moai-workflow-docs-claim-check

Read-only check of whether the claims a public-facing document makes (README, release notes, install and usage guides) are supported by user-supplied evidence. Runs Preflight, Claim Triage, and Validation, splits composite claims into atomic ones, and labels each. Runs no commands and writes no fixes.

Quality

83%

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

92%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, highly actionable read-only workflow with clear sequencing, validation checkpoints, and clean one-level-deep progressive disclosure; the only weakness is moderate restatement of the hard boundaries across several scaffolding sections.

Suggestions

Consolidate the boundary restatements: the no-execution/no-fix rules appear in Hard Boundaries, Common Rationalizations, Red Flags, and Verification — consider trimming Red Flags or Rationalizations to reduce token cost.

The Common Rationalizations table partially duplicates Hard Boundaries and the label semantics; tighten or cross-reference instead of re-explaining.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, assuming Claude's competence without explaining what a README or claim is; however the no-execution/no-fix boundaries are restated across Hard Boundaries, Common Rationalizations, Red Flags, and Verification, which could be trimmed.	4 / 5
Actionability	Gives fully concrete, executable guidance for an instruction-only skill: exact four-value label set, gate-condition table, exact output table columns, and 'Emit exactly these three sections, in this order, every time' — Claude knows precisely what to produce.	5 / 5
Workflow Clarity	Three phases are clearly sequenced with explicit checkpoints ('Complete all three steps before triaging a single claim'), an ordered decision tree ('Stop at the first gate that fires'), and a final Verification checklist; the skill is read-only/non-destructive so the batch/destructive cap does not apply.	5 / 5
Progressive Disclosure	Overview stays in SKILL.md while full gate criteria and worked examples are pushed one level deep to real, clearly signaled files (references/label-decision-tree.md, references/worked-examples.md), both listed in a Bundled references table — easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

75%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 specific and distinctive with a clear niche, but the description field itself omits an explicit 'when to use' trigger clause, capping completeness at 3 even though a separate when_to_use frontmatter field supplies that guidance.

Suggestions

Append a 'Use when...' clause to the description field (e.g. 'Use when auditing a README or release note before publishing, or when checking whether doc claims are backed by evidence') so the description self-contains its trigger guidance.

Add a few natural synonyms users might say — 'documentation', 'docs', 'quickstart', 'migration note' — to broaden trigger-term coverage.

Consider naming file types or formats users mention (e.g. 'published site pages') to further reduce overlap with generic documentation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'check of whether the claims...are supported', 'Runs Preflight, Claim Triage, and Validation', 'splits composite claims into atomic ones, and labels each', 'Runs no commands and writes no fixes' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The description field clearly answers 'what' but contains no 'Use when...' trigger clause; per the rubric, a missing explicit trigger guidance caps completeness at 3 even though a separate when_to_use field exists.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('README, release notes, install and usage guides', 'claims', 'evidence') but lacks a few common synonyms/variations such as 'docs', 'quickstart', or 'documentation audit'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — read-only evidence-backed claim checking of public-facing docs — with distinct triggers (README, release notes, install/usage guides) and minimal overlap risk with doc-editing or code-review skills.	5 / 5
	Total	17 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/moai-workflow-docs-claim-check/SKILL.md
Commit: 4100d87

Reviewed: 2 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.