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.

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 ./plugins/plugin-creator/skills/agentskills/SKILL.md

Quality

Content

72%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 reference skill that practices progressive disclosure effectively, offloading detail to real one-level-deep reference files while keeping the body actionable with concrete validation commands and templates. Its main weakness is workflow clarity, where an explicit checkpointed authoring workflow is absent.

Suggestions

Add a short numbered authoring workflow (e.g., draft frontmatter -> write lean body -> push detail to references/ -> run `uvx skilllint@latest check` -> run `skills-ref validate`) with explicit validation checkpoints to lift workflow_clarity above 3.

Trim context Claude already has, such as "Originally developed by Anthropic, adopted by 25+ agent products," and consolidate the per-principle Reason: notes to tighten conciseness toward a 5.

Make the authoring guidance more concrete by pairing each best-practice principle with one copy-paste example, reducing the principle-only abstraction in the Actionability dimension.

Dimension	Reasoning	Score
Conciseness	The body is a lean overview that pushes detail to reference files and mostly assumes Claude's competence, with only minor padding ("Originally developed by Anthropic, adopted by 25+ agent products" and some Reason: rationale prose); not a 5 because a few sentences could be trimmed.	4 / 5
Actionability	It provides concrete executable commands ("skills-ref validate ./my-skill", "uvx skilllint@latest check <skill-path>") and copy-paste Python API plus frontmatter templates, but the authoring guidance is principle-based rather than fully step-by-step, leaving minor gaps.	4 / 5
Workflow Clarity	Content is logically organized by topic and validation tools are provided (skilllint, skills-ref validate form a feedback loop), but there is no explicit checkpointed authoring sequence, so checkpoints remain implicit; not a 4 because the workflow is not clearly sequenced with explicit validation steps.	3 / 5
Progressive Disclosure	The body is a clear overview with well-signaled one-level-deep references to existing files ("references/specification.md", "references/best-practices.md", "references/integration.md"), with content appropriately split and easy to navigate; all referenced bundle files are present.	5 / 5
	Total	16 / 20 Passed

Description

87%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, third-person description that clearly states both what the skill covers and when to use it, with a distinct portable-skills niche and rich natural trigger terms. It is held just below perfect on specificity and trigger-term coverage by enumerating topics rather than concrete operations and omitting a few natural synonyms.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete coverage areas ("frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring") but presents them as topics rather than concrete operations, leaving minor gaps; not a 5 because it stops short of comprehensive concrete actions.	4 / 5
Completeness	It explicitly answers both what ("Covers frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring") and when ("Use when creating portable skills...", "Load before creating cross-agent skills") with concrete trigger phrases, in third person.	5 / 5
Trigger Term Quality	Strong natural triggers are present ("Claude Code, Cursor, Gemini CLI, OpenAI Codex, VS Code, Roo Code", "portable skills", "cross-agent skills"), but a few natural terms users might say ("skill format", "SKILL.md") are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche ("Agent Skills Open Standard reference", "portable skills", "cross-agent skills") and even self-disambiguates from Claude Code-specific skills, giving it distinct triggers with minimal conflict risk.	5 / 5
	Total	18 / 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: 3 missing	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: Jamie-BitFlight/claude_skills
Path: plugins/plugin-creator/skills/agentskills/SKILL.md
Commit: c337daf

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.