discover-repo
Generate a comprehensive AGENTS.md index for a repository with a CLAUDE.md symlink.
Skill by kyzooghost
Chalk Labs
Need help deploying discover-repo?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kyzooghost-discover-repo
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/discover-repo
What's inside
- Skill name
discover-repo- Description
- Generate a comprehensive AGENTS.md index for a repository with a CLAUDE.md symlink. Dispatches parallel subagents to study directory structure, core code, docs, tests, and config, then synthesizes findings into a structured guide for future Claude sessions. Triggers on "/discover-repo", "discover this repo", "generate a CLAUDE.md", "index this codebase", or "study this repo". Use when onboarding to a new codebase or creating documentation for AI-assisted development.
- License
- MIT
- Instructions
- 158 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- example-publisher-claude-md.md · references/
- template.md · references/
SKILL.md (first lines)
# Discover Repo
Generate a high-quality AGENTS.md that serves as an index and architecture guide for the current repository, with a CLAUDE.md symlink for Claude Code compatibility.
## Output
- `AGENTS.md` at the current directory root (primary artifact)
- `CLAUDE.md` symlink pointing to `AGENTS.md`
- If `AGENTS.md` already exists: write to `AGENTS.discovery.md` and symlink `CLAUDE.discovery.md` to it (never overwrite)
## Process
### Phase 1 - Parallel Discovery
Dispatch 5 Agent subagents simultaneously using `subagent_type: "Explore"`. All 5 MUST be dispatched in a single message for parallel execution.
Replace `{cwd}` with the actual current working directory in each prompt.
**Structure Agent:**
```
Explore the repository at {cwd}. Map the directory structure.
Report in clean markdown:
1. DIRECTORY TREE - Annotated tree of the repo showing key files/directories with one-line descriptions.
- 3 levels deep for all directories, up to 5 levels for src/, lib/, core/, and other source directories
- Annotate each significant file with a one-line description
- Skip node_modules/, target/, build/, dist/, .git/, __pycache__/, vendor/
2. LANGUAGES & BUILD SYSTEM - Languages used, build tool (Cargo, npm, Make, etc.), key config files
3. FILE COUNTS - Approximate source file count by language/extension
Cite exact file paths. Be thorough but concise.
Flag anything uncertain with [NEEDS VERIFICATION].
```
**Core Code Agent:**
```
Explore the repository at {cwd}. Understand the core code architecture.
Report in clean markdown:
1. ENTRYPOINTS - Main/entrypoint files (main.rs, main.go, index.ts, etc.). What each does.
2. KEY COMPONENTS TABLE - For each major module/component/service:
| Component | File(s) | Responsibility |
Include specific method/function names that define the component's behavior.
3. DATA FLOW - How data moves through the system. Trace the main happy path from input to output.
4. EXECUTION FLOW - Step-by-step: what happens when the main operation runs.
5. KEY ABSTRACTIONS - Core types, traits/interfaces, data structures. Name, file, one-line description.
6. IF APPLICABLE (include only if found):
- API routes/endpoints table (HTTP, RPC, WebSocket) with method, path, handler, description
- Wire protocol or message types table (tags, payload types, directions)
Cite exact file paths and line numbers. Focus on architecture, not implementation details.
Flag anything uncertain with [NEEDS VERIFICATION].
```
**Docs Agent:**
```
Explore the repository at {cwd}. Extract the project's purpose and existing documentation.
Report in clean markdown:
1. PURPOSE - What does this project do? Why does it exist? Synthesize from README, doc comments, and code.
2. KEY CAPABILITIES - Bullet list of what the system can do.
3. EXISTING DOCS - List all documentation files with a one-line summary of each.
4. PROTOCOL/DOMAIN CONTEXT - If domain-specific: terminology, external system interactions.
5. NOTEWORTHY COMMENTS - Significant code comments explaining architectural decisions (grep for TODO, HACK, NOTE, IMPORTANT, SAFETY, INVARIANT).
6. CROSS-REPO CONTEXT (if applicable) - How this repo relates to sibling repos, external services, or a broader system. Import/dependency relationships with other repos.
7. HARD-WON RULES (if applicable) - Look for lessons-learned files, "do not" comments, removed-code notes, or operational rules embedded in docs/comments. These encode negative knowledge (what NOT to do).
Cite exact file paths. Prefer direct quotes over paraphrasing.
Flag anything uncertain with [NEEDS VERIFICATION].
```
**Tests Agent:**
```
Explore the repository at {cwd}. Understand the test infrastructure.
