01-discovery
Skill1 starsChanged 53 days agoMITView on GitHub
Version: 1.0.0 Compatible: project_skills >= 1.0 Requires: (none — this is the first skill) Outputs: project-location.md, repository-map.md Find the project within the repository. A repository may contain a single project at root, a monorepo, a partial project, or no code at all. Discovery locates what actually exists before anything else happens. List the top-level structure. Look for: For monorepos, identify which sub-projects exist and which one the current task relates to. For separated structures, identify frontend vs backend vs shared.
Files
01-Discovery Skill
Version: 1.0.0 Compatible: project_skills >= 1.0 Requires: (none — this is the first skill) Outputs: project-location.md, repository-map.md
Purpose
Find the project within the repository. A repository may contain a single project at root, a monorepo, a partial project, or no code at all. Discovery locates what actually exists before anything else happens.
Process
Step 1: Map the repository
List the top-level structure. Look for:
- Single project at root (most common)
apps/,services/,packages/,modules/→ monoreposrc/,app/,backend/,frontend/,api/→ separated concernsdocs/only → documentation project, no code yet- Nothing recognizable → may be a design or planning repo
Step 2: Identify project boundaries
For monorepos, identify which sub-projects exist and which one the current task relates to.
For separated structures, identify frontend vs backend vs shared.
Step 3: Record what is found
For each project or sub-project, record:
- Path
- What it appears to be (frontend, backend, worker, library, etc.)
- Any detection signals present (package.json, Cargo.toml, etc.)
- Whether code exists or only design/docs
Step 4: Identify the target
Determine which project the current task applies to. If ambiguous, report the ambiguity rather than guessing.
Outputs
project-location.md
Discovery Results
=================
Repository: [url or path]
Structure: [single | monorepo | separated | design-only | unknown]
Projects found:
- [path]: [type], [code: yes/no], [signals: ...]
Target project: [path or "not yet determined"]
Rationale: [why this target]repository-map.md
A tree or list of the repository structure with annotations about what each directory appears to contain.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- 00-orchestratorSkill
- 02-project-contextSkill
- 03-business-architectureSkill
- 04-architectureSkill
- 05-documentationSkill
- 06-codebase-auditSkill
- 07-securitySkill
- 08-testingSkill
- 09-performanceSkill
- 10-auditSkill
- 11-controlled-source-of-truthSkill
- 12-context-engineeringSkill
- 13-phase-loop-deliverySkill
- 14-forensics-and-debuggingSkill
- 15-autonomous-loop-and-simplificationSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

