CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agent-skill-creator

Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-skill-creator/SKILL.md

The canonical home for this skill is skill-creator in openclaw/openclaw

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, well-sequenced instruction set with per-step completion criteria and a concrete validation step — an exemplar of lean skill writing. Its only real weaknesses are the missing error-recovery loop after validation and a script pointer that does not resolve against the bundle as provided.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout: every line instructs ("Map shared ordered procedure to SKILL.md", "Run python {baseDir}/scripts/quick_validate.py <skill-directory>"), with no explanations of concepts Claude already knows and no padding.

5 / 5

Actionability

Mostly executable guidance: a runnable validation command, concrete frontmatter field names, and a specific tool ("use skill_workshop to create or revise a pending proposal"). Minor gaps remain — how to invoke skill_workshop and what a helper's "focused test" looks like are not shown.

4 / 5

Workflow Clarity

A clear five-step sequence where every step ends in a checkable completion criterion and step 5 is an explicit validation step with a runnable command and pass conditions ("frontmatter passes, resource pointers resolve, and every touched helper passes its focused test"). It falls short of a 5 only because no explicit error-recovery feedback loop (fix and re-validate on failure) is written out.

4 / 5

Progressive Disclosure

The body is short (~35 lines) and well organized into Workflow and Frontmatter sections with content appropriately placed inline. The gap: the only concrete bundle pointer, {baseDir}/scripts/quick_validate.py, has no corresponding file in the bundle (no scripts/ directory exists), so the reference cannot be verified as resolving.

4 / 5

Total

17

/

20

Passed

Description

58%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, specific set of capabilities in a lean third-person form, but it omits any explicit "when to use this" trigger guidance, which both weakens completeness and limits natural trigger-term coverage. Adding a "Use when..." clause naming how users typically request skill creation or repair would lift the two weakest dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when creating a new skill, fixing or validating an existing SKILL.md, or reorganizing a skill's bundled resources."

Include natural user phrasings as trigger terms such as "write a skill", "make a skill", "skill creation", and "skill validation" alongside the technical terms.

Consider naming the deliverables users ask for by name (e.g. frontmatter, references/scripts/assets layout) to further sharpen distinctiveness against generic review skills.

DimensionReasoningScore

Specificity

Lists several specific actions ("create, repair, validate, or restructure SKILL.md files and bundled resources") covering the domain's main operations, though the actions are verb-level rather than fully elaborated, leaving minor coverage gaps.

4 / 5

Completeness

The "what" is clear and concrete (author or review AgentSkills across create/repair/validate/restructure), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Includes relevant keywords ("AgentSkills", "SKILL.md", "bundled resources") but misses common natural variations a user would say, such as "write a skill", "make a skill", or "fix a skill", so coverage is only partial.

3 / 5

Distinctiveness Conflict Risk

The niche (authoring/reviewing AgentSkills and SKILL.md files) is distinct with targeted triggers, with only minor overlap risk against generic code-review or documentation skills.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

administrakt0r/AGENTARDS

Path

.agents/skills/agent-skill-creator/SKILL.md

Reviewed

Table of Contents

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.