OpenAgentSkillRegistry
ResolveSkillsTasksPacksCompare
Star200+Submit Skill
Star200+

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
Best skill
Score
Agent Proven
Receipt
Install handoff

Resolved decision

Vox Director

Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.

99/100 task fitNeeds first agent outcome73/100 Trust90/100 audit

Install

npx skills add Alisa0808/vox-director --skill vox-director

Safety gate

Reviewed
Review the audit page, then allow agent install in a sandboxed workflow.
Open skillAudit pageText APIInstall receipt

Why this pick

  • Matches task terms: generate, roll
  • Quality score 88/100
  • Install handoff is available
  • Repository freshness signal is available
  • Registry match score 99

Agent Proven

0
Score
0
Runs
No data
Success

No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.

Receipt + outcome loop

Use receipt receipt_22652aa9-709c-4445-83d0-b5686f92e4c2 as the stable install handoff, then report one narrow run so rankings learn from real use.

npx openagentskill outcome "resolve_22652aa9-709c-4445-83d0-b5686f92e4c2" --skill "vox-director" --task "Generate B-roll" --agent "codex" --outcome success

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 one skill plan.

API ready

Try one

Recommendation

Resolve output will appear here

The registry returns a decision, not just links.

Your agent gets one recommended skill, alternatives, install command, Trust Score, audit summary, and a safety policy before it acts.

Plain text API

Agent-readable response

Use text output when an agent or CLI needs the decision without rendering JSON.

Schema

OpenAPI contract

Inspect request parameters, response fields, and recommended integration flow.

Human browse

Review the registry

Browse production candidates with the same trust, safety, and supply signals.

OpenAgentSkill

The skill layer for AI agents: discover, compare, audit, and install reusable capabilities across Codex, Claude Code, Cursor, and agent runtimes.

GitHubX

Explore

SkillsAgent SkillsWhat Is an Agent Skill?AI Agent SkillsTasksInstallable PacksBest SkillsTrendingWorkflow RecipesUse CasesAgentsAgent Entry

Trust

CompareSafety GateSkills RegistryRankingsOutcomesAuditsOfficialWeekly ReportsMonthly IndexState of Agent Skillsvs skills.shAgentSkills.io Alternative

Build

DocsAbout OpenAgentSkillAPIllms.txtOpenAPICLICreator KitX Growth KitSubmitBlogGuidesActivity
OpenAgentSkill Registry
PrivacyBuilt for agent-native discovery