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.
90
86%
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 what the skill does (scans and synthesizes project documentation files across 15+ formats), when it should activate (with multiple explicit trigger scenarios), and what makes it unique (focus on AI agent documentation files and consolidation into AGENTS.md). The description is comprehensive yet concise, uses third person voice correctly, and includes natural trigger terms that users would actually say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scans for documentation files, synthesizes guidance, consolidates 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, consolidates into unified AGENTS.md) and 'when' (explicit auto-activation triggers: reviewing codebases, starting new projects, asking about conventions, when documentation context would help). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'review', 'understand', 'explore a codebase', 'new project', 'conventions', 'agents', 'documentation'. Also lists specific file names (AGENTS.md, CLAUDE.md, CURSOR.md, etc.) that users might reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on AI agent documentation files (AGENTS.md, CLAUDE.md, COPILOT.md, etc.) and their consolidation. The specific file format enumeration and the consolidation use case make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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, concise skill that clearly communicates its purpose and workflow. Its main weaknesses are the lack of executable commands/code (particularly for the glob scanning and file consolidation steps) and the absence of validation checkpoints before the destructive consolidation operation. The progressive disclosure is handled well with external references for detailed patterns and templates.
Suggestions
Add executable glob patterns or tool invocation examples (e.g., the exact Glob tool call syntax) instead of a plain text file list.
Add an explicit validation/confirmation checkpoint before Step 4's destructive consolidation (e.g., 'Present the list of files to be archived and get user confirmation before proceeding').
Include concrete commands for the archival process (e.g., `mkdir -p .doc-archive && mv CLAUDE.md .doc-archive/CLAUDE.md.2025-01-15`).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section serves a purpose, there's no explanation of what documentation files are or why scanning matters, and it assumes Claude knows how to use Glob and read files. | 3 / 3 |
Actionability | The steps are clear but lack executable code. The Glob pattern is listed as a plain text list rather than an actual glob command, the synthesis output is a template outline rather than a concrete example, and the consolidation step lacks specific commands (e.g., mkdir, mv with date formatting). | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and covers the happy path plus the no-docs-found case. However, the consolidation step (Step 4) involves destructive operations (archiving/moving original files) without any validation checkpoint or confirmation step before proceeding, which should cap this at 2. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-organized sections and appropriately references detailed content in one-level-deep external files (./references/file-patterns.md and ./references/templates.md) for patterns and templates. | 3 / 3 |
Total | 10 / 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
e437c3c
- 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.