CtrlK
BlogDocsLog inGet started
Tessl Logo

cluster-documents

Automated content similarity and grouping analysis. Groups related documents by topic, purpose, or content similarity.

52

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cluster-documents/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

The body is lean and well-structured with a clear step sequence and a defined output schema, but it lacks executable code or commands and provides no validation checkpoints for a batch operation over a repository, which caps actionability and workflow clarity.

Suggestions

Add executable guidance: name specific libraries (e.g., scikit-learn KMeans/DBSCAN, scikit-learn TfidfVectorizer or a sentence-embedding model) and a minimal runnable snippet for the core clustering step.

Add validation/verification checkpoints for this batch operation, e.g., verify embeddings were generated for all documents, check for empty clusters, and confirm the report covers every input document before finishing.

Trim the restated-purpose intro line and the Quick Reference section, since 'Purpose' and 'Techniques' duplicate content already implied by the workflow and Required Outputs.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no padding about what NLP or clustering is, but the introductory sentence ('This skill helps organize large collections, identify redundancies, and discover relationships.') and the Quick Reference section restate content already covered. These are minor over-explanation instances rather than verbosity, fitting anchor 4.

4 / 5

Actionability

It names concrete techniques (K-Means, DBSCAN, TF-IDF, embeddings) and defines the output schema, but provides no executable code, specific commands, or library names — it describes steps ('Ingest documents', 'Normalize text') rather than giving runnable guidance. This lands between anchors 2 and 3; the named techniques and structured output lift it to 3.

3 / 5

Workflow Clarity

Steps 1-4 are clearly sequenced, but this is a batch operation over a document repository with no validation or verification checkpoints. Per the rubric, missing validation in batch operations caps workflow_clarity at 3.

3 / 5

Progressive Disclosure

No bundle files exist and the body is under 50 lines, so per the simple-skill guidance progressive disclosure can score 5 when content is clear and well-organized into sections (Inputs, Workflow, Required Outputs, Quick Reference).

5 / 5

Total

15

/

20

Passed

Description

50%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.

The description clearly states what the skill does but omits any 'when to use' trigger guidance, capping completeness. Keywords are present but lack natural user phrasing and synonyms, and the scope is broad enough to risk overlap with related document skills.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g., 'Use when the user asks to cluster, group, or find similar documents, organize a document collection, or find duplicate or redundant documents.'

Add concrete actions to broaden specificity, such as 'extracts text, computes embeddings/TF-IDF, and assigns cluster labels' instead of generic 'analysis'.

Include natural synonyms and phrasings users would actually say ('cluster documents', 'find similar docs', 'deduplicate documents') to improve trigger coverage and distinctiveness.

DimensionReasoningScore

Specificity

Names the domain ('content similarity and grouping analysis') and one concrete action ('Groups related documents by topic, purpose, or content similarity') but is not comprehensive. It is not a 4 because only one distinct concrete action is given and 'analysis' is generic.

3 / 5

Completeness

Has a clear 'what' but no 'Use when...' clause or equivalent trigger guidance, so per the rubric it is capped at 3. It is not a 4 because the 'when' is entirely missing rather than weakly stated.

3 / 5

Trigger Term Quality

Includes relevant natural keywords ('documents', 'topic', 'grouping', 'content similarity') but misses common user phrases like 'cluster documents', 'find similar documents', or 'organize documents'. Anchor 3 fits since common variations and synonyms are absent.

3 / 5

Distinctiveness Conflict Risk

The skill is somewhat specific ('content similarity and grouping analysis') but 'group documents by topic, purpose, or content similarity' is broad and could overlap with other document-organization skills, and no explicit trigger phrases sharpen it.

3 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
dandye/ai-runbooks
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.