Skip to content

hoavdc/CodexKit / skills/codexkit-repo-onboarding

codexkit-repo-onboarding

Verified

Rapidly map a new codebase, identify the runtime model, risk zones, and first high-value next steps.

FileKindSize
SKILL.mdskill md2.3 KB
agents/openai.yamlconfig194 B
examples/common-mistakes.mdmarkdown778 B
examples/good-output.mdmarkdown909 B
verification/checklist.mdmarkdown1.3 KB

verification/checklist.md

View on GitHub
# 4C Verification Checklist — Repo Onboarding

> Use this checklist after generating output. Answer each question honestly.

## Correctness — Is it right?

- [ ] Architecture description matches the actual codebase structure
- [ ] Setup instructions work on a clean machine from scratch
- [ ] Listed dependencies are current and version-accurate

## Completeness — Is it done?

- [ ] Covers: purpose, architecture, setup, key abstractions, conventions, where to start
- [ ] Environment requirements include OS, language versions, and required services
- [ ] Common gotchas and known issues are documented

## Context-fit — Does it match?

- [ ] Depth matches the reader's expected role (contributor vs maintainer vs reviewer)
- [ ] Code examples reference actual files in the repo, not hypothetical patterns
- [ ] Complexity areas are identified: 'This module is tricky because...'

## Consequence — Is it safe to use?

- [ ] If a new dev follows this guide, can they make their first PR within 24 hours?
- [ ] If setup fails at step 3, is troubleshooting guidance provided?
- [ ] If the repo structure changes, how quickly will this guide become outdated?

---

**Final question:** _If this output were used immediately in production, what is the single biggest risk?_

Write the answer here before considering the skill output complete.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall