对照HuggingFace router的模型列表与chat-ui配置,研究尚未收录的模型,编写简短英文说明,并同步添加到生产和开发配置。
- 添加路由中新上线的模型
- 用简短说明概括模型特点
- 同步更新生产和开发环境的模型信息
协调多个GitHub仓库中AI代理的分工与进度,分析依赖关系,开展共享更新、测试和跨项目修改,并创建相互关联的拉取请求。
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm
agent-multi-repo-swarm协调多个GitHub仓库中AI代理团队的分工与工作进度。它涵盖查找相关仓库、分析依赖关系、开展共享更新、执行测试,以及创建并关联拉取请求。资料还展示了如何为仓库设置UI、API、共享库等角色,并为各仓库分配负责的代理。
适合前端与后端分开管理,或多个服务使用同一库的开发项目。依赖包批量更新、API重命名和安全修复等涉及多个项目的工作,都可以统一协调推进。它也涵盖进度监控和依赖关系可视化。
通过$agent-multi-repo-swarm调用。需要完成GitHub CLI身份验证,并拥有目标仓库的访问权限。资料中的流程使用git、jq、npx,以及ruv-swarm或claude-flow的MCP工具。根据配置,还会使用Redis、Webhook、Kafka等。
本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。
AI 仅根据 SKILL.md 的内容,从 4 个方面进行了评估。星标数和热度不计入评估。
总分按每项 A=25 分、B=15 分、C=5 分相加。 由 AI(OpenAI Codex)于 2026年10月21日 评估。仅供参考,安装前请同时查看原文。
安装前可以查看交给 AI 代理的指令内容。
name: multi-repo-swarm description: Cross-repository swarm orchestration for organization-wide automation and intelligent collaboration type: coordination color: "#FF6B35" tools:
Coordinate AI swarms across multiple repositories, enabling organization-wide automation and intelligent cross-project collaboration.
# Initialize multi-repo swarm with gh CLI
# List organization repositories
REPOS=$(gh repo list org --limit 100 --json name,description,languages \
--jq '.[] | select(.name | test("frontend|backend|shared"))')
# Get repository details
REPO_DETAILS=$(echo "$REPOS" | jq -r '.name' | while read -r repo; do
gh api repos$org/$repo --jq '{name, default_branch, languages, topics}'
done | jq -s '.')
# Initialize swarm with repository context
npx ruv-swarm github multi-repo-init \
--repo-details "$REPO_DETAILS" \
--repos "org$frontend,org$backend,org$shared" \
--topology hierarchical \
--shared-memory \
--sync-strategy eventual
# Auto-discover related repositories with gh CLI
# Search organization repositories
REPOS=$(gh repo list my-organization --limit 100 \
--json name,description,languages,topics \
--jq '.[] | select(.languages | keys | contains(["TypeScript"]))')
# Analyze repository dependencies
DEPS=$(echo "$REPOS" | jq -r '.name' | while read -r repo; do
# Get package.json if it exists
if gh api repos$my-organization/$repo$contents$package.json --jq '.content' 2>$dev$null; then
gh api repos$my-organization/$repo$contents$package.json \
--jq '.content' | base64 -d | jq '{name, dependencies, devDependencies}'
fi
done | jq -s '.')
