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.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-creator/SKILL.md

Quality

Content

63%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 body is a thorough, well-sequenced guide with strong concrete commands and JSON examples, but it is weighed down by chatty padding and by several referenced bundle files that are missing, which undermines navigation and executable follow-through.

Suggestions

Trim the conversational asides and redundancy — e.g. 'Cool? Cool.', the plumbers/grandparents paragraph, the 'billions a year in economic value' aside, and the repeated core-loop summary near the end — to lift conciseness without losing guidance.

Resolve the dangling references: the body points to agents/grader.md, agents/comparator.md, agents/analyzer.md, and eval-viewer/generate_review.py, none of which exist in the bundle — either add these files or correct the paths so navigation works.

Turn the grading step into an explicit validation gate (e.g. 'only proceed to the viewer or next iteration once assertions pass') to strengthen workflow_clarity's checkpoints.

Dimension	Reasoning	Score
Conciseness	The core guidance is actionable and mostly efficient, but several padded conversational asides ('Cool? Cool.', the plumbers/grandparents paragraph, 'billions a year in economic value') and a repeated end-of-file core-loop summary could be trimmed without losing meaning.	3 / 5
Actionability	Provides copy-paste-ready bash commands (e.g. `python -m scripts.aggregate_benchmark ...`, `nohup python .../generate_review.py ...`) and concrete JSON shapes (eval_metadata.json, timing.json, grading.json with exact field names), though some referenced scripts and agent files are not present in the bundle.	4 / 5
Workflow Clarity	The eval workflow is cleanly sequenced as Step 1–5 with a grading checkpoint and an explicit iterate-loop, but validation is framed as grading-plus-user-review rather than a strict pass/fail gate before proceeding.	4 / 5
Progressive Disclosure	Structure is sound (overview with one-level references to references/schemas.md, assets/eval_review.html, and scripts/), but four referenced paths — agents/grader.md, agents/comparator.md, agents/analyzer.md, and eval-viewer/generate_review.py — do not exist in the bundle, breaking the navigation the disclosure relies on.	3 / 5
	Total	14 / 20 Passed

Description

88%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 strong: it explicitly pairs concrete capabilities with a detailed 'Use when' trigger clause, covering create/edit/eval/benchmark/optimize use cases. It loses a little on trigger-term naturalness and distinctiveness due to technical jargon and potential overlap with general eval/benchmark skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create new skills, modify and improve existing skills, and measure skill performance' plus 'run evals', 'benchmark skill performance with variance analysis', and 'optimize a skill's description' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly 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, edit, or optimize...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'when' clause covers good natural phrasings ('create a skill from scratch', 'edit', 'optimize an existing skill', 'run evals', 'benchmark'), but leans on technical terms like 'variance analysis' and 'triggering accuracy' and omits casual synonyms like 'make a skill' or 'test my skill'.	4 / 5
Distinctiveness Conflict Risk	Skill creation/improvement is a clear niche, but the eval/benchmark/description-optimization triggers carry minor overlap risk with a dedicated eval-runner or benchmarking skill.	4 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: 0xRabbidfly/Eric-Cartman
Path: .claude/skills/skill-creator/SKILL.md
Commit: a052af0

Reviewed: 2 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.