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.

2.00x

Quality

78%

Does it follow best practices?

Impact

98%

2.00x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/doc-scanner/SKILL.md

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, reasonably actionable skill body with a clear step sequence, undermined by missing validation checkpoints for its destructive/batch consolidation step and by references to bundle files that do not exist.

Suggestions

Add an explicit validation checkpoint before archiving originals and overwriting with the unified AGENTS.md (e.g., confirm the synthesis is complete and originals are safely archived before replacing).

Create the referenced ./references/file-patterns.md and ./references/templates.md files, or remove the dangling references and keep the content inline to avoid broken navigation.

Tighten actionability by giving the exact Glob pattern(s) to run and the precise archive-naming convention (e.g., 'AGENTS.md.2026-08-14.bak') instead of 'archive originals with date suffix'.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — terse step descriptions, a compact file list, and a fill-in template with no padding or explanation of concepts Claude already knows. Every token earns its place.	5 / 5
Actionability	Provides a concrete file list to glob, a specific synthesis output template, and explicit consolidation steps. Mostly executable, but 'archive originals with date suffix' and the Glob invocation lack exact commands/patterns, leaving minor gaps.	4 / 5
Workflow Clarity	Steps 1–5 are clearly sequenced, but the workflow includes batch and destructive operations (reading all docs, archiving originals with date suffix, overwriting with a unified AGENTS.md) with no validation or verification checkpoints. Per the rubric, missing validation in destructive/batch workflows caps this at 3.	3 / 5
Progressive Disclosure	Sections are well organized and two references are signaled one level deep under 'Additional Resources', but those referenced files (./references/file-patterns.md, ./references/templates.md) do not exist in the bundle, breaking navigation. The full file list is also duplicated inline rather than offloaded to the reference.	3 / 5
	Total	15 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that clearly states both capabilities and activation triggers with concrete examples. Its main weakness is that some activation triggers are broad enough to risk overlap with general code-exploration skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Scans for project documentation files', 'synthesizes guidance', 'consolidate multiple platform docs into unified AGENTS.md' — with an explicit list of formats. Falls short of 5 because 'synthesizes guidance' is somewhat generic and the action set, while multiple, has minor gaps.	4 / 5
Completeness	Explicitly answers both what ('Scans for project documentation files... and synthesizes guidance... Can consolidate...') and when ('Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — 'review, understand, or explore a codebase', 'starting work in a new project', 'asking about conventions or agents'. Good coverage but not quite comprehensive enough for a 5; a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The documentation-scanning/AGENTS.md-consolidation niche is mostly distinct, but broad triggers like 'review, understand, or explore a codebase' create minor overlap risk with general codebase-exploration skills, keeping it below 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/doc-scanner/SKILL.md
Commit: 2f57aec

Reviewed: about 23 hours ago

Table of Contents

Discovery Implementation Validation

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.