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
228 skills currently have reported agent outcomes.
Frontend Design
Promising agent evidenceGuidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Promising agent evidence: 56 outcomes, 93% success, 56 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 69/100.
mono-color
Promising agent evidenceGenerate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for 单色海报、双色印刷、单色调视觉、蓝色/绿色孔版印刷、risograph、网点照片、复古或当代编辑排版、zine poster, monochrome editorial poster, duotone print, or asks to use the mono-color style. It uses an adaptive white, gray, or pale-beige substrate, no more than two printing inks, active negative space, terse human language, and strong serif/grotesk/mono typography without making retro styling the default or copying a source composition, wording, logo, or artwork. Produce both the final generation prompt and the generated raster image unless the user explicitly asks for prompt only.
Promising agent evidence: 45 outcomes, 100% success, 45 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 80/100.
Vox Director
Promising agent evidenceTurn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.
Promising agent evidence: 38 outcomes, 100% success, 38 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 80/100.
Taste Skill: Anti-Slop Frontend
Early agent signalDesign and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Early agent signal: 32 outcomes, 88% success, 32 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 66/100.
Guizang Ppt Skill
Promising agent evidenceAI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.
Promising agent evidence: 25 outcomes, 100% success, 25 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 74/100.
Archify
Promising agent evidenceAny agent Skill: generate beautiful architecture diagrams with dark/light theme toggle and PNG/JPEG/WebP/SVG export
Promising agent evidence: 17 outcomes, 100% success, 17 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 75/100.
Canvas Design
Promising agent evidenceCreate original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Promising agent evidence: 13 outcomes, 100% success, 13 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 77/100.
Web Design Guidelines
Promising agent evidenceReview UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.
Promising agent evidence: 12 outcomes, 100% success, 12 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 77/100.
Superpowers
Promising agent evidenceAn agentic skills framework & software development methodology that works.
Promising agent evidence: 13 outcomes, 92% success, 13 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 69/100.
unslop
Promising agent evidenceApplies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.
Promising agent evidence: 13 outcomes, 100% success, 13 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 75/100.
Frontend Slides
Early agent signalCreate beautiful slides on the web using a coding agent's frontend skills
Early agent signal: 12 outcomes, 92% success, 11 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 67/100.
Webapp Testing
Promising agent evidenceUse Playwright to interact with and test local web applications, capture screenshots, debug UI behavior, and inspect browser logs.
Promising agent evidence: 8 outcomes, 100% success, 8 install attempts, 0 risk blocks, 0 setup-required reports, Agent Proven Score 73/100.
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.