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 Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Quality

78%

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 ./desktop/electron/builtin-skills/skill-creator/SKILL.md

Quality

Content

73%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.

A well-structured, highly actionable meta-skill with a clear six-step workflow, explicit validation, and feedback loops. The main weaknesses are verbosity from repeated forward-testing/progressive-disclosure coverage and bundle integrity gaps where referenced scripts are absent from the skill folder.

Suggestions

Consolidate the forward-testing / subagent-validation guidance, which currently appears in 'Protect Validation Integrity', Step 4, and the 'Forward-testing' section, into a single authoritative section to remove redundancy and trim length.

Bundle the referenced scripts (init_skill.py, generate_openai_yaml.py, quick_validate.py) in a scripts/ directory, or reword the body to describe their behavior without implying they are shipped, so the executable commands are actually runnable.

Move the detailed progressive-disclosure pattern examples (the multi-block PDF/BigQuery/cloud-deploy snippets) into a reference file and summarize the patterns in SKILL.md to bring the body comfortably under its 500-line target.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and the content is genuinely procedural, but it is ~410 lines (near its own 500-line ceiling) and repeats themes: forward-testing/subagent validation appears in 'Protect Validation Integrity', Step 4, and the 'Forward-testing' section, and progressive disclosure is explained in both 'Anatomy of a Skill' and its own design-principle section.	3 / 5
Actionability	Provides concrete, copy-paste-ready commands (init_skill.py with flags and examples, generate_openai_yaml.py, quick_validate.py) and concrete examples for naming and description writing, but several referenced scripts are not present in the bundle, so the guidance is not fully executable as shipped.	4 / 5
Workflow Clarity	A clearly sequenced six-step process (Understand, Plan, Initialize, Edit, Validate, Iterate) with an explicit validation checkpoint in Step 5 and feedback loops in Step 6 and the Forward-testing section ('If validation fails, fix the reported issues and run the command again').	5 / 5
Progressive Disclosure	Good structure with one-level-deep, clearly signaled references (references/openai_yaml.md is referenced multiple times with 'See ... for field definitions and examples'), but the body inlines a lot of pattern/anatomy content and references scripts (init_skill.py, generate_openai_yaml.py, quick_validate.py) that are not bundled.	4 / 5
	Total	16 / 20 Passed

Description

82%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, third-person description that clearly answers both what the skill does and when to use it, with an explicit trigger clause and minimal conflict risk. Its only real weakness is that the 'what' stays at the action level (create/update) without naming the constituent authoring activities, leaving specificity slightly below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('creating effective skills') and two concrete actions ('create a new skill', 'update an existing skill'), but does not enumerate the sub-activities (naming, writing frontmatter, bundling resources, validating) that the body actually covers, so coverage is not comprehensive.	3 / 5
Completeness	Explicitly states what the skill does ('Guide for creating effective skills') and gives a concrete 'when' clause ('This skill should be used when users want to create a new skill (or update an existing skill)...'), satisfying both what and when with explicit trigger phrasing.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('create a new skill', 'update an existing skill') with good coverage, but misses common synonyms such as 'build' or 'make a skill'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear meta-skill niche (authoring skills themselves) with distinct triggers that are unlikely to collide with domain skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 20 missing	Warning

	Total	13 / 16 Passed

Repository: Jamailar/Beav
Path: desktop/electron/builtin-skills/skill-creator/SKILL.md
Commit: e8cbd6a

Reviewed: 4 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.