create-skill

Use when creating a new skill, writing a skill from scratch, or converting a process into a reusable skill — enforces TDD, empirical validation, and quality monitoring

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

77%Weight 40%Scale 1-3

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, well-validated workflow, but it is monolithic and somewhat verbose for a single SKILL.md. Splitting the rationalizations table and feeder script into reference files, and tightening prose in the determinism and validation steps, would lift both conciseness and progressive disclosure.

Suggestions

Move the 'Rationalizations & Red Flags' table and the Step 12 devflow feeder bash block into separate reference files (e.g. references/rationalizations.md, scripts/feed-score.sh) referenced one level deep from the body, to improve progressive disclosure and cut inline tokens.

Tighten the prose in steps 9.5 and 10 — the abstain-contract rationale and the 'real case 2026-07-14' anecdote can be condensed to the essential rule without the surrounding justification.

Consolidate the Quality Gates table and the Mermaid flowchart so each gate is stated once rather than repeated across both the diagram, the step text, and the table.

Dimension	Reasoning	Score
Conciseness	The body is instructive and mostly efficient but leans verbose: extended prose in steps 9.5/10/12, an embedded anecdote ('real case 2026-07-14'), and a long rationalizations table with inline parentheticals add tokens beyond what Claude strictly needs. It is closer to 'could be tightened' than fully lean.	2 / 3
Actionability	It provides fully executable, specific commands and snippets — 'tessl review run --threshold 85', the ruby YAML-check one-liner, the bash feeder block — with named tools and concrete paths, matching the copy-paste-ready level-3 anchor.	3 / 3
Workflow Clarity	A clear 12-step sequence anchored by a Mermaid flowchart and a Quality Gates checklist, with explicit validation and retry feedback loops (REFACTOR→re-run, optimize-skill→re-run, validate-frontmatter→fix-before-scoring) for the eval gate.	3 / 3
Progressive Disclosure	No bundle files exist, so all content is inline in a single ~220-line document; the rationalizations table and feeder script are content that could live in separate references but is not split out, fitting 'content that should be separate is inline' rather than well-signaled one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%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.

The description is strong: third-person, specific, with an explicit 'Use when' trigger and a distinct niche. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating a new skill, writing a skill from scratch, or converting a process into a reusable skill' — plus 'enforces TDD, empirical validation, and quality monitoring', matching the level-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	It has an explicit 'Use when...' trigger and clearly states what the skill does (create/write/convert skills, enforce TDD, empirical validation, quality monitoring), answering both what and when as the level-3 anchor requires.	3 / 3
Trigger Term Quality	The 'Use when creating a new skill, writing a skill from scratch, or converting a process into a reusable skill' phrasing maps to natural ways a user would phrase the request, giving good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (skill authoring with a defined methodology) with distinct triggers and third-person voice, making it unlikely to fire for unrelated skills.	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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AndreJorgeLopes/proof-of-skill
Path: skills/create-skill/SKILL.md
Commit: c92f3dc

Reviewed: 24 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.