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.

1.74x

Quality

81%

Does it follow best practices?

Impact

94%

1.74x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

62%Scale 1-3

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 primary weakness is extreme verbosity — the conversational tone, repeated instructions (the core loop appears 3+ times), meta-commentary, and inline content that should be in reference files make it far longer than necessary. The progressive disclosure structure references external files well but fails to move substantial sections out of the main body.

Suggestions

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 one-line pointers from SKILL.md

Remove the repeated core loop summaries — state it once clearly at the top and remove the two redundant restatements at the end

Cut conversational filler ('Cool? Cool.', 'Sorry in advance but I'm gonna go all caps here', 'Good luck!', 'This task is pretty important (we are trying to create billions a year in economic value here!)') — these waste tokens without adding actionable information

Tighten the 'Communicating with the user' section to 2-3 sentences — Claude doesn't need extended explanation about the trend of non-technical users discovering terminals

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~500+ lines with significant conversational padding ('Cool? Cool.'), unnecessary meta-commentary, repeated instructions (the core loop is stated 3+ times), and explanations of concepts Claude already knows (what PDF libraries are, how subagents work). The casual tone adds tokens without adding clarity.	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 tools like generate_review.py, aggregate_benchmark, and package_skill. The guidance is copy-paste ready throughout.	3 / 3
Workflow Clarity	The multi-step workflow is clearly sequenced with explicit steps (Capture Intent → Interview → Write SKILL.md → Run tests → Grade → Aggregate → Launch viewer → Read feedback → Improve → Repeat). Validation checkpoints are present (grading assertions, user review via viewer, feedback loops). Error recovery is addressed (iteration loops, re-running baselines). The 5-step evaluation sequence is particularly well-structured with explicit ordering constraints.	3 / 3
Progressive Disclosure	The skill references external files well (agents/grader.md, agents/comparator.md, agents/analyzer.md, references/schemas.md, assets/eval_review.html) with clear guidance on when to read them. However, the SKILL.md body itself is monolithic and contains enormous amounts of inline 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 skill leaner.	2 / 3
	Total	9 / 12 Passed

Description

100%Scale 1-3

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 defines a meta-skill for skill management. It provides specific concrete actions, includes natural trigger terms users would use, explicitly states both what it does and when to use it, and occupies a distinct niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: create new skills, modify/improve existing skills, measure skill performance, run evals, benchmark with variance analysis, and optimize descriptions for 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 trigger terms users would say: 'create a skill', 'edit', 'optimize', 'run evals', 'test a skill', 'benchmark', 'skill performance', 'triggering accuracy', 'skill description'. These cover a good range of how users would phrase requests.	3 / 3
Distinctiveness Conflict Risk	The meta-skill domain (skills about skills) is a clear niche. Terms like 'skill', 'evals', 'variance analysis', 'triggering accuracy' are highly specific and unlikely to conflict with other skills that handle general coding or document tasks.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: hefgi/dotfiles
Path: .agents/skills/skill-creator/SKILL.md
Commit: e6f304f

Reviewed: 1 day 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.