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

80%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands, a well-sequenced validated workflow, and exemplary reference-based disclosure. Its main weakness is mild verbosity and duplicated openai.yaml instructions that could be consolidated.

Suggestions

Consolidate the openai.yaml generation instructions so they appear once, with the other mentions linking back, to remove repetition and tighten the body.

Trim illustrative analogies ('onboarding guides', 'narrow bridge with cliffs') that restate concepts Codex already understands.

Bundle the referenced scripts (init_skill.py, generate_openai_yaml.py, quick_validate.py) or note where to obtain them, so the copy-paste commands are actually executable from the skill folder.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Codex's competence, but carries analogy padding ('onboarding guides', 'narrow bridge with cliffs') and repeats the openai.yaml generation instructions across the 'Agents metadata' and 'Step 3' sections, so it 'could be tightened'.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands with full flags and worked examples (init_skill.py with --resources/--examples, quick_validate.py, generate_openai_yaml.py), not vague direction or pseudocode.	3 / 3
Workflow Clarity	The six-step creation process is explicitly sequenced with a validation checkpoint in Step 5 ('If validation fails, fix the reported issues and run the command again') and iteration/forward-test feedback loops in Step 6.	3 / 3
Progressive Disclosure	The lean body points to a real, well-signaled, one-level-deep reference (references/openai_yaml.md, verified present) with clear 'when to read' cues, and teaches explicit disclosure patterns; the referenced scripts/ directory is not bundled but those are executable commands rather than docs references.	3 / 3
	Total	11 / 12 Passed

Description

75%

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 clearly answers both what the skill does and when to use it, with an explicit trigger clause and a distinct niche. It is slightly held back by limited action specificity and missing natural trigger variations like 'make/build a skill'.

Suggestions

Expand the action list beyond create/update to concrete sub-actions (e.g., 'scaffold, write, validate, and iterate on skills') to lift specificity toward 3.

Add common natural trigger variations such as 'make a skill', 'build a skill', or 'add a skill' so trigger_term_quality covers what users actually say.

Consider naming the bundled tooling explicitly in the description (e.g., 'using init and validation scripts') to further sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('creating effective skills') and two concrete actions ('create a new skill', 'update an existing skill'), matching the anchor-2 example 'Processes PDF files and extracts content' rather than the three+ distinct actions required for a 3.	2 / 3
Completeness	States both what it does ('Guide for creating effective skills') and when to use it via an explicit 'This skill should be used when users want to...' clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Includes natural triggers users would say ('create a new skill', 'update an existing skill') but misses common variations such as 'make/build/add a skill', fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (skill creation) with triggers ('create a new skill', 'update an existing skill') that are specific enough to avoid conflicting with domain-task skills.	3 / 3
	Total	10 / 12 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: 0b80606

Reviewed: 3 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.