Report in clean markdown:
1. TEST FILES TABLE:
| File/Directory | Tests (approx) | What it tests |
2. TESTING APPROACH - Unit? Integration? E2E? Frameworks? Test utilities/helpers?
3. CI CONFIGURATION - Read CI configs (.github/workflows/, etc.). What runs, what gates merges.
4. TEST COMMANDS - How to run tests.
Cite exact file paths. Count test functions where possible.
Flag anything uncertain with [NEEDS VERIFICATION].
```
**Config Agent:**
```
Explore the repository at {cwd}. Understand configuration, dependencies, and deployment.
Report in clean markdown:
1. BUILD COMMANDS - How to build, test, lint, format. Check Makefile, justfile, package.json scripts, etc.
2. CONFIGURATION - Config files, environment variables, .env templates.
3. DEPENDENCIES - Top 10-15 most important dependencies and their purpose.
4. DEPLOYMENT - Dockerfile, docker-compose, K8s manifests. Deployment targets.From kyzooghost/skills, MIT.
More from kyzooghost/skills
- 0.570score
pr-review-comments
kyzooghost
Transform security review findings into targeted GitHub PR review comments.
SkillAFreshness: AClaude Code +9 - 0.538score
fix-ci
kyzooghost
Use when the user asks for /fix-ci behavior or the equivalent command workflow.
SkillAFreshness: AClaude Code +9 - 0.529score
create-scoped-tickets
kyzooghost
Decompose a technical implementation spec into mutually exclusive GitHub Agent Work Tickets under one or more labels, either seeding an empty label universe…
SkillBFreshness: BClaude Code +9 - 0.529score
ship-from-plan
kyzooghost
Use when the user provides a completed implementation plan and wants one continuous isolated execution through a reviewed, CI-green pull request marked ready…
SkillBFreshness: BClaude Code +9 - 0.524score
scoped-planning
kyzooghost
Per-stage scope-check overlay across the planning lifecycle.
SkillBFreshness: BClaude Code +9 - 0.524score
scoped-differential-review
kyzooghost
Wraps a vendored differential-review skill and routes its findings against a GitHub issue-label universe.
SkillBFreshness: BClaude Code +9 - 0.524score
complexity-review
kyzooghost
Review a PR for unnecessary complexity, brittle test strategies, and overengineering.
SkillBFreshness: BClaude Code +9 - 0.479score
sync-command
kyzooghost
Sync a command from this repo into local agent surfaces.
SkillCFreshness: CClaude Code +9 - 0.479score
sync-skill
kyzooghost
Sync a skill from this repo into the local machine's skill directories.
SkillCFreshness: CClaude Code +9 - 0.479score
llm-wiki
kyzooghost
Build and maintain a personal knowledge wiki using LLMs.
SkillCFreshness: CClaude Code +9 - 0.474score
perf-review
kyzooghost
Use when drafting a periodic performance review (annual review, mid-year, promo packet, peer feedback) from monthly win reports and supporting sources, where…
SkillCFreshness: CClaude Code +9 - 0.474score
handover
kyzooghost
Prepare a structured handover document from the current session for a fresh Claude session to continue the work.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 25, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kyzooghost/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kyzooghost
- 0.570score
pr-review-comments
kyzooghost
Transform security review findings into targeted GitHub PR review comments.
SkillAFreshness: AClaude Code +9 - 0.538score
fix-ci
kyzooghost
Use when the user asks for /fix-ci behavior or the equivalent command workflow.
SkillAFreshness: AClaude Code +9 - 0.529score
create-scoped-tickets
kyzooghost
Decompose a technical implementation spec into mutually exclusive GitHub Agent Work Tickets under one or more labels, either seeding an empty label universe…
SkillBFreshness: BClaude Code +9 - 0.529score
ship-from-plan
kyzooghost
Use when the user provides a completed implementation plan and wants one continuous isolated execution through a reviewed, CI-green pull request marked ready…
SkillBFreshness: BClaude Code +9 - 0.524score
complexity-review
kyzooghost
Review a PR for unnecessary complexity, brittle test strategies, and overengineering.
SkillBFreshness: BClaude Code +9 - 0.524score
scoped-differential-review
kyzooghost
Wraps a vendored differential-review skill and routes its findings against a GitHub issue-label universe.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get discover-repo running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
discover-repo skill. Agent Mart. https://agentmart.dev/skills/kyzooghost-discover-repo (last updated 2026-10-24)