A lean, well-structured, procedural body that models the practices it teaches, with concrete commands and a clear validation section. The remaining gaps are minor: a couple of workflow steps lack worked examples, and validation lacks an explicit fix-and-retry loop.

Suggestions

Add one worked mini-example of the frontmatter output for step 3 (e.g., a real trigger request mapped to a written description/triggers pair) to make the abstract workflow steps concrete.

State the failure path in Validation explicitly: what to do when the pytest run or live-path check fails (fix, re-run, only proceed when green) to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive throughout ("Every skill folder must be named exactly like the skill and contain `SKILL.md`") with no explanation of concepts Claude already knows; every section earns its place. It is not 4 because there is no over-explanation that could be trimmed.	5 / 5
Actionability	Concrete artifacts are present (YAML frontmatter example, directory tree, runnable 'conda run -n a0 pytest tests/test_skills_runtime.py tests/test_tool_action_contracts.py -q'), but workflow steps like 'Identify two or three real user requests' lack a worked example or command. This matches 'mostly executable guidance; concrete code or commands with minor gaps' rather than the fully copy-paste-ready coverage of the 5 anchor.	4 / 5
Workflow Clarity	The 7-step Workflow is clearly sequenced and the Validation section provides concrete checkpoints (targeted pytest command plus a live-path checklist), but there is no explicit error-recovery loop (no 'if validation fails, fix and re-run' guidance). This matches 'clear sequence with most checkpoints present; minor validation gaps'; no destructive/batch cap applies since the operations are not destructive.	4 / 5
Progressive Disclosure	The skill is self-contained with well-organized sections and nothing that belongs in a separate file; it even teaches its own disclosure rules ('Move long examples, schemas, policies, or variant-specific detail to one-level-deep `references/` files') and practices them. It is not 4 because there are no organization gaps or misfiled content, and no bundle files exist that would need signaling.	5 / 5
	Total	18 / 20 Passed

Description

71%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 concise, action-verb-rich description with a clear niche and concrete capabilities, but it omits any explicit 'when to use' trigger guidance. Adding a 'Use when...' clause with natural trigger phrases would resolve its main weakness.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the user asks to create, rename, move, audit, test or refine an Agent Zero skill or reusable workflow.'

Include natural user phrasing synonyms such as 'skill authoring', 'SKILL.md', or 'skill template' so search and relevant-skill recall rank this skill for common variations.

Clarify the 'reusable workflows' half of the scope (what kind of workflows, in which directory) to reduce overlap risk with general workflow-related skills.

Dimension	Reasoning	Score
Specificity	The description lists six concrete lifecycle actions ("Create, rename, move, audit, test or refine") that comprehensively cover the skill-authoring domain, matching the 'multiple specific concrete actions; comprehensive coverage' anchor. It is not 4 because coverage of the domain is essentially complete rather than having minor gaps.	5 / 5
Completeness	The 'what' is clear (create/rename/move/audit/test/refine skills), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the 'when' is entirely absent, not merely imprecise.	3 / 5
Trigger Term Quality	"skills" and "reusable workflows" are natural terms a user would say, giving good keyword coverage, but there are no synonyms or variations (e.g., "SKILL.md", "skill authoring", "plugin"). This matches 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The "Agent Zero skills" niche is clearly distinct, but "reusable workflows" adds breadth with minor overlap risk against general workflow-related skills, matching 'mostly distinct; minor overlap risk'. It is not 5 because the workflow half of the scope is broad and lacks distinct trigger phrasing.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agent0ai/agent-zero
Path: skills/build-skill/SKILL.md
Commit: e3051fb

Reviewed: 10 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.