mcollina/skill-optimizer
Optimizes AI skills for activation, clarity, and cross-model reliability. Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark and release gates for skills. Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.
87
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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.
This is a well-structured description that clearly defines its purpose and provides explicit usage triggers. The main weakness is that the trigger terms lean heavily toward technical jargon that skill developers might use rather than natural language a typical user would employ when seeking help with skill issues.
Suggestions
Add more natural language trigger variations like 'skill not activating', 'improve my skill', 'skill isn't being selected', or 'make skill work better' alongside the technical terms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creating or editing skill packs', 'diagnosing weak skill uptake', 'reducing regressions', 'tuning instruction salience', 'improving examples', 'shrinking context cost', 'setting benchmark/release gates'. | 3 / 3 |
Completeness | Clearly answers both what ('Optimizes AI skills for activation, clarity, and cross-model reliability') and when ('Use when creating or editing skill packs, diagnosing weak skill uptake...') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms section with domain-specific keywords like 'skill optimization', 'activation gap', 'regression', but these are technical jargon rather than natural phrases users would say. Missing common variations like 'improve my skill', 'skill not working', 'fix skill'. | 2 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on AI skill optimization with distinct technical triggers like 'activation gap', 'with/without skill delta', 'prompt salience' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is well-structured with excellent progressive disclosure and a clear workflow. The main weakness is actionability—while the process is well-defined, it lacks concrete examples of what 'explicit triggers,' 'integrated examples,' or 'decision rules' actually look like in practice. The heuristics section provides good guidance but would benefit from at least one concrete before/after example.
Suggestions
Add a concrete before/after example showing a weak skill instruction transformed into a high-salience version with explicit triggers
Include a sample benchmark scoring table or template showing what 'with-skill vs without-skill' comparison data looks like
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient, assuming Claude's competence. No unnecessary explanations of basic concepts; every section serves a clear purpose with minimal padding. | 3 / 3 |
Actionability | Provides a clear workflow and heuristics, but lacks concrete executable examples. The optimization loop describes steps abstractly rather than showing specific commands, code, or copy-paste ready templates. | 2 / 3 |
Workflow Clarity | The 5-step optimization loop is clearly sequenced with explicit validation (re-run evals, compare deltas) and a feedback pattern (edit -> re-run -> ship with guardrails). Steps are numbered and logical. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview and well-signaled one-level-deep references to five specific rule files. Navigation is clear and content is appropriately split between overview and detailed procedures. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
Reviewed
Table of Contents