running-clustering-algorithms
Analyze datasets by running clustering algorithms (K-means, DBSCAN, hierarchical) to identify data groups. Use when requesting "run clustering", "cluster analysis", or "group data points". Trigger with relevant phrases based on skill purpose.
52
42%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ai-ml/clustering-algorithm-runner/skills/running-clustering-algorithms/SKILL.mdQuality
Discovery
85%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 is solid with specific algorithms listed, a clear 'Use when' clause, and good distinctiveness. However, the final sentence 'Trigger with relevant phrases based on skill purpose' is meaningless filler that adds no value, and the trigger terms could include more natural user variations like 'segmentation' or 'find groups'.
Suggestions
Remove the vague filler sentence 'Trigger with relevant phrases based on skill purpose' as it provides no actionable information.
Add more natural trigger term variations such as 'segmentation', 'unsupervised learning', 'find patterns in data', or 'k-means' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and algorithms: 'running clustering algorithms (K-means, DBSCAN, hierarchical) to identify data groups.' This names the domain (datasets), the technique (clustering), and specific algorithm variants. | 3 / 3 |
Completeness | Clearly answers both 'what' (analyze datasets by running clustering algorithms to identify data groups) and 'when' (explicit 'Use when' clause with trigger phrases like 'run clustering', 'cluster analysis', 'group data points'). | 3 / 3 |
Trigger Term Quality | Includes some good trigger terms like 'run clustering', 'cluster analysis', 'group data points', but the final sentence 'Trigger with relevant phrases based on skill purpose' is vague filler. Missing natural variations like 'segmentation', 'unsupervised learning', 'find patterns', or 'k-means'. | 2 / 3 |
Distinctiveness Conflict Risk | Clustering is a well-defined niche within data analysis. The specific algorithm names (K-means, DBSCAN, hierarchical) and trigger terms like 'cluster analysis' make it clearly distinguishable from other data analysis or machine learning skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is almost entirely generic boilerplate with no actionable content. It describes what clustering is and what the skill would theoretically do, but provides zero executable code, no concrete parameter guidance, no validation steps, and no real examples. Nearly every section could apply to any skill with minimal word changes, indicating template-driven content rather than genuine instruction.
Suggestions
Replace the abstract 'How It Works' and 'Examples' sections with concrete, executable Python code snippets showing K-means, DBSCAN, and hierarchical clustering using scikit-learn, including data loading, preprocessing, execution, and evaluation metrics.
Add a clear workflow with validation checkpoints, e.g., check data shape after loading, verify no NaN values, evaluate silhouette score after clustering, and include a feedback loop for parameter tuning.
Remove all sections that explain concepts Claude already knows (what clustering is, what preprocessing means, generic 'Instructions', 'Output', 'Error Handling', 'Resources' boilerplate) to dramatically reduce token waste.
Add specific parameter guidance with concrete defaults and decision criteria, e.g., 'Use elbow method to select k for K-means; start with eps=0.5, min_samples=5 for DBSCAN and adjust based on results.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanation of concepts Claude already knows (what clustering is, how algorithms work, what preprocessing means). Sections like 'Overview', 'How It Works', 'When to Use This Skill', 'Integration', 'Instructions', and 'Output' are padded filler that add no actionable value. The 'Best Practices' section explains basic ML concepts Claude already understands. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific examples with actual code. The examples describe what the skill 'will do' in abstract terms rather than providing copy-paste ready Python code. The 'Instructions' section is entirely generic ('Invoke this skill when the trigger conditions are met') with zero specificity. | 1 / 3 |
Workflow Clarity | The 'How It Works' section lists abstract steps (analyzing context, generating code, executing, providing results) but provides no concrete sequence, no validation checkpoints, no error recovery loops. For a multi-step data analysis workflow involving preprocessing, algorithm selection, parameter tuning, and evaluation, there are no explicit validation steps or feedback loops. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no bundle files and no references to external resources. Multiple sections contain generic boilerplate ('The skill produces structured output relevant to the task') that could be removed entirely. No structure guides the reader from quick-start to advanced usage. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.