doc-scanner
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.
94
Quality
92%
Does it follow best practices?
Impact
98%
2.00xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Evaluation results
100%
52%Onboarding Documentation Summary
Documentation synthesis format
Glob scan performed
0%
100%
All known file types scanned
0%
100%
All found files read
50%
100%
PROJECT DOCUMENTATION header
0%
100%
Sources list present
75%
100%
RECOMMENDED AGENTS section
50%
100%
KEY WORKFLOWS section
50%
100%
CONVENTIONS section
50%
100%
QUICK COMMANDS section
50%
100%
Priority order respected
80%
100%
Summary written to file
100%
100%
Without context: $0.1531 · 31s · 10 turns · 12 in / 1,749 out tokens
With context: $0.5015 · 1m 44s · 28 turns · 572 in / 5,802 out tokens
100%
62%Tidy Up AI Documentation
Multi-doc consolidation workflow
.doc-archive/ created
0%
100%
Originals archived
100%
100%
Date suffix on archives
0%
100%
Unified AGENTS.md generated
0%
100%
AGENTS.md contains merged content
0%
100%
Consolidation report produced
100%
100%
Source files no longer in root
100%
100%
Glob-based discovery
20%
100%
Without context: $0.3626 · 1m 17s · 23 turns · 28 in / 4,524 out tokens
With context: $0.5819 · 2m 5s · 35 turns · 294 in / 7,194 out tokens
95%
32%Bootstrap Agent Documentation for a New Project
No-docs AGENTS.md generation
Glob scan attempted
0%
50%
No-docs condition recognised
0%
100%
AGENTS.md generated
100%
100%
Project structure observed
100%
100%
Tech stack reflected
100%
100%
RECOMMENDED AGENTS section
0%
100%
KEY WORKFLOWS section
50%
100%
CONVENTIONS section
70%
100%
QUICK COMMANDS section
92%
100%
Without context: $0.2293 · 1m 6s · 12 turns · 19 in / 3,639 out tokens
With context: $0.3988 · 1m 32s · 20 turns · 272 in / 5,085 out tokens
- Repository
- NeverSight/skills_feed
- Commit
5342bca
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.