project-discovery — Claude Code skill: codebase map and stack
project-discovery is a Claude Code skill that maps a codebase’s structure, tech stack, entry points, and documentation mismatches against actual code.
MIT ★ 587 updated 2026-10-26
/plugin marketplace add rsmdt/the-startup
/plugin install team@the-startupWhat project-discovery does
project-discovery reads manifests, configs, and file layout to identify architecture, frameworks, package managers, and key modules. It verifies claims from README and specs against real code and highlights discrepancies.
The skill uses search patterns from reference/search-patterns.md and reference/framework-signatures.md to detect frameworks through multiple signals at once: dependencies plus config plus file structure. The final report lists technologies, conventions, verified and outdated documentation parts.
It skips node_modules and vendor unless explicitly asked. Returns confidence level for findings and suggests what to inspect next.
What it helps with
- map an unfamiliar codebase during onboarding
- locate entry points and key modules in a project
- identify frameworks and tools from configs and dependencies
- verify documentation against actual implementation
- flag outdated or conflicting README sections
Example prompts for the agent
- Build a map of the project: architecture, stack, entry points
- Check if the README matches the actual code structure
- Find frameworks and package managers in this repo
How to install project-discovery
1Plugin marketplace
/plugin marketplace add rsmdt/the-startup/plugin install team@the-startupThis installs the whole team plugin with all its skills
2Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill project-discovery -a claude-code3Manually: put the files in place
~/.claude/skills/project-discovery/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/project-discovery/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill project-discovery -a codex2Manually: put the files in place
.agents/skills/project-discovery/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill project-discovery -a cursor2Manually: put the files in place
.cursor/skills/project-discovery/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rsmdt/the-startup plugins/team/skills/cross-cutting/project-discovery2Manually: put the files in place
.github/skills/project-discovery/SKILL.md1Skills CLI (Vercel)
npx skills add rsmdt/the-startup --skill project-discovery -a gemini-cli2Platform CLI
gemini skills install https://github.com/rsmdt/the-startup --path plugins/team/skills/cross-cutting/project-discoveryManually: put the files in place
.devin/skills/project-discovery/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about project-discovery
How to install project-discovery in Claude Code?
Run /plugin marketplace add rsmdt/the-startup, then /plugin install team@the-startup.
What does project-discovery do?
The skill analyzes project structure, detects the tech stack, and cross-checks documentation against real code. It outputs a report with architecture, frameworks, entry points, and documentation mismatches.
How does project-discovery identify frameworks?
It checks dependencies in manifests, presence of configs, and file layout simultaneously, not relying on a single indicator. The reference/framework-signatures.md reference holds detection signatures.
Source text
SKILL.md · MIT
---
name: project-discovery
description: Unified codebase discovery across structure navigation, tech-stack detection, and documentation extraction. Use when onboarding to a project, locating implementation paths, identifying frameworks/tooling, or validating docs against code reality.
---
## Persona
Act as a project discovery specialist that builds a fast, reliable map of a codebase: structure, stack, and documentation truth.
**Discovery Target**: $ARGUMENTS
## Interface
ProjectDiscoveryReport {
architecture: string
techStack: string[]
packageManagers: string[]
keyEntryPoints: string[]
criticalDocs: string[]
docMismatches: string[]
conventions: string[]
confidence: HIGH | MEDIUM | LOW
}
State {
target = $ARGUMENTS
files = []
docs = []
findings = []
}
## Constraints
**Always:**
- Start with repo/documentation overview, then narrow to target scope.
- Verify framework detection using multiple signals (manifest + config + structure).
- Cross-check critical documentation claims against implementation.
- Prefer narrow searches in relevant directories after initial mapping.
**Never:**
- Assume stack or architecture from a single indicator.
- Treat docs as authoritative without verification for high-impact claims.
- Scan dependency/vendor directories unless explicitly required.
## Reference Materials
- `reference/search-patterns.md` — Glob/Grep patterns for structure analysis, implementation tracing, and architecture mapping
- `reference/framework-signatures.md` — Detection signatures for frontend, backend, build, CSS, DB, testing, API, monorepo, mobile, and deployment frameworks
- `reference/error-handling-patterns.md` — Error classification, handling patterns, and logging level guidance
## Workflow
### 1. Map Structure
- Identify top-level modules, entry points, and test locations.
- Identify config/manifests for language/tooling.
### 2. Detect Stack
- Detect ecosystems/package managers from lock/manifests.
- Detect frameworks/build/test tooling from dependency + config + file layout.
### 3. Extract and Verify Docs
- Read README/spec/config docs relevant to target.
- Flag outdated, conflicting, or missing documentation.
### 4. Build Discovery Report
- Summarize architecture, stack, conventions, and verified/mismatched doc claims.
- Highlight unknowns and next best inspection steps.
© Rudolf S. · MIT · rsmdt/the-startup