API reference covering API discovery, authentication, request format, common errors, and Download Station task operations.

ugai Bundle

Scouts the codebase for bugs, improvement opportunities, and missing features, then posts well-scoped GitHub Issues for Issue Slayers to pick up. Discovery only — does NOT implement fixes or open PRs (use issue-slayer for that, or dispatching-guild-expedition for the full pipeline). Use when asked to find new issues, propose quests, scout the codebase, populate the issue board, "find problems in the code", or "what needs fixing?"

ugai Skill

Orchestrates a full sprint from discovery to open PRs: Rangers scout in parallel, user approves issues, Raid Commander detects conflicts, then Slayers implement in parallel. Use when asked to run a full development cycle, a sprint, an expedition, or to "find and fix a bunch of issues" or "run a full improvement pass". NOT for single-issue work (use issue-slayer) or discovery-only (use issue-ranger). Does NOT merge PRs.

spitoglou Bundle

Create and improve technical documentation including architecture designs, PRDs, API docs, code explanations, and visual diagrams. Use when asked to document systems, explain codebases, create design documents, write PRDs, generate Mermaid/PlantUML diagrams, review architecture, write user stories, or create pull request descriptions. Triggers include "document this", "create a design doc", "explain this code", "write a PRD", "create a diagram", "architecture overview", "user story for", "PR description".

ssheleg Bundle

Use when defining or revising WHO the users are and WHY they use the product - personas, Jobs to Be Done, customer journey maps, user stories with acceptance criteria. A journey covers the end-to-end experience including what happens after the first session - where a user comes back, where user retention is won, and where churn actually starts. Maintains docs/ux/foundation.md, the WHY layer that UX scenarios trace to. Triggers - "jtbd" / "джобы", "customer journey" / "карта пути", "user story" / "юзер стори", "personas" / "персоны", "who is this for", "user retention" / "ретеншн", "churn" / "отток", new product discovery.

sshh12 Bundle

Builds a dedicated MCP server for a single web app by walking through API discovery, tool design, security review, implementation, testing, and deployment. Use when the user asks to create an MCP server, connect a web app to Claude Code, or build a tool integration for any web app.

svd-ai-lab Bundle

Search scholarly literature and research data through discoverable providers, including public metadata APIs, optional user-configured sources, legal open-access full-text discovery, identifier resolution, and citation/reference triage. Use when the user asks for paper search, topic or author literature discovery, DOI/arXiv/PMID/PMCID lookup, dataset DOI metadata, legal OA PDF or full-text locations, references, citations, related work, paper metadata, or evidence-backed literature triage.

svd-ai-lab Bundle

Use when handling simulation requirement docs, 任务书/specs, client/lab/customer asks, vague modeling requests, paid gigs, or before costly full solves, long runs, sweeps, optimization, calibration, and coupled simulations where the decision, physical model, assumptions, validation evidence, or deliverable must be clear before execution.

tahajemmali Skill

Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./docs/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".

tahajemmali Skill

Create a PRD through user interview, codebase exploration, and module design, then save to docs/<feature>/PRD.md. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

taoidle Bundle

Project-level multi-task orchestration system. Manages multiple hybrid:worktree features in parallel with dependency resolution, coordinated PRD generation, and unified merge workflow.

taoidle Bundle

Hybrid architecture combining Ralph's PRD format with Planning-with-Files' structured approach. Auto-generates PRDs from task descriptions, manages parallel story execution with dependency resolution, and provides context-filtered agents for efficient multi-story development.

tencent Bundle

very_simple_matmcd: Causal Discovery with Statistical Tools + Domain Knowledge

yzr95924 Bundle

当用户要为软件系统或功能编写正式系统设计文档（设计文档 / design doc / 技术方案 / 评审用 设计文档）时使用本 skill——主场景是基于已有系统增加或修改功能 / 特性（"给工单系统加审批流， 写个设计文档" / "结算要支持优惠券叠加，出个技术方案"），也覆盖全新系统设计与小改动的轻量 设计说明。按改动规模路由 full / lite 两档模板（assets/ 单文件跟踪），产出结构一致的中文 Markdown 本地文件（full 档 14 节：需求层 / 方案层 / 落地层 + DFX），并配套生成实施任务书 （独立 tasks 文件，供执行 agent 按任务实施、反馈进度与设计变更，形成设计—执行循环迭代）。 触发："帮我写个设计文档" / "下周评审要用的系统设计" / "把这个功能的技术方案整理成文档" / "write a design doc for X"。 不适用：产品需求文档（PRD）、API 参考文档、README、事后沉淀进 wiki 的文档；用户只要 代码实现、没要文档（不主动加文档）。

zenml-io Bundle

Give first-time users a short, value-first Kitaru tour with the PydanticAI returns agent example in the Kitaru repository. Use when someone has no agent or traces of their own, arrives from Kitaru onboarding, asks for a demo, tutorial, quickstart, or guided example, needs the quickstart example cloned or prepared, wants the coding agent to prepare trace annotations before they judge sessions, or wants to experience Kitaru's value before learning the full investigation method. Prepare a three-session frontend review, let the human provide verdicts, turn one accepted finding into a deterministic evaluator, and finish with one approved bounded replay experiment. Route real agents, open-ended discovery, and production evidence to kitaru-investigation instead.

liustack Bundle

细分市场发现与评估：四路信号交叉验证（关键词/社区痛点/竞品差评/趋势）+ 五维评分卡 + AI 红海测试，输出 go/收窄/no-go 结论。Niche discovery and scoring for one-person companies. Use when the user wants to 找产品或生意方向 / 选赛道 / 找细分市场 / 验证一个 niche / find a niche / validate a market idea / what product or business should I build.

ondata Bundle

Query OpenAlex API from the command line with curl and jq for publication discovery, filtering, sorting, pagination, and PDF availability checks. Use when searching scholarly works/authors/sources, building or debugging OpenAlex queries, extracting results, or downloading available PDFs using OPENALEX_API_KEY.

plaited Bundle

Echo back messages for testing skill discovery.

riadchaban994-bot Bundle

Use when setting up a discovery practice, when research keeps being a one-off project instead of a habit, when recruiting participants is the bottleneck, when past research cannot be found or gets redone, when discovery findings are not reaching stakeholders, or when scheduling and automating the recurring parts of research.

riadchaban994-bot Bundle

Use when a product metric moved and the cause is unknown, when designing what to measure for a feature or outcome, when analysing funnels, cohorts, retention or churn, when working out how many users a test needs, when analysing a survey, or when a number in a document needs checking before anyone acts on it.