docs-cleaner
Consolidates redundant documentation while preserving all valuable content. This skill should be used when users want to clean up documentation bloat, merge redundant docs, reduce documentation sprawl, or consolidate multiple files covering the same topic. Triggers include "clean up docs", "consolidate documentation", "too many doc files", "merge these docs", or when documentation exceeds 500 lines across multiple files covering similar topics.
82
73%
Does it follow best practices?
Impact
96%
1.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs-cleaner/SKILL.mdQuality
Discovery
89%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 a well-crafted skill description with strong trigger terms and excellent completeness, clearly answering both what the skill does and when to use it. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed during consolidation (e.g., deduplication, merging, restructuring). Overall it would perform well in a multi-skill selection scenario.
Suggestions
Expand the capability description with more specific actions, e.g., 'identifies duplicate content across files, merges overlapping sections, removes outdated information, and updates cross-references' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (documentation) and a primary action (consolidates redundant documentation while preserving valuable content), but doesn't list multiple specific concrete actions like 'identify duplicates, merge sections, remove outdated content, update cross-references'. | 2 / 3 |
Completeness | Clearly answers both 'what' (consolidates redundant documentation while preserving valuable content) and 'when' (explicit 'Use when' clause with multiple trigger scenarios and even specific trigger phrases). The explicit trigger guidance is thorough. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'clean up docs', 'consolidate documentation', 'too many doc files', 'merge these docs', 'documentation bloat', 'documentation sprawl', and the quantitative trigger of exceeding 500 lines. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around documentation consolidation and redundancy reduction, with specific triggers that are unlikely to conflict with general documentation writing or editing skills. The 500-line threshold adds further distinctiveness. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured skill for documentation consolidation with good organization and a clear phased workflow. Its main weaknesses are the lack of concrete, executable guidance (no specific commands or tool invocations) and missing validation gates before destructive operations like file deletion. The content would benefit from more actionable instructions and explicit verification steps.
Suggestions
Add concrete commands for the discovery phase (e.g., `find . -name '*.md' | xargs wc -l` or specific tool invocations) to make the workflow actionable rather than descriptive.
Move the Value Preservation Checklist before Phase 4 execution and add an explicit validation gate: 'Only proceed with deletion after confirming all checklist items are preserved in the consolidated document.'
Add a concrete example of a before/after consolidation showing actual markdown content being merged, not just line count metrics.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary framing (e.g., 'Core Principle' section restates what should be implicit, and some table entries explain obvious concepts). The anti-patterns table adds value but could be slightly tighter. | 2 / 3 |
Actionability | Provides a structured workflow with concrete examples like the value analysis table and before/after metrics, but lacks executable commands or code. The steps are descriptive rather than prescriptive—'Identify all documentation files' doesn't specify how (e.g., a grep/find command). No concrete tool usage or copy-paste ready instructions. | 2 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced and logical, but Phase 4 involves destructive operations (deleting files, updating references) without explicit validation checkpoints or feedback loops. There's no 'verify before committing deletions' step or rollback guidance. The checklist is present but positioned after execution rather than as a gate before it. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, appropriate use of tables, and a reference to an external template file (value_analysis_template.md) for detailed criteria. The skill stays at overview level while pointing to deeper resources, and the organization makes it easy to navigate. | 3 / 3 |
Total | 9 / 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
- fernandezbaptiste/claude-code-skills
- Commit
4f0eae8
- 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.