Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.
Use when a project is on an older Clarity Framework version, a new release is out, or the user asks to update or sync the framework — upgrades documents and tooling without losing anything already written.
Generate a type-safe form from a zod schema using react-hook-form, @hookform/resolvers, and Tamagui field components. Use when building any user input form — login, registration, payments, profile edits.
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Fix a specific design-system integration finding in a Figma screen or component, including missing shared components, local overrides, and unbound tokens.
Turn messy input (notes, transcripts, chat threads, brain dumps, follow-ups that change earlier asks) into finished, verified work, and keep going until everything asked is proven done. Use when the user dumps several asks, changes requirements mid-task, says /ship, or when SHIP.md exists. Not for quick questions or single small edits.
Write precise TypeScript — generic constraints, conditional types, mapped types, template literal types, branded/nominal types, type narrowing, satisfies operator, and utility type composition. Use when asked about "TypeScript generics", "conditional type", "mapped type", "infer keyword", "branded type", "nominal typing", "template literal type", "satisfies", "utility types", "type narrowing", "discriminated union", "type predicate", "TypeScript strict mode", "keyof typeof", or "TypeScript advanced patterns". Do NOT use for: React-specific TypeScript — see frontend-patterns. Do NOT use for: API type generation — see api-design.
Use when implementing any feature, fixing any bug, or changing behavior in TypeScript or Python — and whenever the user mentions TDD, test-first, test-driven, red-green-refactor, "write tests", "add tests", unit/integration tests, pytest, vitest, jest, mocking/test doubles, coverage gates, or retrofitting tests onto a legacy codebase. Teaches the full TDD discipline (the Iron Law, red-green-refactor, the Three Laws, FIRST, AAA/GWT, triangulation), with extensive runnable TypeScript (Vitest) and Python (pytest) examples, test-double/mocking guidance and anti-patterns, how to bootstrap TDD into a new OR existing repo, advanced patterns (outside-in, double-loop, property-based, controlling time/IO), and WHY test-first produces better software specifically when an AI agent writes the code. This is the comprehensive companion to the terse `superpowers:test-driven-development` enforcer — use both: that one to stay disciplined in the loop, this one for depth, examples, and setup.
Drive the waza CLI (microsoft/waza) — the default skill-evaluation tool for this workspace — to check skill readiness for free (waza check, waza tokens), run behavioral eval suites with LLM graders, compare models A/B, measure quality with an LLM judge, and gate regressions in CI. Use when checking a skill before submission, running evals, comparing models, or auditing eval coverage. Do NOT use for post-hoc real-session efficiency telemetry (what a skill actually burned when it ran) — that is the copilot-session-telemetry skill (formerly agentic-workflow-benchmark), whose findings hand off here for eval refinement.
Verify and enforce actual NVIDIA CUDA GPU execution for ML training, inference, evaluation, or benchmarking when GPU use is required. Unexpected CPU fallback is a defect.
Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fields): "fill in the form", "fill out this PDF", "complete the form fields", "write values into PDF", "what fields does this PDF have". REFORMAT (apply design to an existing doc): "reformat this document", "apply our style", "convert this Markdown/text to PDF", "make this doc look good", "re-style this PDF". This skill uses a token-based design system: color, typography, and spacing are derived from the document type and flow through every page. The output is print-ready. Prefer this skill when appearance matters, not just when any PDF output is needed.
Multi-page Lighthouse audit via the MIT-licensed Unlighthouse CLI. Free-tier alternative to running PageSpeed against every URL on a site — no API quota burn, runs locally.
Use when deciding which cc-* sub-skill to invoke next, or when sequencing a Cancer Cell (Cell Press) manuscript from scope check through peer-review revision. Routes — it does not replace — the specialized skills.