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

68%

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 ./bundled/skills/.system/skill-creator/SKILL.md

Quality

Content

65%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 a well-structured, actionable guide with a clear sequenced workflow and real bundle references (references/openai_yaml.md, scripts/init_skill.py, scripts/quick_validate.py all present). Its main weakness is verbosity—re-explained analogies and three near-duplicate progressive-disclosure patterns inflate the token cost without adding proportional guidance.

Suggestions

Cut the 'narrow bridge / open field' analogy and the restated 'context window is a public good' framing; Codex knows this and they add tokens without guidance.

Collapse the three progressive-disclosure patterns into one pattern with a compact example table, keeping only distinct guidance (one-level-deep, TOC for >100 lines).

Promote the Step 5 validate step to an explicit 'Only proceed when validation passes' checkpoint to reach the anchor-5 feedback-loop style.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural prose, but several passages restate concepts Codex already knows (e.g. 'The context window is a public good', the analogy 'Think of Codex as exploring a path: a narrow bridge with cliffs') and the progressive-disclosure patterns re-explain the concept across three similar patterns, adding padding that could be trimmed.	3 / 5
Actionability	It provides concrete executable commands (init_skill.py usage with flags, generate_openai_yaml.py, quick_validate.py) and real examples, with only minor gaps such as the question prompts in Step 1 being illustrative rather than a copy-paste script.	4 / 5
Workflow Clarity	The six-step creation process is clearly sequenced with a numbered list, skip-conditions stated, and a validate-then-fix loop in Step 5 ('If validation fails, fix the reported issues and run the command again'); it stops short of the explicit 'only proceed when valid' checkpoint style of the anchor 5 example.	4 / 5
Progressive Disclosure	Structure is good: SKILL.md stays an overview, openai.yaml detail is split to references/openai_yaml.md and clearly signaled ('See references/openai_yaml.md'), and the file listing confirms that referenced path exists; however the three progressive-disclosure pattern sections plus extensive inlined example blocks are somewhat redundant and could be condensed rather than split.	4 / 5
	Total	15 / 20 Passed

Description

72%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 cleanly answers what and when with a distinct niche, but it leans on abstract capability language rather than concrete skill-authoring actions. Tightening it to name specific tasks (scaffold, validate, generate openai.yaml) would lift specificity and trigger coverage.

Suggestions

Add concrete actions to the 'what' clause, e.g. 'Scaffold, edit, validate, and iterate on skills that extend Codex's capabilities' to raise specificity.

Include natural synonyms a user might say—'author a skill', 'scaffold a skill', 'set up a skill'—to broaden trigger-term coverage.

Keep the explicit 'Use when...' style trigger but pair it with the concrete actions above for a fuller completeness match.

Dimension	Reasoning	Score
Specificity	The description names the domain (creating/updating skills) but the only concrete action stated is extending capabilities 'with specialized knowledge, workflows, or tool integrations'—no concrete skill-authoring actions like 'scaffold a skill folder', 'generate openai.yaml', or 'validate frontmatter' are listed.	3 / 5
Completeness	It answers both 'what' (guide for creating effective skills that extend Codex's capabilities) and 'when' ('should be used when users want to create a new skill (or update an existing skill)'), satisfying the explicit-trigger requirement; the 'when' clause is clear but slightly generic.	4 / 5
Trigger Term Quality	Natural phrasing is present ('when users want to create a new skill (or update an existing skill)') with the core keyword 'skill' repeated, but synonyms like 'author a skill', 'scaffold a skill', or file-extension hints are missing.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear, narrow niche—skill authoring—that is unlikely to overlap with domain skills, and the trigger ('create a new skill or update an existing skill') is distinct.	5 / 5
	Total	16 / 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: 12 missing	Warning

	Total	13 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/.system/skill-creator/SKILL.md
Commit: d5ae560

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.