CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator

Guide for creating effective Agent Skills. Use when users want to create a new skill (or update an existing skill) that extends an AI agent's capabilities with specialized knowledge, workflows, or tool integrations. Covers skill structure, YAML frontmatter, trigger configuration, and the 500-line rule.

72

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured creator skill: highly actionable commands, a validated multi-step workflow with a testing checklist, and clean progressive disclosure to real reference files. The only weakness is some conceptual preamble in the 'About Skills' section that assumes too little of the agent.

Suggestions

Trim the 'About Skills' / 'What Skills Provide' section to remove generic framing the agent already knows ('Skills are modular, self-contained packages...', 'Think of them as onboarding guides...'); keep only what is non-obvious about THIS skill's conventions.

The frontmatter field table and the inline frontmatter example in Step 4 overlap; consider consolidating to one canonical reference to save tokens.

DimensionReasoningScore

Conciseness

Mostly efficient with tables, code blocks, and tight checklists, but the 'About Skills / What Skills Provide' framing ('Skills are modular, self-contained packages...', 'Think of them as onboarding guides...') restates concepts an intelligent agent largely already knows and could be trimmed.

2 / 3

Actionability

Copy-paste-ready commands throughout — 'yarn agents:skill-management init <skill-name>', validate/generate-skill-rules, and concrete test invocations with full JSON echo pipes — plus complete YAML frontmatter and trigger-config examples.

3 / 3

Workflow Clarity

The 'Skill Creation Process' is a clearly sequenced Steps 1–6 with an explicit validation checkpoint (Step 5: validate + regenerate skill-rules) and a terminal 'Testing Checklist' providing the feedback loop.

3 / 3

Progressive Disclosure

SKILL.md acts as an overview pointing one level deep to four clearly signaled, real reference files (workflows.md, output-patterns.md, patterns-library.md, troubleshooting.md, all present in references/), with detail appropriately split out and templates kept in assets/.

3 / 3

Total

11

/

12

Passed

Description

100%

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, third-person description that names concrete capabilities, explicit 'Use when' triggers, and a distinctive skill-creation niche. It earns top marks on all four dimensions with no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'creating effective Agent Skills', 'create a new skill (or update an existing skill)', 'specialized knowledge, workflows, or tool integrations', plus 'skill structure, YAML frontmatter, trigger configuration, and the 500-line rule'.

3 / 3

Completeness

Explicitly answers both what ('Guide for creating effective Agent Skills... Covers skill structure, YAML frontmatter, trigger configuration, and the 500-line rule') and when ('Use when users want to create a new skill (or update an existing skill)...').

3 / 3

Trigger Term Quality

Natural phrasing a user would actually say — 'create a new skill', 'update an existing skill', 'skill' — with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Clear niche (skill authoring) with distinct triggers unlikely to fire for unrelated skills; third-person voice keeps it specific.

3 / 3

Total

12

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 2 missing

Warning

referenced_paths_exist

Referenced path issues: 10 missing

Warning

Total

12

/

16

Passed

Repository
hashintel/hash
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.