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

76%

Does it follow best practices?

Impact

94%

1.74x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/anthropic-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 highly actionable with a clear sequenced workflow, but it is over the stated length budget with repeated content and casual padding, and it references bundle paths that do not exist in the actual file tree. Tightening the prose and fixing the broken references would materially raise quality.

Suggestions

Trim the padding — remove the 'Cool? Cool.' aside, the plumbers/grandparents anecdote, and consolidate the core loop to a single authoritative statement instead of restating it three times — to bring the body under the 500-line ideal.

Fix broken bundle references: create the referenced agents/grader.md, agents/comparator.md, and agents/analyzer.md files (or move that guidance into references/), and correct the eval-viewer/generate_review.py path to the actual scripts/generate_report.py location.

Add an explicit validate-then-retry checkpoint in the skill-improvement loop (e.g., re-run test cases and confirm assertions pass before declaring an iteration done) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The ~480-line body carries noticeable padding — casual asides ('Cool? Cool.'), the plumbers/grandparents anecdote, and the core loop restated three times — that could be tightened without losing substance.	3 / 5
Actionability	Provides concrete directory layouts, exact JSON shapes, copy-paste shell commands, and specific field names, with only minor gaps around unresolved placeholders and reliance on bundled-script behavior.	4 / 5
Workflow Clarity	The eval loop is a clearly sequenced five-step process with an explicit iteration loop and termination conditions, though formal validate-then-retry checkpoints for skill revision itself are only lightly specified.	4 / 5
Progressive Disclosure	Section hierarchy and one-level references to real files (schemas.md, eval_review.html, scripts/) are good, but several signaled paths (agents/*.md, eval-viewer/generate_review.py) do not exist or are misnamed in the actual bundle, breaking navigation.	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.

A strong, specific description that clearly covers both capabilities and trigger contexts with concrete phrasing. Its only weak spot is slightly less thorough coverage of casual synonyms a non-technical user might use.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — create, modify/improve, run evals, benchmark with variance analysis, optimize the description — giving comprehensive coverage with no real gaps.	5 / 5
Completeness	Explicitly states what the skill does and follows with a 'Use when...' clause enumerating concrete trigger contexts, matching the anchor-5 exemplar pattern.	5 / 5
Trigger Term Quality	Good natural-term coverage ('create a skill from scratch', 'edit', 'optimize', 'run evals', 'benchmark'), but some casual synonyms a user might say ('make/build a skill') are absent.	4 / 5
Distinctiveness Conflict Risk	The skill-creation/eval/benchmark niche is clear and distinct, with only minor theoretical overlap risk against a generic eval-runner skill.	4 / 5
	Total	18 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: boisenoise/skills-collections
Path: skills/anthropic-skill-creator/SKILL.md
Commit: 19c310e

Reviewed: about 22 hours 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.