CtrlK
BlogDocsLog inGet started
Tessl Logo

agentskills

Agent Skills Open Standard reference (agentskills.io). Use when creating portable skills for Claude Code, Cursor, Gemini CLI, OpenAI Codex, VS Code, Roo Code, and 20+ compatible agents. Covers frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring. Load before creating cross-agent skills.

71

Quality

86%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

This is a well-structured reference skill that provides highly actionable guidance for creating portable agent skills. Its main strengths are concrete examples (frontmatter, directory structures, validation commands) and excellent progressive disclosure. The primary weaknesses are a missing explicit authoring workflow with validation checkpoints and some sections that could be more concise (the comparison table and best practices rationale explanations add moderate token overhead).

Suggestions

Add an explicit step-by-step authoring workflow (e.g., '1. Create directory → 2. Write frontmatter → 3. Write body → 4. Run skilllint → 5. Fix issues → 6. Validate with skills-ref → 7. Only commit when valid') to improve workflow clarity.

Trim the 'Authoring Best Practices' section by removing the '**Reason:**' explanations — Claude understands why conciseness and feedback loops matter; just state the principles as directives.

DimensionReasoningScore

Conciseness

Generally efficient but includes some unnecessary content: the portable vs Claude Code comparison table is lengthy, the authoring best practices section re-explains reasoning Claude already understands (e.g., 'Claude is already smart'), and the description guidelines section could be tighter. However, most sections are well-structured and avoid excessive verbosity.

2 / 3

Actionability

Provides concrete, executable examples throughout: complete frontmatter YAML blocks, directory structures, validation CLI commands, Python API usage, and specific naming rules with valid/invalid examples. The field reference table with constraints is immediately usable.

3 / 3

Workflow Clarity

The skill describes a creation workflow implicitly (write frontmatter → write body → organize files → validate) but never presents it as an explicit sequential process with checkpoints. Validation is mentioned but not integrated into a clear step-by-step authoring workflow with feedback loops, despite the skill involving multi-step file creation where validation matters.

2 / 3

Progressive Disclosure

Excellent progressive disclosure structure: the SKILL.md provides a comprehensive overview with clear one-level-deep references to `references/specification.md`, `references/best-practices.md`, and `references/integration.md`. The content teaches progressive disclosure patterns while also practicing them. Navigation is well-signaled with a dedicated 'Detailed References' section.

3 / 3

Total

10

/

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.

This is a strong description that clearly identifies its niche (the Agent Skills Open Standard), lists specific capabilities it covers, names the target platforms, and provides explicit trigger guidance with 'Use when' and 'Load before' clauses. It uses third person voice appropriately and is concise without being vague.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring. These are concrete, identifiable aspects of the standard.

3 / 3

Completeness

Clearly answers both what ('Agent Skills Open Standard reference covering frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring') and when ('Use when creating portable skills for Claude Code, Cursor, Gemini CLI... Load before creating cross-agent skills').

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'portable skills', 'Claude Code', 'Cursor', 'Gemini CLI', 'OpenAI Codex', 'VS Code', 'Roo Code', 'cross-agent skills', 'agentskills.io', 'frontmatter schema'. Good coverage of tool names and concepts a user would mention.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche — specifically about the Agent Skills Open Standard (agentskills.io) for cross-agent portable skill authoring. The mention of specific agent platforms and the standard's name make it very unlikely to conflict with other skills.

3 / 3

Total

12

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
Jamie-BitFlight/claude_skills
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.