pattern-detection
Auto-detects reusable patterns, best practices, and automation opportunities during implementation. Recognizes repetitive structures and generalizable solutions that could become skills.
49
33%
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/claude-code-dev/skills/pattern-detection/SKILL.mdQuality
Discovery
17%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 description explains the skill's purpose at a conceptual level but fails to provide actionable trigger guidance or natural user-facing keywords. It reads more like an internal capability description than a selection guide for Claude. The lack of explicit 'Use when...' triggers and absence of natural language terms users would actually say significantly limits its utility for skill selection.
Suggestions
Add an explicit 'Use when...' clause with concrete triggers, e.g., 'Use when implementing similar functionality multiple times, when code could be templated, or when the user mentions creating reusable components.'
Include natural trigger terms users would say: 'template', 'reuse', 'save this pattern', 'create a skill', 'make this repeatable', 'DRY'.
Specify concrete outputs or actions: 'Creates new skill files', 'Suggests skill templates', 'Documents patterns in SKILL.md format'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (pattern detection, automation) and some actions ('auto-detects', 'recognizes'), but the actions remain somewhat abstract. 'Reusable patterns', 'best practices', and 'automation opportunities' are conceptual rather than concrete operations like 'creates skill files' or 'generates templates'. | 2 / 3 |
Completeness | Describes what it does (detects patterns and opportunities) but completely lacks a 'Use when...' clause or any explicit trigger guidance. There's no indication of when Claude should select this skill over others. | 1 / 3 |
Trigger Term Quality | Uses technical/abstract terms like 'reusable patterns', 'generalizable solutions', and 'automation opportunities' that users would rarely say naturally. Missing natural trigger terms users might actually use like 'create a skill', 'save this for later', 'make this reusable', or 'template'. | 1 / 3 |
Distinctiveness Conflict Risk | The focus on 'skills' and 'automation opportunities' provides some distinctiveness, but 'best practices' and 'reusable patterns' are generic enough to potentially overlap with code review, refactoring, or documentation skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for pattern recognition with good categorization and quality criteria, but suffers from verbosity and passive guidance. The examples are helpful but extensive, and the actual workflow for Claude is unclear - it's more descriptive than instructive about what actions to take when patterns are recognized.
Suggestions
Remove explanatory content about what patterns are (Claude knows this) and focus on the specific recognition triggers and quality criteria
Add concrete actions Claude should take when recognizing a pattern - e.g., specific phrases to use, how to structure notes, or explicit markers to include in responses
Move the extensive good/bad pattern examples to a separate EXAMPLES.md file and keep only 1-2 inline
Clarify the integration with feedback hooks - what specifically does Claude output that gets captured? What format should pattern notes take?
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places, explaining concepts like what factory patterns are and providing extensive examples of both good and bad patterns. Some sections like 'Purpose' explain things Claude would understand implicitly. | 2 / 3 |
Actionability | The skill provides concrete code examples and clear criteria tables, but the actual guidance is somewhat abstract - it tells Claude to 'note mentally' and 'continue implementing' without specific actions. The integration with feedback hooks is vague about what Claude should actually do. | 2 / 3 |
Workflow Clarity | The 'Integration with Feedback Hooks' section provides a sequence but it's passive ('note mentally', 'be descriptive'). There are no validation checkpoints or clear decision points for when to capture vs ignore a pattern. The recognition triggers are listed but not sequenced into a workflow. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and tables, but it's monolithic - all content is inline rather than referencing external files for detailed examples or pattern libraries. The extensive good/bad examples could be in a separate reference file. | 2 / 3 |
Total | 8 / 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 | |
- Repository
- jpoutrin/product-forge
- Commit
0ebe7ae
- 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.