cluster-documents
Automated content similarity and grouping analysis. Groups related documents by topic, purpose, or content similarity.
Install with Tessl CLI
npx tessl i github:dandye/ai-runbooks --skill cluster-documents46
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description provides a reasonable overview of the skill's purpose but suffers from missing explicit trigger guidance, which is critical for skill selection. It names the domain adequately but lacks the concrete action details and natural user keywords that would help Claude confidently choose this skill over alternatives.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user asks to cluster documents, find similar content, group files by topic, or identify duplicate content.'
Include more natural trigger terms users would say: 'cluster', 'categorize', 'organize by similarity', 'find duplicates', 'group similar files'.
Add specific concrete actions: 'Calculates similarity scores, generates topic clusters, produces grouping reports, identifies near-duplicates.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (content similarity/grouping) and some actions ('groups related documents'), but lacks comprehensive concrete actions like specific algorithms, output formats, or detailed operations. | 2 / 3 |
Completeness | Describes what it does but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms ('content similarity', 'grouping', 'documents', 'topic'), but misses common user variations like 'cluster', 'categorize', 'organize', 'deduplicate', or 'find similar'. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to similarity/grouping analysis, but 'documents' and 'content' are generic enough to potentially overlap with document processing, search, or organization skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a high-level specification than actionable guidance for Claude. It describes the conceptual workflow for document clustering but provides no executable code, specific library usage, or concrete examples. The lack of implementation details means Claude would need to figure out the actual approach independently.
Suggestions
Add executable Python code examples using specific libraries (e.g., scikit-learn for clustering, sentence-transformers for embeddings) with copy-paste ready implementations
Include a concrete example showing sample input documents and the expected output format with actual JSON structure
Add validation steps such as checking minimum document count, verifying embedding generation succeeded, and validating cluster quality metrics
Specify exact output format with a JSON schema example rather than just describing the structure in prose
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some unnecessary structure like the 'Quick Reference' section that adds little value. The workflow steps could be more compact. | 2 / 3 |
Actionability | The skill describes what to do at a high level but provides no executable code, no specific library recommendations, no concrete commands, and no examples of actual clustering implementation. It reads like a specification rather than actionable guidance. | 1 / 3 |
Workflow Clarity | Steps are listed in sequence but lack validation checkpoints. There's no guidance on what to do if clustering fails, how to verify results, or how to handle edge cases like empty documents or encoding issues. | 2 / 3 |
Progressive Disclosure | The content is reasonably organized with clear sections, but for a skill of this complexity, it would benefit from references to detailed implementation guides or example files rather than keeping everything abstract in one file. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- 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.