AGENT SKILL

worker-integration

Worker-Agent integration for intelligent task dispatch and performance tracking

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
worker-integration
author
agentic-flow
version
1.0.0
invocable
true
description
Worker-Agent integration for intelligent task dispatch and performance tracking
capabilities
[ "agent_selection", "performance_tracking", "memory_coordination", "self_learning" ]

03 SKILL.md 正文

Worker-Agent Integration Skill

Intelligent coordination between background workers and specialized agents.

Quick Start

# View agent recommendations for a trigger
npx agentic-flow workers agents ultralearn
npx agentic-flow workers agents optimize

# View performance metrics
npx agentic-flow workers metrics

# View integration stats
npx agentic-flow workers stats --integration

Agent Mappings

Workers automatically dispatch to optimal agents based on trigger type:

Trigger Primary Agents Fallback Pipeline Phases
ultralearn researcher, coder planner discovery → patterns → vectorization → summary
optimize performance-analyzer, coder researcher static-analysis → performance → patterns
audit security-analyst, tester reviewer security → secrets → vulnerability-scan
benchmark performance-analyzer coder, tester performance → metrics → report
testgaps tester coder discovery → coverage → gaps
document documenter, researcher coder api-discovery → patterns → indexing
deepdive researcher, security-analyst coder call-graph → deps → trace
refactor coder, reviewer researcher complexity → smells → patterns

Performance-Based Selection

The system learns from execution history to improve agent selection:

// Agent selection considers:
// 1. Quality score (0-1)
// 2. Success rate
// 3. Average latency
// 4. Execution count

const { agent, confidence, reasoning } = selectBestAgent('optimize');
// agent: "performance-analyzer"
// confidence: 0.87
// reasoning: "Selected based on 45 executions with 94.2% success"

Memory Key Patterns

Workers store results using consistent patterns:

{trigger}/{topic}/{phase}

Examples:
- ultralearn/auth-module/analysis
- optimize/database/performance
- audit/payment/vulnerabilities
- benchmark/api/metrics

Benchmark Thresholds

Agents are monitored against performance thresholds:

{
  "researcher": {
    "p95_latency": "<500ms",
    "memory_mb": "<256MB"
  },
  "coder": {
    "p95_latency": "<300ms",
    "quality_score": ">0.85"
  },
  "security-analyst": {
    "scan_coverage": ">95%",
    "p95_latency": "<1000ms"
  }
}

Feedback Loop

Workers provide feedback for continuous improvement:

import { workerAgentIntegration } from 'agentic-flow/workers/worker-agent-integration';

// Record execution feedback
workerAgentIntegration.recordFeedback(
  'optimize',           // trigger
  'coder',              // agent
  true,                 // success
  245,                  // latency ms
  0.92                  // quality score
);

// Check compliance
const { compliant, violations } = workerAgentIntegration.checkBenchmarkCompliance('coder');

Integration Statistics

$ npx agentic-flow workers stats --integration

Worker-Agent Integration Stats
══════════════════════════════
Total Agents:       6
Tracked Agents:     4
Total Feedback:     156
Avg Quality Score:  0.89

Model Cache Stats
─────────────────
Hits:     1,234
Misses:   45
Hit Rate: 96.5%

Configuration

Enable integration features in .claude/settings.json:

{
  "workers": {
    "enabled": true,
    "parallel": true,
    "memoryDepositEnabled": true,
    "agentMappings": {
      "ultralearn": ["researcher", "coder"],
      "optimize": ["performance-analyzer", "coder"]
    }
  }
}

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1