skill-creator

Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.

Quality

82%

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

Quality

Content

86%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.

This is a tightly written, well-structured instruction skill that follows its own style guide. It earns top marks on actionability and progressive disclosure; the only meaningful gap is minor frontmatter-template duplication and the absence of an explicit post-creation validation step.

Suggestions

Collapse the duplicate frontmatter presentation: keep the copy-paste template in Execution Steps and reduce the Inline Fallback Rules good/bad block to a one-line pointer, trimming redundant tokens.

Add an explicit post-creation validation step to Execution Steps (e.g., "Verify frontmatter is one physical line, <=250 chars, and trigger-first") to close the workflow-clarity feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative with no padding of concepts Claude already knows, but the frontmatter shape is presented twice (Execution Steps template and Inline Fallback good/bad examples), creating minor redundancy that could be trimmed; not a 5 because of that duplication.	4 / 5
Actionability	Guidance is concrete and copy-paste ready: exact file paths to check, a directory-structure template, a complete frontmatter shape with required fields, a fixed section order, a decision-gate table, and a precise output contract; for an instruction-only skill this is fully actionable.	5 / 5
Workflow Clarity	The 7-step Execution Steps form a clear ordered sequence with a pre-flight checkpoint (step 3: confirm the skill does not already exist), but there is no explicit post-creation validation or feedback loop; not a 5 because validation checkpoints beyond the pre-flight check are implicit only.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references (docs/skill-style-guide.md, then the bundled references/skill-style-guide.md which exists on disk), plus compact inline fallback rules used only when neither guide is available; content is appropriately split and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

78%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 well-formed: trigger-first, single physical line, and it cleanly answers both what and when. It is held back from the top tier mainly by limited action specificity and a slightly abstract third trigger phrase.

Suggestions

Add one or two more concrete actions (e.g., "Create, update, or audit LLM-first skills with valid frontmatter") to lift specificity toward a 5.

Replace the abstract "documenting AI usage patterns" with a more natural user phrase like "skill creation" or "make a skill" to improve trigger-term naturalness.

Dimension	Reasoning	Score
Specificity	The phrase "Create LLM-first skills with valid frontmatter" names the domain and one concrete action plus a qualifier, but offers only a single action rather than comprehensive coverage; not a 4 because no additional specific actions are listed.	3 / 5
Completeness	It explicitly answers both when ("Trigger: new skills, agent instructions, documenting AI usage patterns") and what ("Create LLM-first skills with valid frontmatter") with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	"new skills" and "agent instructions" are natural terms users would say, giving good keyword coverage; not a 5 because "documenting AI usage patterns" is more aspirational than a phrase users naturally utter and common synonyms (e.g., "skill creation", "make a skill") are missing.	4 / 5
Distinctiveness Conflict Risk	"Create LLM-first skills" carves a clear, distinct niche with low conflict risk, but "agent instructions" and "documenting AI usage patterns" are broad enough to create minor overlap with general documentation skills, keeping it just below 5.	4 / 5
	Total	16 / 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: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/skill-creator/SKILL.md
Commit: a245f26

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.