skill-creator

Create or update AgentSkills, especially when a user wants the agent to learn a reusable capability, workflow, integration, domain rule, team process, or tool usage pattern for future tasks. Use when designing, structuring, reviewing, validating, packaging, or improving skills with SKILL.md, scripts, references, and assets.

Quality

73%

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 ./openclaw/skills/skill-creator/SKILL.md

Quality

Content

63%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, actionable meta-skill with a clear workflow and validation loop, but it is longer than necessary and, critically, references bundled reference files that do not exist in the skill. Fixing the broken references and trimming conceptual padding would lift the weakest dimensions.

Suggestions

Create the missing references/workflows.md and references/output-patterns.md files (or remove the 'See references/...' links) so the body's navigation actually resolves.

Trim conceptual padding the agent already knows — e.g. the 'About Skills' intro, repeated directory trees, and the 'What to Not Include' enumeration — to bring the body well under its 500-line target.

Document the bundled quick_validate.py with an invocation example so the validation step is concrete rather than relying only on package_skill.py's built-in validation.

Dimension	Reasoning	Score
Conciseness	The 440-line body is mostly efficient but includes padding the agent already knows (what skills are, re-explaining scripts/references/assets, repeated directory trees, a 'What to Not Include' list); several sections could be tightened to respect its own token-budget guidance.	3 / 5
Actionability	Provides concrete executable commands with real flags (init_skill.py and package_skill.py invocations) and a concrete 6-step process; minor gaps such as the bundled quick_validate.py never being invoked in the body keep it just below fully copy-paste ready.	4 / 5
Workflow Clarity	A clearly numbered 6-step sequence with ordering guidance and a real validate-fix-retry loop in the packaging step; not a 5 because validation checkpoints are not explicit at every step and the iteration step is light.	4 / 5
Progressive Disclosure	Sectioning and splitting examples are decent, but the body directs readers to references/workflows.md and references/output-patterns.md (lines 350-351) while no references/ directory exists, so the signaled navigation is broken; content that should be split is partly inline.	3 / 5
	Total	14 / 20 Passed

Description

83%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, clearly written description that answers both what the skill does and when to use it with concrete trigger verbs. It is mostly distinct and specific, falling just short of the top anchors on trigger coverage and overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain ('Create or update AgentSkills') and lists several concrete actions ('designing, structuring, reviewing, validating, packaging, or improving skills') plus the capability types being learned; a few natural action phrasings are absent, so it sits just below comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' (create/update AgentSkills and which capability types) and 'when' (a concrete 'Use when designing, structuring, reviewing, validating, packaging, or improving skills...' trigger clause), matching the anchor for clearly answering both with concrete triggers.	5 / 5
Trigger Term Quality	Strong natural gerunds users would say ('designing, structuring, reviewing, validating, packaging, or improving') and an explicit 'Use when...' clause, but a few common phrasings like 'build a skill' or 'make a skill' are not surfaced.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (skill authoring/maintenance) with distinct triggers and low conflict risk, but the broad verbs 'Create or update' leave minor overlap with general code-creation skills.	4 / 5
	Total	17 / 20 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: 15 missing	Warning

	Total	14 / 16 Passed

Repository: trpc-group/trpc-agent-go
Path: openclaw/skills/skill-creator/SKILL.md
Commit: 9f7e561

Reviewed: ~16 hours 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.