explore-codebase
Skill0 starsChanged 15 days agoMITView on GitHub
Map an unfamiliar repository — stack, install/run/test/lint commands, layout, entry points, and conventions. Report a map and proposed AGENTS.md updates from evidence without writing files. Use when starting in a new repo, onboarding, or before changing code you have not read. Do not invent commands.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- rpraharaj/ai-engineertheir own version, first seen Nov 1, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
- ashvin-to/BaseMemtheir own version, first seen Oct 19, 2026
- Arasz/ai-badgertheir own version, first seen Oct 11, 2026
- johanolofsson72/Claudetheir own version, first seen Oct 2, 2026
- aprameyak/coding-skillstheir own version, first seen Oct 2, 2026
Used with
Projects with it also use debug-issue, review-changes and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
NVIDIASkilldebug-issue
Use when the user asks to debug, investigate, or fix a GitHub issue or supplies a repository bug report.
Also in 5 projects that use this
DockerSkillreview-changes
Review uncommitted or recently committed documentation changes for correctness, coherence, and style compliance. Use before creating a PR to catch issues. "review my changes", "review the diff", "check the fix before submitting", "does this look right".
Also in 4 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- tirth8205/code-review-graph★ 33ksame name
- Arasz/ai-badger★ 3same name
- iadr-dev/colab★ 2same name
- imMamdouhaboammar/get-things-done★ 2same name
- johanolofsson72/Claude★ 2same name
- aprameyak/coding-skills★ 1same name
- ashvin-to/BaseMem★ 1same name
- exactbee/claude-code-workflow★ 1same name
- KMaruthi2002/universal-llm-skills★ 1same name
- rpraharaj/ai-engineer★ 1same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- update-raidSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Read root AGENTS.md if present.
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Explore codebase
A stranger can run, test, and change this repo without guessing. Do not implement product features. Do not invent commands you did not see in a file or run successfully.
Is this the right skill?
| Signal | Do this instead |
| How one feature works | explain-code |
| Empty tree, start an app | start-project |
| Shape a change you already understand | shape-work |
Required inputs
- A workspace you can list and read
- Git root if this is a repo (
git rev-parse --show-toplevel)
Human decisions (do not invent)
- None for the map. Do not invent glossary jargon.
Procedure
- Read root
AGENTS.mdif present. Record Root. - Detect stack only from files that exist (manifests, lockfiles, CI). See references/stack-evidence.md.
- Resolve Install / Run / Test / Lint / Typecheck / Build from manifests or CI. Prefer the CI command. Else
(unknown). Never inventnpm test. - Stay read-only: use read/search commands only. Record discovered checks as
not run; hand execution toverifierand dependency installation toimplementer. Do not run tests, install dependencies, or start servers in an explore session. - Map layout from README + shallow listing (not
node_modules/vendor/dist/.git). - Open references/agents-template.md and report proposed managed blocks. A
plannersession may persist them: replace only matching managed blocks; if absent, append the managed repo section without overwriting existing commands or program-context pointers. Flag conflicting commands for resolution. Glossary facts live only incontext/glossary.md; propose additions there, or report terms in the reply if that file does not exist.
Output
- Path: reply; optional planner handoff for root
AGENTS.mdmanaged sections - Template:
references/agents-template.md
Quality bar
- Every command is from a file you opened or a command you ran
- Unknowns are
(unknown) - No invented glossary terms
- No secrets
- No files edited or executable checks run by the explore profile
Done
- Root and languages
- Commands you ran and pass/fail
- Layout + do-not-edit
- Proposed
AGENTS.mdblocks and any planner / verifier / implementer handoffs - Next:
shape-workordebug— not a drive-by refactor
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.