policy-check

This skill should be used when the user asks to "run policy check", "check policy", "policy-check", or needs to validate package compliance. Provides guidance on running policy checks for specific packages or the entire repository.

Quality

76%

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 ./.claude/skills/policy-check/SKILL.md

Quality

Content

83%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 exceptionally lean and gives fully executable commands for both invocation modes, but it omits any failure-handling/feedback-loop guidance for the batch repo-wide check, which caps workflow clarity. Structure is minimal but adequate for the skill's size.

Suggestions

Add a brief feedback loop: when `policy-check` reports failures, fix the offending package and re-run until it passes.

Add minimal section headers (e.g., '## Single package' and '## Repository-wide') to improve scanability.

Note how to interpret output or where failures are reported so Claude knows what a passing vs. failing run looks like.

Dimension	Reasoning	Score
Conciseness	Two lean paragraphs with no padding or explanation of concepts Claude already knows; every token earns its place, including the brief justification for repo-wide checks, matching the 'lean and efficient' anchor.	5 / 5
Actionability	Provides copy-paste-ready executable commands (`pnpm policy-check --path <relative-path>` and bare `pnpm policy-check`) covering both common cases (single package and repo-wide), matching the 'fully executable; specific examples cover the common cases' anchor.	5 / 5
Workflow Clarity	The single action is clear but the skill involves a batch/repo-wide operation with no validation/verification or failure-handling feedback loop (what to do when policy check fails), so the rubric's batch-operation cap at 3 applies and takes precedence over the simple-skill exception.	3 / 5
Progressive Disclosure	The content is self-contained, appropriately scoped, and free of nested references for a tiny under-50-line skill, but it lacks any section headers/structure, placing it just below the 'well-organized sections' 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

70%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 clearly states when to invoke the skill via concrete trigger phrases and identifies the policy-check niche, but the 'what' is somewhat generic and the capability list is not comprehensive. Trigger coverage and distinctiveness are solid.

Suggestions

Strengthen the 'what' by stating the concrete outcome (e.g., 'Runs pnpm policy-check and reports package compliance failures') instead of 'Provides guidance'.

Add a few more natural trigger synonyms such as 'compliance check' or 'lint packages' to broaden keyword coverage.

Clarify the scope boundary (e.g., monorepo/pnpm context) to further reduce overlap with generic linting skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('running policy checks', 'validate package compliance') with 1-2 concrete actions but offers no broader enumeration of capabilities, matching the '1-2 concrete actions, not comprehensive' anchor; not score 4 because it lacks several specific actions.	3 / 5
Completeness	Explicitly answers 'when' via concrete trigger phrases ('should be used when the user asks to...') and gives a 'what' ('running policy checks for specific packages or the entire repository'); the 'what' is slightly generic ('Provides guidance'), keeping it just below the fully concrete 5 anchor.	4 / 5
Trigger Term Quality	Quotes several natural trigger phrasings users would say ('run policy check', 'check policy', 'policy-check', 'validate package compliance') with good synonym coverage, but a few natural variants (e.g., 'lint', 'compliance check') are absent, so it is below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The 'policy-check' / 'package compliance' niche is mostly distinct with specific triggers, but 'validate package compliance' is broad enough to risk minor overlap with general lint/compliance skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-risk 5.	4 / 5
	Total	15 / 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: microsoft/FluidFramework
Path: .claude/skills/policy-check/SKILL.md
Commit: f02e424

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.