Agent skill resolver

Describe the task. Get the right reusable skill.

OpenAgentSkill turns vague agent work into a concrete install plan: recommended skill, alternatives, Trust Score, audit notes, safety policy, and target-specific handoff.
1 + 4
Ranked skills
Score
Agent Proven
Receipt
Install handoff

Resolved decision

analyze-skill-issues

Query the integration-test storage account to find why a specific skill's tests are failing. Reads blob-stored test result files and surfaces error details. TRIGGERS: why is skill failing, skill test failures, debug skill tests, skill failing tests, analyze skill failures, why are tests failing for skill, skill test errors, investigate skill issues. DO NOT USE FOR: analyzing a GitHub Actions run report or comparing test runs across runs (use analyze-test-run).

30/100 task fitNeeds first agent outcome63/100 Trust79/100 audit

Install

npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-skill-issues

Safety gate

Reviewed with permission notes
Require human approval before installing into a real workspace.

Task fit

Matches the job your agent needs to do

Searches scenario, tags, repository metadata, category, and use-case signals before choosing a skill.

Trust

Ranks by quality, adoption, and maintenance

Combines GitHub stars, freshness, license clarity, install readiness, and OpenAgentSkill Trust Score.

Agent Proven

Uses real run outcomes when available

Surfaces reported success, recent failures, install success, output quality, and production-use signals.

Install

Returns agent-ready handoffs

Provides CLI command, target agent prompt, detail page, audit page, and safer next steps.

Agent Resolve

Describe the task. Get a ranked skill plan.

Try one

Recommendation

Resolve output will appear here

The registry returns a decision, not just links.

Your agent gets one primary recommendation plus qualified alternatives, install command, Trust Score, audit summary, and a safety policy before it acts.