Skip to content
Back to skills

Doc Scanner

ASecurity

Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance. Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project, when asking about conventions or agents, or when documentation context would help. Can consolidate multiple platform docs into unified AGENTS.md.

  • 6 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 8, 2026
ai-agentsbashgitdocumentation

Works with

  • cursor
  • vscode
  • terminal

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 8, 2026

npx -y skills add bg-szy/TOP-SKILLS --skill doc-scanner --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Doc Scanner?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Doc Scanner
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/bg-szy-doc-scanner/badge)](https://www.skillsdirectory.com/skills/bg-szy-doc-scanner)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: doc-scanner
description: "Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance. Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project, when asking about conventions or agents, or when documentation context would help. Can consolidate multiple platform docs into unified AGENTS.md."
license: MIT
allowed-tools: "Glob Read Write Bash"
metadata:
  author: claude-mods
  related-skills: "repo-doctor, adr-ops"
---

# Documentation Scanner

Scan for and synthesize project documentation.

## When to Activate

- User asks to review, understand, or explore a codebase
- Starting work in a new/unfamiliar project
- User asks about project conventions or workflows
- Before making significant architectural decisions

## Instructions

### Step 1: Scan for Documentation

Use Glob to search project root:

```
AGENTS.md, CLAUDE.md, AI.md, ASSISTANT.md,
GEMINI.md, COPILOT.md, CHATGPT.md, CODEIUM.md,
CURSOR.md, WINDSURF.md, VSCODE.md, JETBRAINS.md,
WARP.md, FIG.md, DEVCONTAINER.md, GITPOD.md
```

### Step 2: Read All Found Files

Read complete contents of every documentation file found.

### Step 3: Synthesize

Combine information into unified summary:

```
PROJECT DOCUMENTATION

Sources: [list files found]

RECOMMENDED AGENTS
  Primary: [agents for core work]
  Secondary: [agents for specific tasks]

KEY WORKFLOWS
  [consolidated workflows]

CONVENTIONS
  [code style, patterns]

QUICK COMMANDS
  [common commands]
```

### Step 4: Offer Consolidation

If 2+ documentation files exist, offer to consolidate:

1. Create `.doc-archive/` directory
2. Archive originals with date suffix
3. Generate unified AGENTS.md
4. Report what was consolidated

### Step 5: No Documentation Found

If none found, offer to generate AGENTS.md based on:
- Project structure and tech stack
- Patterns observed in codebase

## Priority Order

1. AGENTS.md (platform-agnostic)
2. CLAUDE.md (Claude-specific)
3. Other AI docs
4. IDE docs
5. Terminal docs

## Additional Resources

For detailed patterns, load:
- `./references/file-patterns.md` - Complete list of files to scan
- `./references/templates.md` - AGENTS.md generation templates

When generating a NEW AGENTS.md, follow the entry-doc standard in
`rules/agentic-quality.md` (Landmines section mandatory, ~150-line budget) —
skeleton at the repo-doctor skill's `assets/AGENTS-template.md`. To AUDIT an
existing doc set rather than generate one, hand off to `repo-doctor`.

Files in this skill

  • SKILL.md2.5 KB
  • reference.md2.5 KB
  • skill-report.json55.9 KB
  • templates.md3.4 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.