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

92%

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

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, actionable skill body that practices its own progressive-disclosure and routing advice, with clear workflows and verification loops. The only notable weakness is redundancy between the 'How to use this skill' and 'Quick workflow' sections, which cover the same steps at two granularities.

Suggestions

Collapse 'How to use this skill (for a coding agent)' and 'Quick workflow' into a single workflow section (e.g., keep the concrete conditional branches from Quick workflow and fold in the explanatory sub-bullets), removing the overlapping identify/optimize/design/evaluate steps.

Consider moving the CloudBase-specific guardrail bullets (lines 26-35) into references/cloudbase-skill-review.md and leaving a one-line pointer in the body, since they are inline detail that the routing table already covers.

Dimension	Reasoning	Score
Conciseness	The body is lean and free of concept-explanation padding, but 'How to use this skill (for a coding agent)' (six steps) and 'Quick workflow' (seven steps) restate largely overlapping steps (identify task, optimize triggers, design behavior, load materials, evaluate) and could be consolidated — the 'could be tightened' level-2 anchor fits better than level 3.	2 / 3
Actionability	Guidance is concrete and executable for an instruction-only skill: a routing table maps each task to a specific reference file, and steps like 'Draft name and description before expanding the body' and 'Create should-trigger and should-not-trigger prompts, run them, review, and iterate' give copy-ready direction.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced with an explicit feedback loop ('Evaluate before considering the skill complete... revise until trigger quality and behavior are stable') and verification checkpoints ('verify the public structure and at least one real URL before writing'), plus a 'Minimum self-check' checklist.	3 / 3
Progressive Disclosure	The body is an overview that routes to seven real, one-level-deep reference files via a clearly signaled task→file table, with no nested reference chains; all referenced paths exist under references/, matching the level-3 anchor.	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 description that names concrete capabilities, provides explicit 'use when' triggers with natural user language, and carves out a clear, low-conflict niche. Voice is appropriately third person with no first/second-person slip.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions ('Design, improve, and evaluate', 'create', 'rewrite or review', 'audit', 'organize skill references', 'evaluate whether a skill should trigger'), matching the level-3 anchor rather than the level-2 single-domain example.	3 / 3
Completeness	It explicitly states both what the skill does ('Design, improve, and evaluate reusable agent skills...') and when to use it ('This skill should be used when users ask to...'), with an explicit trigger clause that the level-2 anchor lacks.	3 / 3
Trigger Term Quality	It covers natural user phrasing such as 'create a new skill', 'rewrite or review an existing skill', 'audit a skill collection', and 'improve skill trigger quality', giving broad coverage rather than the partial set at level 2.	3 / 3
Distinctiveness Conflict Risk	The skill-authoring/evaluation niche is clearly bounded by skill-specific triggers (SKILL.md, trigger quality, skill references), making overlap with unrelated skills unlikely; it is more distinct than the level-2 'Works with document files' example.	3 / 3
	Total	12 / 12 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: 3dcff8b

Reviewed: 1 day 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.