Skills directory · page 74

Generate SQL queries from natural language descriptions. Supports BigQuery, PostgreSQL, MySQL, and other dialects. Reads database schemas from uploaded diagrams or documentation. Use when writing SQL, building data reports, exploring databases, or translating business questions into queries.

Write correct and efficient SQL: joins, aggregations, window functions, CTEs, and query optimization. Use for any relational data access.

Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, reconciliation report, production vs staging comparison. Uses mssql-python driver with Apache Arrow for fast columnar data transfer and comparison.

Use SQLite for embedded relational storage: schema, WAL mode, transactions, indexing, and performance. Use for local and mobile data layers.

This skill should be used when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database credentials using sqlmap," "dump tables and columns from a vulnerable database," or "perform automated database penetration testing." It provides comprehensive guidance for using SQLMap to detect and exploit SQL injection vulnerabilities.

Define reliability with SRE practices: SLIs, SLOs, error budgets, and data-driven deploy decisions. Use for balancing features with reliability.

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control, using vectorized environments for parallel training, and integrating with deep RL workflows. This skill should be used when users request RL algorithm implementation, agent training, environment design, or RL experimentation.

Use when a managed-agent build sheet is ready to launch ('launch it', 'deploy the agent'). Generates and validates API payloads with payload_generator.py and payload_validator.py and writes a resumable curl script with launch_script_writer.py that uses the user's own key.

Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan. Use when managing stakeholders, preparing for a launch, aligning cross-functional teams, or planning stakeholder engagement.

Add a self-hosted "Stargazers over time" chart to any GitHub repo's README. GitHub now restricts the stargazers endpoint to a repo's own admins/collaborators, so third-party live services (star-history free tier, starchart.cc) return "Requires authentication" for everyone. This generates a static, theme-aware SVG in-repo and auto-refreshes it weekly with a GitHub Action using the repo's own GITHUB_TOKEN. Use when the star chart in a README is broken, shows "Requires authentication", or you want a star history that never breaks.

Use when adding auth to a TanStack Start app — route protection, server-function authorization, sessions, CSRF. Do NOT use for generic route guards.

Use when scaffolding a TanStack Start project, wiring the build tool, or debugging setup (blank page, hydration, no client JS).

Use when building or deploying a TanStack Start app — Cloudflare, Netlify, Vercel/Node/Bun, prerendering, or env vars. Do NOT use for app logic or generic Vite config.

機能ブランチ開発ワークフロー: Issue/DesignDoc確認 → worktree作成 → 計画 → 実装 → コミット → PR作成。 セッション内で worktree を管理する。 Trigger when the user says: "feature開発", "開発開始", "新機能開発", "PRワークフロー", "start dev", "start feature", "new feature", or similar phrases requesting to start development.

Use when deciding where TanStack Start code runs, fixing secret leaks, DB-in-loader bugs, or hydration mismatches.

Use when composing cross-cutting server logic in TanStack Start with createMiddleware — chaining, context, auth factories.

Use when loading data in Start routes — isomorphic loaders, TanStack Query in a loader, mutations, or per-route SSR. Do NOT use for generic Router/Query API.

Use when creating type-safe RPC server logic with createServerFn — validators, handlers, FormData, redirects. Do NOT use for raw HTTP endpoints or middleware chains.

Use when building raw HTTP endpoints in TanStack Start with the server property — handlers, params, middleware. Do NOT use for internal RPC (start-server-functions).

Generate a Startup Canvas combining Product Strategy (9 sections) and Business Model (costs + revenue) for a new product. An alternative to BMC and Lean Canvas that separates strategy from business model. Use when launching a new product or evaluating a startup concept.

Renders every state of a component you choose on a throwaway page, with mock data and a switcher, so you can work on each state.

Check Forge route declarations and hash-anchor targets without requiring a browser dependency.

Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research.

Is a difference real? Significance tests, confidence intervals, sample size and test duration for A/B results. Load whenever the user asks if a lift is real or noise, which variant won, or how many users a test needs.

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Show every CCM Stack rule and what enforces it; turn rules or the voice on and off; ccm doctor. Use for /ccm-stack:status.

Create and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run.

Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern

Convert frontend code (Vite, React, Angular, Vue, etc.) to a Stitch Design by chaining static HTML extraction, design system extraction, and file upload. **ALWAYS** use this skill when the user's intent is to move existing web apps or React/Angular/Vue components into Stitch (e.g., requests to "save", "migrate", or "upload"). You must use this skill even for simple "save" operations, as it is the only way to ensure the design system is extracted and assets are properly linked.

Extract a comprehensive design system (DESIGN.md) directly from frontend source code — React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce a rich, Stitch-compatible design system document. Use this skill whenever the user wants to reverse-engineer a design system from an existing codebase, audit the visual language of a project, extract design tokens from source files, or understand the styling patterns in a frontend repo — even if they just say "what does this app look like?" or "pull out the design from this code."

Extract self-contained static HTML from a built web application or React components by inlining CSS and images. Use this skill whenever you need to capture a specific UI state, share a static version of a page, or prepare assets for Stitch upload, even if the user just asks to 'save the HTML' or 'mock the view'.

Generate new screens from text prompts or images, edit existing screens with prompts and design system tokens, and generate design variants using Stitch MCP. Includes prompt enhancement pipeline, design mappings, professional UI/UX terminology, design tokens and theme system capabilities.

Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.

Converts Stitch designs into modular Vite and React components, or syncs/updates existing React components to align with the latest Stitch designs, using system-level networking and AST-based validation.

Convert Stitch HTML designs to React Native components, or syncs/updates existing native components to align with the latest Stitch designs, using StyleSheet.

Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project. ALWAYS use this skill when you need to upload visual assets, HTML pages, or design docs to Stitch, particularly when direct MCP tool calls fail or truncate due to base64 token limits.

Analyze, research or value a listed stock or company (US, global, NSE or BSE) with verified data, ratios, scores and valuation. Use whenever asked if a stock is a buy, what it is worth, or how a company looks.

Manage a file-based epic → story → sprint development loop without requiring an external project management tool. Creates and tracks epics, breaks them into user stories, assigns them to sprints, and drives implementation story by story. Use when starting a new feature initiative or when the team has no Jira/Linear/Taiga but needs structured delivery tracking.

Use when teams pull in different directions, OKRs don't connect or departments optimize locally. Maps the strategy cascade and finds orphan goals and silos with alignment_checker.py.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when a session is approaching a context limit and a task phase is a natural place to compact.

任意の自動コンパクションではなく、タスクフェーズを通じてコンテキストを保持するための論理的な間隔での手動コンパクションを提案します。

임의의 자동 컴팩션 대신 논리적 간격에서 수동 컨텍스트 압축을 제안하여 작업 단계를 통해 컨텍스트를 보존합니다.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when a session is approaching a context limit and a task phase is a natural place to compact.

Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria for each. Use when stress-testing a plan, pressure-testing a strategy, challenging assumptions, or preparing a doc for executive review.

Stress-test a plan built on untested assumptions. Use whenever the user bets on a hockey-stick model or long pilot.

Use when the user says 'no hallucinations', 'verify APIs' or 'don't invent functions', or code depends on a library version you have not checked. Requires proof that every method, import and variable exists in the installed version before using it.

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

Build or review a Stripe integration with current Stripe guidance: Checkout Sessions, Payment Element, Setup Intents, subscriptions and the Customer Portal, webhook-driven fulfillment, idempotency, restricted API keys and Stripe Tax. Use when: stripe, payments, checkout, subscription, billing, webhook, refund, payment intent.