skill-registry
Create or update the skill registry for the current project. Scans user skills and project conventions, writes .atl/skill-registry.md, and saves to engram if available. Trigger: When user says "update skills", "skill registry", "actualizar skills", "update registry", or after installing/removing skills.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is a strong skill description that clearly communicates what the skill does (creates/updates a skill registry by scanning skills and conventions), where it writes output (.atl/skill-registry.md), and when to use it (explicit trigger phrases and contextual situations). The description is concise, uses third person voice, and provides enough specificity to distinguish it from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create or update the skill registry', 'Scans user skills and project conventions', 'writes .atl/skill-registry.md', and 'saves to engram if available'. These are clear, actionable operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (create/update skill registry, scan skills and conventions, write to .atl/skill-registry.md, save to engram) and 'when' (explicit 'Trigger:' clause with specific phrases and situational triggers). | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would actually say: 'update skills', 'skill registry', 'actualizar skills', 'update registry', plus contextual triggers like 'after installing/removing skills'. Good coverage including a Spanish variant. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: skill registry management for a specific system (.atl/skill-registry.md). The specific file path, 'engram' reference, and domain-specific triggers make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides clear step-by-step instructions for building a skill registry. Its main strengths are the concrete directory paths, output templates, and the excellent compact rules example. Weaknesses include moderate verbosity with some repeated explanations and a monolithic structure that could benefit from splitting the registry template into a separate reference file.
Suggestions
Remove redundant explanations of compact rules' purpose — state it once in Purpose, then just provide the format and example in Step 1b.
Consider extracting the full registry markdown template (Step 3) into a separate template file referenced from the skill, reducing the main file's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and mostly necessary given the complexity of the task, but there's some redundancy — the purpose of compact rules is explained multiple times, and the full registry template could be more concise. Some explanatory text (e.g., 'This is the foundation of the Skill Resolver Protocol') adds context Claude doesn't need. | 2 / 3 |
Actionability | Highly actionable with specific directory paths to scan, exact file formats to produce, concrete markdown templates for output, specific glob patterns, deduplication rules, and even a mem_save call with exact parameters. The compact rules example (react-19) is concrete and illustrative. | 3 / 3 |
Workflow Clarity | Clear 5-step sequential workflow with explicit substeps. Each step has well-defined inputs and outputs. Step 4 is marked MANDATORY with a fallback path (file write always, engram optionally). The deduplication priority (project over user-level) and the 200-line guard provide clear decision points. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file at ~150 lines with no references to external files for detailed content. It references `_shared/skill-resolver.md` but doesn't split out the lengthy registry template or scanning logic into separate files. For a skill of this complexity, some content (like the full registry markdown template) could be externalized. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Gentleman-Programming/agent-teams-lite
- Commit
6901875
- 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.