skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's capabilities with specialized knowledge, workflows, or tool integrations.

1.29x

Quality

83%

Does it follow best practices?

Impact

100%

1.29x

Average score across 6 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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 strong, actionable meta-skill with a clear sequenced workflow and validation feedback loop. Its main gaps are some metaphorical padding that hurts conciseness and two body references to files that are absent from the bundle.

Suggestions

Tighten the 'Degrees of Freedom' section by removing the bridge/field metaphor and keeping only the high/medium/low-freedom definitions.

Either add the missing references/workflows.md and references/output-patterns.md files, or remove the broken pointers on the 'Learn Proven Design Patterns' lines so all referenced paths resolve.

Trim introductory 'About Skills' prose that restates what a competent model already knows about skills to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The 382-line body is mostly efficient procedural guidance, but includes unnecessary metaphor ('a narrow bridge with cliffs needs specific guardrails') and explanatory prose a competent model already knows, so it could be tightened to earn the top score.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands (node init_skill.cjs, node package_skill.cjs, gemini skills install), explicit naming rules, and a numbered creation process, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 7-step creation process is clearly sequenced with ordering guidance, and packaging includes an explicit validate -> fix -> re-run feedback loop ('If validation fails... Fix any validation errors and run the packaging command again').	3 / 3
Progressive Disclosure	The body is well-organized and models progressive-disclosure patterns, but it points to references/workflows.md and references/output-patterns.md that do not exist in the bundle, so the actual referenced paths are missing and not reliably signaled.	2 / 3
	Total	10 / 12 Passed

Description

90%

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-constructed: it states the purpose, gives explicit use-triggers in natural language, and stays in third person. Its only weakness is moderate specificity — it names the domain and two actions rather than enumerating a fuller set of concrete capabilities.

Dimension	Reasoning	Score
Specificity	The description names the domain ('creating effective skills') and a couple of concrete actions ('create a new skill', 'update an existing skill'), but does not enumerate a comprehensive list of specific actions like the top anchor requires.	2 / 3
Completeness	It states what the skill does ('Guide for creating effective skills') and an explicit when-trigger ('This skill should be used when users want to create a new skill (or update an existing skill)'), answering both what and when.	3 / 3
Trigger Term Quality	It uses natural phrases a user would actually say ('create a new skill', 'update an existing skill') and covers relevant capability terms (knowledge, workflows, tool integrations), matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Skill creation is a clear, distinct niche with specific triggers unlikely to collide with other skills, and it uses third-person voice with no overlap risk.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 17 missing	Warning

	Total	14 / 16 Passed

Repository: google-gemini/gemini-cli
Commit: 172ff92

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.