skill-creator

Create new skills following the GBrain conformance standard. Generates SKILL.md with frontmatter, Contract, Phases, Output Format, and Anti-Patterns. Checks MECE against existing skills. Updates manifest and resolver.

Quality

72%

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 ./skills/skill-creator/SKILL.md

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.

The body is an exemplar of a lean, actionable instruction skill: a tight contract, a well-sequenced six-phase workflow ending in a concrete conformance-test verification step, and a complete copy-paste template, with no wasted tokens. The only meaningful improvements are showing the exact manifest.json and RESOLVER.md entry formats and adding an explicit fix-and-re-test loop for failed conformance runs.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding: no concept explanations, and every section (Contract bullets, six phases, template, output format, anti-patterns) is directly load-bearing, assuming Claude's competence. Matches anchor 5 — every token earns its place — with nothing identifiable to trim for anchor 4.	5 / 5
Actionability	Provides a complete copy-paste SKILL.md template, exact file paths ('skills/manifest.json', 'skills/RESOLVER.md'), and an exact verification command ('bun test test/skills-conformance.test.ts'). Minor gaps keep it below 5: no example manifest entry or RESOLVER routing entry, so the manifest/resolver update steps lack copy-ready formats.	4 / 5
Workflow Clarity	A clear six-step sequence (gap identification, MECE check, create, manifest, resolver, verify) with an explicit validation checkpoint in step 6. It falls short of anchor 5 because there is no explicit error-recovery loop (what to fix and re-run if the conformance test fails), but validation is present so neither the anchor-3 cap nor anchor 3 itself applies.	4 / 5
Progressive Disclosure	Self-contained, roughly 45 non-blank lines, with well-organized sections and no external references needed; the inline template is the core deliverable and appropriately belongs in SKILL.md. Under the rubric's simple-skill exception, well-organized sections alone justify a 5, and no bundle files exist to restructure.	5 / 5
	Total	18 / 20 Passed

Description

58%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 concrete and distinct, clearly stating what the skill does across several specific actions, but it omits any 'when to use' guidance and carries few natural trigger keywords within the description text itself (they sit in the separate triggers field). It reads as a solid capability summary that would benefit from an explicit use-when clause and richer trigger phrasing.

Suggestions

Append an explicit 'Use when...' clause to the description (e.g., 'Use when the user asks to create a new skill, add a skill to the library, or scaffold skill boilerplate') to lift completeness above 3.

Weave natural trigger variations into the description — 'add a skill', 'make a skill', 'scaffold a new skill' — rather than relying solely on the triggers field, improving trigger-term coverage.

Name the concrete artifacts updated ('skills/manifest.json' and 'skills/RESOLVER.md') and mention the conformance test run, tightening specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Generates SKILL.md with frontmatter, Contract, Phases, Output Format, and Anti-Patterns', 'Checks MECE against existing skills', 'Updates manifest and resolver' — with minor gaps (manifest/resolver files are not named, no mention of the conformance test). Not comprehensive enough for 5, but well beyond the 1-2 actions of anchor 3.	4 / 5
Completeness	The 'what' is clear and multi-part (create skills, generate SKILL.md, MECE check, update manifest and resolver), but there is no 'Use when...' clause or equivalent 'when' guidance in the description itself, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	The description contains the natural phrase 'Create new skills' but misses common variations a user would say ('add a skill', 'make a skill', 'skill template'); the natural trigger phrases live in the separate triggers field, not the description. Some relevant keywords exist, so above anchor 2, but coverage is incomplete.	3 / 5
Distinctiveness Conflict Risk	'Create new skills following the GBrain conformance standard. Checks MECE against existing skills' carves a distinct meta-niche with low conflict risk; only minor overlap remains (e.g., 'improve this skill' could collide with a future skill-improvement skill). Clear enough to be above anchor 3 but not the minimal-conflict clarity of anchor 5.	4 / 5
	Total	14 / 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: garrytan/gbrain
Path: skills/skill-creator/SKILL.md
Commit: e78f1c3

Reviewed: 5 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.