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

87%

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

100%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.

Exemplary minimal skill body: executable commands for both invocation scopes, an explicit pitfall warning, and a clear rule for when repo-wide checks are needed — all in two sentences with no filler. Nothing to trim and nothing missing for a skill of this scope.

Dimension	Reasoning	Score
Conciseness	Two lean sentences with zero padding: the exact command ("Run `pnpm policy-check --path <relative-path>` from the repo root"), one anti-pattern ("Do NOT `cd` into the package directory"), and one rule about repo-wide checks. Every token adds information Claude would not infer (repo-root invocation, the cd pitfall, cross-package failure propagation).	5 / 5
Actionability	Fully executable, copy-paste-ready commands covering both common cases: per-package (`pnpm policy-check --path <relative-path>`) and repository-wide (`pnpm policy-check` without `--path`). The explicit negative guidance ("Do NOT `cd`") prevents a likely execution mistake.	5 / 5
Workflow Clarity	This is a simple single-task skill and the single action is unambiguous: exact command, working directory, and scope selection. The check itself is the validation step and the operation is non-destructive, so the batch/destructive cap does not apply; the note that per-package changes can break other packages also clarifies when to escalate to a repo-wide run.	5 / 5
Progressive Disclosure	The skill is under 50 lines with a single task and no bundle files (no references/, scripts/, or assets/ exist), so nothing needs offloading. The two short paragraphs are trivially navigable and appropriately scoped for progressive disclosure.	5 / 5
	Total	20 / 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.

A solid description with explicit, natural trigger phrases and both "what" and "when" covered. The main weakness is the vague "Provides guidance on" framing, which undersells the concrete capability (running pnpm policy checks per-package or repo-wide).

Suggestions

Replace "Provides guidance on running policy checks" with the concrete capability, e.g., "Runs pnpm policy checks for a specific package or the entire repository and explains when repo-wide checks are needed".

State the concrete action/outcome explicitly (executing `pnpm policy-check` and interpreting failures) instead of the generic "provides guidance", which would lift both specificity and completeness.

Add one or two common synonym triggers such as "policy compliance" or "check packages" to broaden natural-term coverage toward anchor 5.

Dimension	Reasoning	Score
Specificity	"Provides guidance on running policy checks for specific packages or the entire repository" names the domain and 1-2 concrete actions, but "provides guidance" is generic phrasing and the concrete outcome of a check is unstated. It lists too few specific actions to match anchor 4, yet is far more concrete than the minimal/generic anchors 1-2.	3 / 5
Completeness	Both halves are present: the "what" ("running policy checks for specific packages or the entire repository") and an explicit "when" clause with concrete trigger phrases ("This skill should be used when the user asks to..."). The "what" leans on the vague "Provides guidance on" rather than stating specific capabilities, which keeps it below the fully concrete anchor 5 but clearly above anchor 3 where "when" is only weakly implied.	4 / 5
Trigger Term Quality	Quotes the natural phrases a user would actually say — "run policy check", "check policy", "policy-check" — plus "needs to validate package compliance", giving good keyword coverage. A few natural synonyms are missing (e.g., "policy compliance", "lint the repo"), so it does not reach the comprehensive coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	"policy check" / "policy-check" is a clear niche with distinct, named triggers, so it is unlikely to fire for unrelated skills. The broader phrase "needs to validate package compliance" leaves minor overlap risk with generic linting/compliance skills, preventing a 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: e41dc04

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.