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
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 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 would naturally use when wanting to work with skills. | 3 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — skill management, creation, evaluation, and optimization — which is unlikely to conflict with other 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 comprehensive, highly actionable skill with excellent workflow clarity and concrete executable guidance throughout. Its main weakness is extreme verbosity — conversational asides, repeated summaries of the core loop, explanations of obvious concepts, and inline content that should be in reference files significantly inflate the token count. The skill would benefit greatly from aggressive trimming and better use of its own progressive disclosure pattern.
Suggestions
Cut the conversational padding ('Cool? Cool.', 'Good luck!', 'This task is pretty important...'), the repeated core loop summaries (stated 3 times), and the communication style section — these add ~100+ lines of low-value tokens.
Move the Claude.ai-specific instructions, Cowork-specific instructions, and Description Optimization sections into separate reference files (e.g., references/claude-ai.md, references/cowork.md, references/description-optimization.md) with clear pointers from SKILL.md.
Remove explanations of concepts Claude already knows (e.g., what JSON fields are, why malware is bad, what a PDF is) and trust Claude's competence — this alone could cut 20-30% of content.
Consolidate the three restatements of the core loop into a single concise summary at the top, removing the redundant versions at the bottom.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines with significant conversational padding ('Cool? Cool.'), explanations of concepts Claude knows (what a PDF is, what JSON is), meta-commentary about communication style, and repeated emphasis blocks. The casual tone adds tokens without adding value. The core loop is stated three times. | 1 / 3 |
Actionability | Despite verbosity, the skill provides highly concrete, executable guidance: specific CLI commands, exact JSON schemas, file path conventions, step-by-step sequences with actual code blocks, and precise instructions for spawning subagents, grading, and launching the viewer. Commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit validation checkpoints: capture intent → interview → write skill → run tests (with parallel baseline) → grade → aggregate → launch viewer → read feedback → iterate. Each step has clear inputs/outputs, and the feedback loop (improve → rerun → review → repeat) is well-defined with explicit stopping criteria. | 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 to keep 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
- anthropics/claude-plugins-official
- Commit
0d82eac
- 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.