CtrlK
BlogDocsLog inGet started
Tessl Logo

pattern-discovery-capture

Automatically capture recurring patterns discovered in the codebase during exploration. This skill logs implicit conventions, architectural patterns, and coding practices that are followed consistently but not formally documented. Use this proactively when you observe patterns that could become explicit standards.

60

Quality

70%

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 ./.claude/skills/pattern-discovery-capture/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 highly actionable thanks to a complete, documented YAML template and concrete examples, but it is hurt by significant verbosity (duplicated schema, six repetitive examples, conceptual padding) and workflow-clarity gaps from duplicate step numbering and absent post-write validation.

Suggestions

De-duplicate the YAML schema: keep one full annotated template and remove the redundant 'Discovered Patterns YAML Schema' restatement, cutting several dozen lines.

Reduce the six full YAML example blocks to two representative ones and reference a single canonical template, trimming repetition while preserving coverage.

Fix the duplicate 'Step 3' numbering (Step 3: Silent Logging and Step 3: File Management) and add a validate-after-write checkpoint (e.g. re-read the YAML to confirm it parses) to strengthen the workflow.

DimensionReasoningScore

Conciseness

The ~480-line body is noticeably verbose: the YAML schema is duplicated (full example in Step 3 and again in the 'Discovered Patterns YAML Schema' section), six near-identical YAML example blocks repeat the same structure, and sections like Benefits, Future Use, and Distinction restate concepts Claude already knows. It is below a 3 because the redundancy and padding go beyond minor over-explanation.

2 / 5

Actionability

Provides a copy-paste-ready YAML template with field-by-field documentation, a concrete output target (.claude/discovered-patterns.yaml), and six complete worked examples covering common cases.

5 / 5

Workflow Clarity

Steps are sequenced (Observe, Verify 3+, Silent Logging, File Management, User Review) with a 3+ examples validation gate, but there are two numbered 'Step 3' sections and no validate-after-write feedback loop. Not a 4 because the duplicate numbering and missing post-write validation are real clarity gaps.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent) and all content lives inline in one long SKILL.md; section headers provide some structure, but content that could be split (the six examples and the duplicated schema reference) is inlined. Not a 4 because organization gaps and duplication remain.

3 / 5

Total

13

/

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.

The description clearly states what the skill does and when to use it with concrete trigger phrasing and good natural-language keywords. It is specific and mostly distinct, with only minor overlap risk against sibling capture skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('logs implicit conventions, architectural patterns, and coding practices that are followed consistently'), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because coverage of actions is not fully comprehensive.

4 / 5

Completeness

Explicitly answers what ('Automatically capture recurring patterns... logs implicit conventions, architectural patterns, and coding practices') and when ('Use this proactively when you observe patterns that could become explicit standards') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms a user would say ('recurring patterns', 'implicit conventions', 'architectural patterns', 'patterns that could become explicit standards') giving good keyword coverage; not a 5 because it lacks synonyms and concrete extensions like file names or artifact references.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (capturing discovered codebase patterns) with distinct triggers and mostly distinct from sibling skills; not a 5 due to minor overlap risk with related capture skills like signal-capture or decision-capture.

4 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
cteyton/packmind
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.