alchaincyf/huashu-skills / huashu-agent-swarm
huashu-agent-swarm
Verified多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.6 KB |
| references/agent-prompt-template.md | markdown | 4.1 KB |
| references/carlini-lessons.md | markdown | 3.3 KB |
| scripts/agent_loop.shexecutable | script | 2.8 KB |
| scripts/dashboard.pyexecutable | script | 20.6 KB |
| scripts/send_input.shexecutable | script | 1.0 KB |
| scripts/setup_project.shexecutable | script | 2.7 KB |
| scripts/start_swarm.shexecutable | script | 3.3 KB |
| scripts/status.shexecutable | script | 2.7 KB |
| scripts/stop_swarm.shexecutable | script | 2.3 KB |
scripts/send_input.sh
View on GitHub#!/bin/bash
# send_input.sh - 向蜂群发送人类指令
# 用法: bash send_input.sh <项目目录> "你的指令"
# 示例: bash send_input.sh /path/to/project "停止重构,优先修复登录bug"
PROJECT_DIR="${1:-.}"
PROJECT_DIR="$(cd "$PROJECT_DIR" && pwd)"
MESSAGE="$2"
if [ -z "$MESSAGE" ]; then
echo "用法: bash send_input.sh <项目目录> \"你的指令\""
echo ""
echo "示例:"
echo " bash send_input.sh . \"优先修复登录页面的bug\""
echo " bash send_input.sh . \"不要动 config/ 目录下的文件\""
echo " bash send_input.sh . \"所有agent停止当前工作,先跑一遍完整测试\""
exit 1
fi
# 写入指令
TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S')
cat > "$PROJECT_DIR/HUMAN_INPUT.md" << EOF
# 人类指令 - ${TIMESTAMP}
${MESSAGE}
EOF
# 提交并推送
cd "$PROJECT_DIR"
git add HUMAN_INPUT.md
git commit -m "HUMAN: ${MESSAGE:0:50}" 2>/dev/null
git push origin main 2>/dev/null || true
echo "指令已发送: $MESSAGE"
echo "下一个启动session的agent会优先执行此指令"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |