skill-creator

Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.

Quality

60%

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 ./codex-rs/skills/src/assets/samples/skill-creator/SKILL.md

Quality

Content

67%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 meta-skill that practices progressive disclosure with real referenced files and concrete commands; its main weakness is repetition of the same few principles across multiple sections, which hurts conciseness.

Suggestions

Consolidate the progressive-disclosure guidance into a single section to remove the repetition across Core Principles, the SKILL.md subsection, and Progressive Disclosure in Practice.

Tighten or merge the 'Match specificity to the risk' principle with the overlapping advice in 'Write the Instructions' to reduce token cost.

Optionally convert the create/update workflow into a short explicit checklist with a validate->fix->revalidate loop to push workflow clarity toward the top anchor.

Dimension	Reasoning	Score
Conciseness	The body largely avoids explaining basic concepts and gives non-obvious meta-guidance, but it restates the progressive-disclosure and specificity-to-risk principles across Core Principles, the SKILL.md subsection, Progressive Disclosure in Practice, and the resource sections, which is more than minor tightening.	3 / 5
Actionability	It provides concrete, copy-pasteable commands (scripts/init_skill.py, scripts/quick_validate.py, scripts/generate_openai_yaml.py) and real examples, but a substantial portion is abstract meta-guidance rather than executable steps, leaving minor gaps versus the fully-executable anchor.	4 / 5
Workflow Clarity	The create/update flow is clearly sequenced (Naming -> Initialize -> Write Instructions -> Validate and Iterate) with an explicit validation checkpoint via quick_validate.py, but it is presented as sectioned guidance rather than a tight stepwise checklist with explicit error-recovery loops.	4 / 5
Progressive Disclosure	The body acts as an overview with well-signaled one-level-deep references (references/openai_yaml.md, scripts/, assets/ all verified to exist) and clear section navigation, with only minor organization gaps from the cross-section redundancy.	4 / 5
	Total	15 / 20 Passed

Description

53%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 states a clear capability and niche but omits an explicit 'when to use' trigger clause and limits itself to two actions, which constrain specificity, trigger-term coverage, and completeness to the mid anchors.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g. 'Use when creating, updating, or scaffolding a Codex skill') to lift completeness and trigger-term quality.

Expand the action list with a few more specific verbs (e.g. 'scaffold, validate, and document') to move specificity toward the broader-coverage anchor.

Include common synonyms users might say ('make a skill', 'build a skill', 'add a skill') to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('Codex skill') and two concrete actions ('Create or update') plus 'supporting resources', but does not list several specific actions, so it sits at the 1-2-concrete-actions anchor rather than the broader-coverage anchor.	3 / 5
Completeness	The 'what' is clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guideline a missing explicit 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Phrases like 'Create or update a Codex skill' are reasonably natural, but coverage lacks common synonyms/variations (e.g. 'make', 'build', 'add a skill'), matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Create or update a Codex skill' is a clear, narrow niche with low conflict risk; only minor overlap with generic build/create requests, fitting the 'mostly distinct; minor overlap risk' anchor rather than the fully-distinct 5 because triggers are not spelled out.	4 / 5
	Total	13 / 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: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 16 missing	Warning

	Total	13 / 16 Passed

Repository: openai/codex
Path: codex-rs/skills/src/assets/samples/skill-creator/SKILL.md
Commit: 78245b4

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.