メニュー
Systematically map an unfamiliar codebase before changing it — entry points, build/test loop, conventions, data flow. Use when starting work in a repo you haven't seen, or asked "how does this codebase work?".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Make the agent improve with every task — review the run, distill lessons into durable memory, and reinforce what worked. Use at the end of any non-trivial task, or when the user asks the agent to "learn from this".
Write a blameless, actionable incident postmortem from the raw facts. Use after an outage/incident, or when asked to write up "what happened" for the team.
Write a reviewer-first pull-request description from the actual branch diff. Use when opening a PR or asked to write/improve a PR description.
Root-cause a bug with a hypothesis-driven loop instead of shotgun edits. Use when a bug isn't obvious after the first look, or when asked to "find out why" something fails.
Write tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches. Use when adding tests for new code or backfilling tests for a fix.
Generate or update a CHANGELOG.md in Keep a Changelog format from real git history. Use when cutting a release, tagging a version, or asked "what changed since…".
SOC 職業分類に基づく
| name | repo-onboarding |
| description | Systematically map an unfamiliar codebase before changing it — entry points, build/test loop, conventions, data flow. Use when starting work in a repo you haven't seen, or asked "how does this codebase work?". |
| version | 1.0.0 |
| license | MIT |
| keywords | ["onboarding","codebase","exploration","architecture","conventions"] |
Resist editing until you can answer: how do I run it, how do I test it, where does the change go, and what style does this house write in?
README.md, then the manifest
(package.json / pyproject.toml / go.mod / Cargo.toml): name, scripts,
dependencies. The scripts block is the repo telling you its verbs.bin/main fields, src/index.*, cmd/,
__main__.py. Trace one request/command end-to-end at skim depth — names
only, no line-reading.git log --name-only -10): error handling pattern, naming, comment density,
test structure. Your changes should be indistinguishable from these.CONTRIBUTING.md, CLAUDE.md, .github/
workflows (what CI actually enforces), lint configs.Write a short map (10–20 lines) before starting the actual task:
run: npm start (src/cli.js) test: npm test, ~6s, green at HEAD
flow: cli.js → commands/* → store.js (all persistence) → index.json
style: ESM, no deps, errors thrown as plain Error, tests in test/*.test.js
care: store.js is imported everywhere; schema changes ripple
rules: CI runs lint+test on 3 OS; commits are conventional
Keep it honest — list what you didn't look at, so later-you knows where the map has blank spots.