skill-creator

Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with clear sequenced workflows and well-signaled references to a real bundle, excelling on actionability and workflow clarity. It loses points on conciseness due to conversational padding and over-explanation, and minor reference gaps keep progressive disclosure at 4.

Suggestions

Trim conversational filler ('Cool? Cool.', the plumbers/grandparents anecdote, the 'billions a year in economic value' aside) to reduce padding that Claude does not need.

Reduce over-explanation of concepts Claude already knows (e.g., the general theory-of-mind rationale) and consolidate to concrete rules.

Verify the agents/ directory reference (grader.md, comparator.md, analyzer.md) matches the actual bundle structure or explicitly note it is host-provided, since those files are not present in the skill directory.

Dimension	Reasoning	Score
Conciseness	The body is thorough but includes padded conversational filler ('Cool? Cool.', plumbers/grandparents anecdote, 'we are trying to create billions a year in economic value here!') and over-explains concepts Claude already knows, so it is mostly efficient but could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready code blocks and exact commands (e.g., 'python -m scripts.aggregate_benchmark ...', 'python -m scripts.run_loop ...') with concrete JSON examples covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced (Steps 1-5 in 'Running and evaluating test cases', the iteration loop) with explicit validation/feedback checkpoints (grade assertions, re-run on feedback, kill viewer).	5 / 5
Progressive Disclosure	Good structure with one-level-deep references to real bundle files (scripts/, references/schemas.md, assets/eval_review.html, agents/*.md), but the agents/ directory is referenced while not visibly present and references are sometimes described rather than cleanly signaled.	4 / 5
	Total	17 / 20 Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, comprehensive, and explicitly pairs what-it-does with when-to-use-it using natural trigger phrases, fitting the top rubric anchors well. Minor overlap risk with adjacent skills keeps distinctiveness at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create, refine, and benchmark agent skills' plus 'building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description' — covering the skill's full range comprehensively.	5 / 5
Completeness	Explicitly states what it does ('Create, refine, and benchmark agent skills') and when to use it ('Use when building a new skill, updating an existing one, running evals...') with concrete trigger contexts.	5 / 5
Trigger Term Quality	Includes natural user phrases ('building a new skill', 'updating an existing one', 'running evals', 'checking trigger quality', 'improving a skill description') that mirror how a user would actually phrase such a request.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (agent skill authoring workflow) with distinct triggers; minor overlap risk with generic 'code' or 'eval' skills but the trigger phrases are specific enough to minimize conflict.	4 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (508 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: feiskyer/claude-code-settings
Path: skills/skill-creator/SKILL.md
Commit: 6e19e61

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.