CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

winmd-api-search

Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable, well-structured skill with copy-paste commands, a clearly sequenced discover workflow with a score-threshold fallback, and real bundled scripts. Minor room remains in trimming redundant sections and moving low-frequency detail (scoring internals, command catalog) into a reference file.

DimensionReasoningScore

Conciseness

Largely efficient tables and copy-paste commands, but the "When to Use This Skill" section restates the frontmatter description and the internal "Search Scoring" table is tool detail Claude rarely needs to act — minor trimmable material, matching the level 4 anchor rather than the every-token-earns-its-place level 5.

4 / 5

Actionability

Fully executable PowerShell for every action (search, members, enums, types, namespaces, projects, packages, stats), concrete cache-setup commands, exact web-search fallback query strings, and a troubleshooting table with fixes — copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

The Discover path is a numbered 0–5 sequence with an explicit validation checkpoint ("low scores (below 60) or are irrelevant" → fall back to web search then return for local signatures), a required cache-setup gate before first use, and an error-recovery troubleshooting table — clear sequence with feedback loops matching the level 5 anchor.

5 / 5

Progressive Disclosure

Well-organized sections with real bundle script files correctly referenced (verified scripts/Invoke-WinMdQuery.ps1 and scripts/Update-WinMdCache.ps1 exist), but all detail lives inline in a single ~190-line file (Search Scoring internals, full command catalog) rather than split into reference files, so it fits 'good structure; minor organization gaps' rather than the appropriately-split level 5.

4 / 5

Total

18

/

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 description: concrete capability list, explicit 'Use when' trigger guidance, and a clearly differentiated Windows API niche. The only gap is missing synonym/technical keyword variations that would make triggering even more robust.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Find and explore Windows desktop APIs", "Discovers the right API for a task", "retrieves full type details (methods, properties, events, enumeration values)" — with comprehensive coverage and no gaps, matching the top anchor rather than the 'minor gaps' level 4.

5 / 5

Completeness

Explicitly answers both what ("Discovers the right API… retrieves full type details") and when ("Use when building features that need platform capabilities — …") with concrete trigger phrases, exactly matching the level 5 anchor rather than the merely-present level 4.

5 / 5

Trigger Term Quality

Natural capability terms users would say ("camera, file access, notifications, UI controls, AI/ML, sensors, networking") give good coverage, but synonyms and technical extensions (WinRT, .winmd, WinUI) are absent, so it falls short of the comprehensive-synonym level 5.

4 / 5

Distinctiveness Conflict Risk

"Windows desktop APIs" with platform-capability triggers carves a clear niche with minimal overlap risk against other skills; it is not merely 'mostly distinct' as at level 4.

5 / 5

Total

19

/

20

Passed

Validation

100%

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/PowerToys

Path

.github/skills/winmd-api-search/SKILL.md

Reviewed

Table of Contents

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.