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

88%

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

77%

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 concrete code, commands, and a validated 4-step workflow, but it carries some redundancy and keeps secondary topics (extension policies, preview features) inline rather than in referenced files. Strong on actionability and workflow clarity, slightly weaker on conciseness and progressive disclosure.

Suggestions

De-duplicate the `minimumVersion` guidance (stated in Step 1, the value example, and the preview-features pattern) into one authoritative spot.

Move the 'Policy for extension-provided settings' and 'GitHub Preview Features' sections into referenced reference files to slim the main SKILL.md body and improve progressive disclosure.

Consolidate the repeated `npm run export-policy-data` explanations into a single step referenced from the other sections.

Dimension	Reasoning	Score
Conciseness	Mostly lean and domain-specific with real paths and exact commands, but repeats the `minimumVersion` instruction and re-explains the export flow across the extension-policy and GitHub-preview sections, so it could be tightened.	2 / 3
Actionability	Provides fully executable code blocks (complete `policy:` objects with inline field comments), exact shell commands, exact enum values, file paths, and a quoted error message — copy-paste ready.	3 / 3
Workflow Clarity	A clearly sequenced 4-step procedure with an explicit TypeScript validation checkpoint (Step 3) and output verification (Step 4), plus error-recovery guidance in Learnings.	3 / 3
Progressive Disclosure	Well-organized into clear sections with one-level source-file references, but the extension-policy and GitHub-preview subsections are inline content that could be split into reference files; no bundle files exist.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 third person, concise, and clearly states both capabilities and explicit 'Use when'/'Run on ANY change' triggers tied to a distinctive `policy:` field marker. It hits the top anchor on all four dimensions without fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'adding, modifying, or reviewing VS Code configuration policies', 'registration to export to platform-specific artifacts', and 'adds a policy: field' — exceeding the domain-and-some-actions bar.	3 / 3
Completeness	Explicitly answers what ('Covers the full policy lifecycle from registration to export to platform-specific artifacts') and when ('Use when...', 'Run on ANY change that adds a policy: field') with explicit triggers.	3 / 3
Trigger Term Quality	Includes natural trigger phrasing a developer would say ('Use when adding, modifying, or reviewing...') plus the literal `policy:` field marker and 'configuration property', giving good coverage.	3 / 3
Distinctiveness Conflict Risk	A clear niche tied to the highly specific `policy:` configuration field marker, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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: posit-dev/positron
Path: .github/skills/add-policy/SKILL.md
Commit: b87c504

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.