add-policy

Use when adding, modifying, or reviewing VS Code configuration policies. Covers the full policy lifecycle from registration to export to platform-specific artifacts. Run on ANY change that adds a `policy:` field to a configuration property.

Quality

86%

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

81%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 highly actionable with a well-sequenced, validated workflow and concrete code, but it repeatedly delegates to two reference files that are missing from the bundle. Supplying github-managed-settings.md and local-testing.md would resolve the broken progressive disclosure.

Suggestions

Add the missing ./github-managed-settings.md and ./local-testing.md bundle files referenced repeatedly in the body, so the delegated detail is actually reachable.

Trim the Architecture Overview and Learnings sections that restate runtime plumbing (e.g., the getPolicyData merge mechanics) in favor of prose contracts, per the skill's own Learnings guidance.

Consider collapsing the extension-policy and managed-settings sub-sections into their referenced files to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with dense reference tables and targeted code, but the Architecture Overview table and the long Learnings section restate some runtime plumbing that could be trimmed; it is efficient but not maximally lean.	4 / 5
Actionability	Provides copy-paste-ready code blocks, exact commands (`npm run export-policy-data`, `npm run typecheck-client`), and specific file paths covering the common cases of adding, exporting, and extending policies.	5 / 5
Workflow Clarity	Clear numbered Step 1–4 sequence with explicit validation checkpoints (typecheck, export-then-verify) plus a CI clean-environment feedback loop in Learnings for recovering from export failures.	5 / 5
Progressive Disclosure	References github-managed-settings.md and local-testing.md are well-signaled and one level deep, but both referenced files are absent from the bundle, so the navigation links are broken and the promised detail is unreachable.	2 / 5
	Total	16 / 20 Passed

Description

92%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 strong, specific description that clearly states both capability and trigger conditions with concrete terms. It could broaden trigger-term coverage with more everyday synonyms, but otherwise communicates its niche distinctly.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full lifecycle — "adding, modifying, or reviewing", "registration to export to platform-specific artifacts", and "Run on ANY change that adds a `policy:` field" — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both "what" (full policy lifecycle from registration to export) and "when" ("Use when adding, modifying, or reviewing" / "Run on ANY change that adds a `policy:` field") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like "adding, modifying, or reviewing", "VS Code configuration policies", and "`policy:` field" map well to user requests, but jargon ("platform-specific artifacts", "policy lifecycle") and a lack of common synonyms keep it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Scoped narrowly to VS Code configuration policies and the `policy:` field trigger, occupying a clear niche with minimal overlap with other skills.	5 / 5
	Total	19 / 20 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
relative_links	Relative link issues: 7 missing	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: .github/skills/add-policy/SKILL.md
Commit: 061594d

Reviewed: 9 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.