skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
85
81%
Does it follow best practices?
Impact
88%
1.87xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 description that clearly articulates what the skill does (create, modify, evaluate, and optimize skills) and when to use it (with explicit trigger scenarios). It uses third-person voice, includes natural trigger terms, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create new skills', 'modify and improve existing skills', 'measure skill performance', 'run evals', 'benchmark skill performance with variance analysis', 'optimize a skill's description for better triggering accuracy'. | 3 / 3 |
Completeness | Clearly answers both 'what' (create, modify, improve, measure skills) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios like creating from scratch, editing, running evals, benchmarking, and optimizing descriptions. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'create a skill', 'edit', 'optimize', 'evals', 'benchmark', 'skill performance', 'triggering accuracy', 'description'. These cover a good range of terms a user working with skills would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — skill creation, editing, evaluation, and optimization — which is a meta-level task unlikely to conflict with domain-specific skills. Terms like 'skill', 'evals', 'triggering accuracy', and 'variance analysis' are highly distinctive. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with clear workflows and validation checkpoints, but it suffers significantly from verbosity. The conversational tone, repeated instructions (core loop stated 3 times), casual asides, and inline content that should be in reference files inflate the token cost substantially. The skill would benefit greatly from aggressive trimming and moving environment-specific sections to separate reference files.
Suggestions
Cut the conversational padding ('Cool? Cool.', 'Sorry in advance but I'm gonna go all caps here', 'Good luck!') and reduce the core loop from 3 repetitions to 1, saving significant tokens.
Move environment-specific sections (Claude.ai instructions, Cowork instructions) into separate reference files (e.g., references/claude-ai.md, references/cowork.md) and reference them with one-line pointers from SKILL.md.
Move the Description Optimization section (~150 lines) into a separate reference file since it's a distinct workflow that doesn't need to be in context for the core skill creation loop.
Tighten the 'Communicating with the user' and 'How to think about improvements' sections — these explain soft skills and theory of mind concepts that Claude already understands, and could be reduced to 2-3 bullet points each.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines with significant conversational padding ('Cool? Cool.'), extensive explanations of concepts Claude already knows (what JSON is, how to organize directories), repeated instructions (the core loop is stated 3+ times), and casual asides that don't add actionable value. Much of the content could be cut by 40-50% without losing information. | 1 / 3 |
Actionability | Despite the verbosity, the skill provides highly concrete, executable guidance: specific CLI commands, exact JSON schemas, file path conventions, script invocation patterns, and detailed step-by-step procedures. The code examples are copy-paste ready and the workflows are specific enough to follow without ambiguity. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases (Capture Intent → Interview → Write → Test → Evaluate → Iterate), validation checkpoints (grading, benchmark aggregation, user review via viewer), and feedback loops (read feedback → improve → rerun → review again). The 5-step evaluation sequence includes explicit validation and error recovery patterns. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (agents/grader.md, agents/comparator.md, agents/analyzer.md, references/schemas.md) with clear guidance on when to read them. However, the SKILL.md body itself is monolithic and contains substantial content that could be split into reference files — the description optimization section, Claude.ai-specific instructions, and Cowork-specific instructions could each be separate files, keeping the main body leaner. | 2 / 3 |
Total | 9 / 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
- boisenoise/skills-collections
- Commit
95574f3
- 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.