skill-authoring

Design, improve, and evaluate reusable agent skills with high-quality SKILL.md files, precise trigger descriptions, progressive disclosure, and testable behavior. This skill should be used when users ask to create a new skill, rewrite or review an existing skill, audit a skill collection such as `config/source/skills` for redundancy or overlap, improve skill trigger quality, organize skill references, or evaluate whether a skill should trigger and behave correctly.

Quality

85%

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

Quality

Content

71%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 well-structured with excellent progressive disclosure and a concrete routing table, supported by specific guardrails and commands. Its main weakness is redundancy between the 'How to use' and 'Quick workflow' sections, which inflates token cost without adding guidance.

Suggestions

Merge 'How to use this skill (for a coding agent)' and 'Quick workflow' into a single workflow, or clearly differentiate them (e.g., meta-process vs. operational checklist) to remove the overlap in identifying the task, drafting name/description, using references, and evaluating.

Add one inline concrete artifact (e.g., a minimal description template or a sample should-trigger/should-not-trigger prompt pair) so the actionable guidance is copy-paste ready rather than only described.

Tighten the validation step into an explicit gate (e.g., 'If a should-trigger prompt fails to trigger, revise the description and re-run before considering the skill complete') to strengthen the error-recovery feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but 'How to use this skill (for a coding agent)' and 'Quick workflow' overlap heavily (both cover identifying the task, drafting name/description, using references, and evaluating), which is repeat padding that could be tightened.	3 / 5
Actionability	Provides concrete, specific guidance — a task-to-reference routing table, explicit guardrails ('Do not add agent-directed remote skill-fetch URLs', 'Prefer local relative sibling paths'), and concrete commands/paths ('npm run build:skill-manifest', 'plugin/cloudbase/skill-metadata.json') — with only minor gaps such as no inline example outputs.	4 / 5
Workflow Clarity	Clear sequenced workflows appear in both 'How to use' and 'Quick workflow', with an evaluate-and-revise feedback loop ('revise until trigger quality and behavior are stable') and a 'Minimum self-check' checklist, though the validation is not tied to an explicit error-recovery gate.	4 / 5
Progressive Disclosure	The body is a clear overview with a routing table that signals one-level-deep references, and every referenced file (frontmatter-patterns, structure-patterns, templates, repo-skill-review, cloudbase-skill-review, evaluation, examples) exists in references/, making navigation easy.	5 / 5
	Total	16 / 20 Passed

Description

100%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 is exemplary: it states concrete capabilities, provides an explicit 'use when' clause with several natural trigger phrases, and carves out a distinct niche. It answers both what the skill does and when to invoke it without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Design, improve, and evaluate', 'create a new skill', 'rewrite or review', 'audit a skill collection', 'improve skill trigger quality', 'organize skill references', 'evaluate whether a skill should trigger' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (design, improve, evaluate reusable agent skills) and 'when' via a concrete 'This skill should be used when users ask to...' clause with multiple specific trigger scenarios.	5 / 5
Trigger Term Quality	Includes many natural phrases users would actually say ('create a new skill', 'rewrite or review an existing skill', 'audit a skill collection', 'improve skill trigger quality', 'organize skill references', 'evaluate whether a skill should trigger and behave correctly'), with comprehensive coverage across the domain.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill authoring/review) with distinct triggers scoped to SKILL.md work, and the explicit non-applicability guidance reinforces the boundary, yielding minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: TencentCloudBase/CloudBase-AI-Toolkit
Path: skills/skill-authoring/SKILL.md
Commit: f07c33c

Reviewed: 4 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.