JPeetz/agent-skills / skills/development/repo-recon
repo-recon
VerifiedUse 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.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 1.3 KB |
| LICENSE | other | 1.0 KB |
| SKILL.md | skill md | 8.4 KB |
| evals/evals.json | config | 1.9 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"
}
]
}Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |