一键导入
skills
skills 收录了来自 francogalfre 的 11 个 skills,并提供仓库级职业覆盖和站内 skill 详情页。
这个仓库中的 skills
Writes and debugs Bitbucket Pipelines CI/CD configuration. Use when the user says "set up Bitbucket Pipelines", "write a bitbucket-pipelines.yml", "my pipeline is failing", "add a deployment step", "configure CI for Bitbucket", "add tests to my pipeline", "set up staging and production deployments in Bitbucket", or shares a bitbucket-pipelines.yml and asks for help.
Refactors code to be cleaner, more readable, and easier to maintain — without changing behavior. Use when the user says "clean up this code", "refactor this", "this is messy", "improve readability", "simplify this function", "too many nested ifs", "make this more maintainable", or pastes code that works but is hard to read or understand.
Diagnoses and fixes performance problems in web apps: slow renders, memory leaks, large bundles, waterfall requests, and poor Core Web Vitals. Use when the user says "my app is slow", "too many re-renders", "memory leak", "LCP is bad", "bundle is too large", "this feels laggy", "optimize this component", or shares performance profiler output or Lighthouse results.
Audits package.json dependencies for outdated packages, security vulnerabilities, unnecessary deps, and version issues. Use when the user says "audit my dependencies", "check my packages", "what deps should I update", "clean up package.json", "are there security issues in my deps", or pastes a package.json.
Reviews UI components and HTML for accessibility issues based on WCAG 2.1 AA standards. Use when the user says "check accessibility", "is this accessible", "WCAG review", "a11y audit", "fix accessibility issues", or pastes a React component, HTML, or JSX and asks for accessibility feedback.
Reviews code for bugs, security vulnerabilities, performance issues, and readability problems. Use when the user says "review this code", "check my code", "what's wrong with this", "code review", "audit this file", or pastes code and asks for feedback. Works with any language but optimized for TypeScript, JavaScript, React, and Node.js.
Generates correct conventional commit messages from a diff, file list, or change description. Use when the user says "write a commit message", "generate a commit", "what should I name this commit", "help me commit this", or pastes a git diff or list of changed files. Also apply when the user asks to squash, split, or rewrite existing commit messages.
Documents REST API endpoints with complete request/response examples, error codes, authentication, and parameters. Use when the user says "document this endpoint", "write API docs for...", "generate API documentation", "add docs to my route", "write OpenAPI for this", or pastes a route handler, controller, or function and asks for documentation.
Generates complete, structured pull request descriptions. Use when the user says "write a PR description", "generate a pull request", "describe my changes", "write the PR for this diff", "help me document this PR", or pastes a git diff, commit list, or change summary and asks for a description.
Guides building and deploying full-stack applications on AWS using SST v3 (Ion). Use when the user says "deploy to AWS with SST", "set up sst.config.ts", "add a Lambda function", "connect a queue or bucket", "manage SST secrets", "run sst dev", "set up multi-stage deployments", or "migrate from SST v2 to v3". Apply when working with any SST component: Function, ApiGatewayV2, Bucket, Queue, Cron, Postgres, Dynamo, or Nextjs.
Guides writing and refactoring production-grade system prompts for AI SDKs (Vercel AI SDK, Anthropic SDK, OpenAI SDK). Use when the user asks to "write a system prompt", "create agent instructions", "build a chatbot prompt", "improve my system prompt", "refactor this prompt", or when working with the system field in generateText, streamText, or generateObject. Also apply when debugging inconsistent, hallucinated, or off-format model output caused by a weak or missing system prompt.