skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update 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.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 skill description that clearly articulates both capabilities and trigger conditions. It uses third person voice correctly, lists specific concrete actions, and includes natural keywords users would employ when working with skills. The explicit 'Use when...' clause with multiple trigger scenarios makes it highly effective for skill selection.
| 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'. | 3 / 3 |
Completeness | Clearly answers both what ('Create new skills, modify and improve existing skills, and measure skill performance') AND when ('Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance...'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'create a skill', 'update', 'optimize', 'run evals', 'test a skill', 'benchmark', 'variance analysis', 'triggering accuracy'. Good coverage of terms a user working with skills would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on skill management, creation, and evaluation. The terms 'skill', 'evals', 'triggering accuracy', and 'variance analysis' are highly specific to this meta-skill domain and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 is a comprehensive, well-structured skill for creating and iterating on skills. Its greatest strengths are actionability (concrete commands, schemas, and step-by-step processes) and workflow clarity (explicit phases, validation checkpoints, and decision points). The main weakness is verbosity—some sections could be tightened, and the core loop is repeated multiple times unnecessarily.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but verbose in places, with some redundant explanations (e.g., repeating the core loop multiple times, explaining AskUserQuestion structure in detail). However, it mostly avoids explaining concepts Claude already knows and focuses on workflow-specific guidance. | 2 / 3 |
Actionability | Provides highly concrete, executable guidance throughout: specific bash commands, JSON schemas, exact file paths, code examples for running scripts, and detailed step-by-step processes. Commands are copy-paste ready with actual script names and parameters. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing, explicit validation checkpoints (security scan before packaging, grading before viewer launch), and feedback loops (iterate until satisfied). The numbered steps with explicit 'Step N' labels and decision points via AskUserQuestion provide clear navigation through complex processes. | 3 / 3 |
Progressive Disclosure | Well-organized with clear hierarchy: main SKILL.md provides overview and workflow, with explicit one-level-deep references to agents/ and references/ directories for specialized content. Navigation is clearly signaled (e.g., 'Read agents/grader.md', 'See references/schemas.md for the full schema'). | 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (1054 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- daymade/claude-code-skills
- Commit
392d34c
- 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.