Agent outcome loop
Let rankings learn from real agent runs.
Resolve
The agent gets one recommended skill.
Resolve returns the selected skill, alternatives, install plan, Trust Score, safety policy, and a unique feedback event id.
Run
The agent tries one narrow task.
Use a sandbox workflow first. Record whether install was used, whether setup was required, and whether risk blocked execution.
Learn
The registry updates trust signals.
Aggregate outcomes improve rankings without exposing raw agent notes or per-user identifiers publicly.
Outcome leaderboard
Skills with the strongest adoption evidence
12 skills currently have reported agent outcomes.
女娲.Skill
Early agent signal你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。
Early agent signal: 2 outcomes, 100% success, 2 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 50/100.
Animation Vocabulary
Early agent signalReverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
Early agent signal: 1 outcome, 100% success, 1 install attempt, 0 risk blocks, 0 setup-required reports, Agent Proven Score 51/100.
Taste Skill: Anti-Slop Frontend
Early agent signalDesign and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Early agent signal: 1 outcome, 100% success, 1 install attempt, 0 risk blocks, 0 setup-required reports, Agent Proven Score 42/100.
Frontend Design
Early agent signalGuidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Early agent signal: 1 outcome, 100% success, 1 install attempt, 0 risk blocks, 0 setup-required reports, Agent Proven Score 42/100.
Crawl4AI
Early agent signalOpen-source LLM-friendly web crawler and scraper
Early agent signal: 1 outcome, 100% success, 0 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 39/100.
SenseVoice
Early agent signalMultilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
Early agent signal: 1 outcome, 100% success, 1 install attempt, 0 risk blocks, 0 setup-required reports, Agent Proven Score 42/100.
Aaron Marketing Skills
Early agent signalA comprehensive set of 38 marketing skills and 5 commands for Claude Code covering SEO/GEO and influencer marketing with evaluation frameworks.
Early agent signal: 1 outcome, 100% success, 1 install attempt, 0 risk blocks, 0 setup-required reports, Agent Proven Score 42/100.
Agent Skills
Early agent signalProduction-grade engineering skills for AI coding agents.
Early agent signal: 1 outcome, 0% success, 0 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 19/100.
Dokploy
Early agent signalOpen Source Alternative to Vercel, Netlify and Heroku.
Early agent signal: 1 outcome, 0% success, 0 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 19/100.
InsForge
Early agent signalThe all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.
Early agent signal: 1 outcome, 0% success, 1 install attempt, 0 risk blocks, 0 setup-required reports, Agent Proven Score 15/100.
Ui Ux Pro Max Skill
Needs first agent runAn AI agent skill that provides design intelligence and UI/UX guidelines for building professional interfaces across multiple platforms.
No agent outcome reports yet. The first resolved run should report success, failed, not_relevant, blocked_by_risk, or setup_required.
MiroFish
Needs first agent runA Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
No agent outcome reports yet. The first resolved run should report success, failed, not_relevant, blocked_by_risk, or setup_required.
POST /api/agent/outcome
Report after one narrow run.
Resolve responses include a unique feedback.event_id. Agents should reuse it when reporting the result so retries stay idempotent.
{
"event_id": "resolve_...",
"skill_slug": "crawl4ai",
"task": "scrape pricing pages",
"agent": "codex",
"outcome": "success",
"install_used": true,
"time_to_useful_ms": 120000
}Outcome meanings
Use the smallest honest label.
successThe skill helped complete the task.failedThe skill was attempted but did not work.not_relevantThe selected skill did not fit the task.blocked_by_riskAudit, license, token, shell, or network risk stopped execution.setup_requiredThe skill looked relevant but needed missing keys, data, or configuration.