Skip to content

JPeetz/agent-skills / skills/development/repo-recon

repo-recon

Verified

Use this skill when you need to map an unfamiliar codebase before changing anything. Runs a systematic five-step recon pass — read the map, learn the commands, trace one flow end-to-end, note conventions then match them, and write it down — so you understand architecture, build/test commands, and code conventions before making a single edit. Prevents broken builds, misfiled changes, and convention-violating PRs caused by search-before-assuming. Activates on "where do I start", "understand this codebase", "how do I build/test this", "what are the conventions here", and first-time work in any repository.

FileKindSize
CHANGELOG.mdmarkdown1.3 KB
LICENSEother1.0 KB
SKILL.mdskill md8.4 KB
evals/evals.jsonconfig1.9 KB

evals/evals.json

View on GitHub
{
  "skill": "repo-recon",
  "version": "1.0.0",
  "cases": [
    {
      "id": "e1",
      "description": "Should trigger: first time in a repo, general orientation",
      "input": "I just cloned this repository. Where do I even start? Help me understand the codebase before I change anything.",
      "shouldTrigger": true,
      "expect": "Five-step recon pass: read the map, learn commands, trace one flow, note conventions, write it down"
    },
    {
      "id": "e2",
      "description": "Should trigger: onboarding into a codebase before first ticket",
      "input": "I'm onboarding into the payments repo. Walk me through what the code does and how to build and test it before I pick up my first ticket.",
      "shouldTrigger": true,
      "expect": "Repo map plus verified build/test/run commands, no code changes"
    },
    {
      "id": "e3",
      "description": "Should trigger: learn conventions before writing code",
      "input": "What are the naming and testing conventions in this codebase so my PR doesn't get rejected for style?",
      "shouldTrigger": true,
      "expect": "Convention list from actual sources (not assumptions): naming, structure, error handling, test style"
    },
    {
      "id": "e4",
      "description": "Should trigger: trace a single flow end-to-end",
      "input": "Trace how an order flows through this system from the API to the database — first time I've looked at this project.",
      "shouldTrigger": true,
      "expect": "One flow traced end-to-end with file:line anchors from entry point to output"
    },
    {
      "id": "n1",
      "description": "Should NOT trigger: unrelated framework comparison question",
      "input": "We're choosing between React and Svelte for our next app — what are the tradeoffs?",
      "shouldTrigger": false,
      "expect": "Framework comparison, not codebase reconnaissance"
    }
  ]
}
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall