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
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities (scanning for 15+ documentation formats, synthesizing guidance, consolidating docs), provides explicit trigger conditions with natural language terms, and carves out a distinct niche around AI agent documentation files. The description uses proper third-person voice and balances comprehensiveness with clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Scans for project documentation files', 'synthesizes guidance', 'consolidate multiple platform docs into unified AGENTS.md'. Also enumerates specific file formats (AGENTS.md, CLAUDE.md, GEMINI.md, etc.). | 3 / 3 |
Completeness | Clearly answers both what ('Scans for project documentation files and synthesizes guidance', 'consolidate multiple platform docs') AND when ('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'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'review', 'understand', 'explore a codebase', 'new project', 'conventions', 'agents', 'documentation'. Also lists specific file names users might reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific file formats (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, etc.) and clear niche around AI agent documentation files. Unlikely to conflict with general documentation or code review skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent organization and clear workflow steps. The content is appropriately concise and assumes Claude's competence. The main weakness is the lack of executable code examples for the scanning and file reading operations, relying instead on descriptive instructions.
Suggestions
Add an executable glob command or code snippet showing exactly how to perform the scan (e.g., actual Glob tool invocation syntax)
Include a concrete example of reading and parsing one documentation file to show the expected input/output transformation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, with no unnecessary explanations. It assumes Claude knows what glob patterns are and how to read files, focusing only on the specific task at hand. | 3 / 3 |
Actionability | Provides clear steps and a template output format, but lacks executable code examples. The glob pattern list and synthesis template are helpful but the actual commands/code to execute are missing (e.g., no actual glob command syntax shown). | 2 / 3 |
Workflow Clarity | Clear 5-step sequence with logical progression from scanning to synthesis to consolidation. Includes a fallback path (Step 5) for when no documentation is found, demonstrating good workflow coverage. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections and appropriate references to external files (file-patterns.md, templates.md) for detailed content. The main skill stays focused on the overview while pointing to deeper resources. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
5342bca
- Reviewed
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.