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.
Install with Tessl CLI
npx tessl i github:boisenoise/skills-collections --skill skill-creator94
Does it follow best practices?
Validation for skill structure
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 what the skill does (create, modify, measure skills) and when to use it (with explicit trigger scenarios). It uses third person voice correctly, includes natural trigger terms users would say, and occupies a distinct niche that won't conflict 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, measure skills) AND when with explicit 'Use when...' clause listing specific trigger scenarios: creating from scratch, editing, optimizing, running evals, benchmarking, and optimizing descriptions. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'create a skill', 'edit', 'optimize', 'run evals', 'test a skill', 'benchmark', 'skill performance', 'triggering accuracy'. Good coverage of variations for skill-related tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on skill management and meta-operations. Terms like 'skill', 'evals', 'triggering accuracy', and 'variance analysis' are highly specific to this 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 well-structured, highly actionable skill for creating and iterating on skills. It excels at workflow clarity with explicit multi-step processes and validation checkpoints, and provides concrete executable commands throughout. The main weakness is some verbosity and casual asides that could be trimmed without losing clarity.
Suggestions
Remove casual asides like 'Cool? Cool.' and 'Sorry in advance but I'm gonna go all caps here' to improve token efficiency
Consolidate the repeated emphasis sections at the end (the core loop is stated 3 times in different forms) into a single concise summary
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, like the casual 'Cool? Cool.' and repeated emphasis sections. Some explanations could be tightened, though it generally respects Claude's intelligence and avoids explaining basic concepts. | 2 / 3 |
Actionability | Provides highly concrete, executable guidance throughout - specific bash commands, JSON schemas, file paths, and code examples. The workflow steps are copy-paste ready with clear command syntax and expected outputs. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with explicit validation checkpoints (e.g., 'Step 1: Spawn all runs', 'Step 2: While runs are in progress, draft assertions'). Includes feedback loops for iteration and clear sequencing with numbered steps throughout. | 3 / 3 |
Progressive Disclosure | Well-organized with clear section hierarchy and explicit references to external files (agents/grader.md, references/schemas.md, etc.). Uses one-level-deep references with clear guidance on when to read them. The skill appropriately splits content between SKILL.md and bundled resources. | 3 / 3 |
Total | 11 / 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.
- 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.