# Discover and analyze
npx ruv-swarm github discover-repos \
--repos "$REPOS" \
--dependencies "$DEPS" \
--analyze-dependencies \
--suggest-swarm-topology
# Execute synchronized changes across repos with gh CLI
# Get matching repositories
MATCHING_REPOS=$(gh repo list org --limit 100 --json name \
--jq '.[] | select(.name | test("-service$")) | .name')
# Execute task and create PRs
echo "$MATCHING_REPOS" | while read -r repo; do
# Clone repo
gh repo clone org/$repo $tmp/$repo -- --depth=1
# Execute task
cd $tmp/$repo
npx ruv-swarm github task-execute \
--task "update-dependencies" \
--repo "org/$repo"
# Create PR if changes exist
if [[ -n $(git status --porcelain) ]]; then
git checkout -b update-dependencies-$(date +%Y%m%d)
git add -A
git commit -m "chore: Update dependencies"
# Push and create PR
git push origin HEAD
PR_URL=$(gh pr create \
--title "Update dependencies" \
--body "Automated dependency update across services" \
--label "dependencies,automated")
echo "$PR_URL" >> $tmp$created-prs.txt
fi
cd -
done
# Link related PRs
PR_URLS=$(cat $tmp$created-prs.txt)
npx ruv-swarm github link-prs --urls "$PR_URLS"
# .swarm$multi-repo.yml
version: 1
organization: my-org
repositories:
- name: frontend
url: github.com$my-org$frontend
role: ui
agents: [coder, designer, tester]
- name: backend
url: github.com$my-org$backend
role: api
agents: [architect, coder, tester]
- name: shared
url: github.com$my-org$shared
role: library
agents: [analyst, coder]
coordination:
topology: hierarchical
communication: webhook
memory: redis:/$shared-memory
dependencies:
- from: frontend
to: [backend, shared]
- from: backend
to: [shared]
// Define repository roles and responsibilities
{
"roles": {
"ui": {
"responsibilities": ["user-interface", "ux", "accessibility"],
"default-agents": ["designer", "coder", "tester"]
},
"api": {
"responsibilities": ["endpoints", "business-logic", "data"],
"default-agents": ["architect", "coder", "security"]
},
"library": {
"responsibilities": ["shared-code", "utilities", "types"],
"default-agents": ["analyst", "coder", "documenter"]
}
}
}
# Update dependencies across all repos with gh CLI
# Create tracking issue first
TRACKING_ISSUE=$(gh issue create \
--title "Dependency Update: typescript@5.0.0" \
--body "Tracking issue for updating TypeScript across all repositories" \
--label "dependencies,tracking" \
--json number -q .number)
# Get all repos with TypeScript
TS_REPOS=$(gh repo list org --limit 100 --json name | jq -r '.[].name' | \
while read -r repo; do
if gh api repos$org/$repo$contents$package.json 2>$dev$null | \
jq -r '.content' | base64 -d | grep -q '"typescript"'; then
echo "$repo"
fi
done)
# Update each repository
echo "$TS_REPOS" | while read -r repo; do
# Clone and update
gh repo clone org/$repo $tmp/$repo -- --depth=1
cd $tmp/$repo
# Update dependency
npm install --save-dev typescript@5.0.0
# Test changes
if npm test; then
# Create PR
git checkout -b update-typescript-5
git add package.json package-lock.json
git commit -m "chore: Update TypeScript to 5.0.0
Part of #$TRACKING_ISSUE"
git push origin HEAD
gh pr create \
--title "Update TypeScript to 5.0.0" \
--body "Updates TypeScript to version 5.0.0\n\nTracking: #$TRACKING_ISSUE" \
--label "dependencies"
else
# Report failure
gh issue comment $TRACKING_ISSUE \
--body "❌ Failed to update $repo - tests failing"
fi
cd -
done
# Coordinate large-scale refactoring
npx ruv-swarm github multi-repo-refactor \
--pattern "rename:OldAPI->NewAPI" \
--analyze-impact \
--create-migration-guide \
--staged-rollout
# Coordinate security patches
npx ruv-swarm github multi-repo-security \
--scan-all \
--patch-vulnerabilities \
--verify-fixes \
--compliance-report
// webhook-coordinator.js
const { MultiRepoSwarm } = require('ruv-swarm');
const swarm = new MultiRepoSwarm({
webhook: {
url: 'https:/$swarm-coordinator.example.com',
secret: process.env.WEBHOOK_SECRET
}
});
// Handle cross-repo events
swarm.on('repo:update', async (event) => {
await swarm.propagate(event, {
to: event.dependencies,
strategy: 'eventual-consistency'
});
});
# Federated schema for multi-repo queries
type Repository @key(fields: "id") {
id: ID!
name: String!
swarmStatus: SwarmStatus!
dependencies: [Repository!]!
agents: [Agent!]!
}
type SwarmStatus {
active: Boolean!
topology: Topology!
tasks: [Task!]!
memory: JSON!
}
# Kafka configuration for real-time coordination
kafka:
brokers: ['kafka1:9092', 'kafka2:9092']
topics:
swarm-events:
partitions: 10
replication: 3
swarm-memory:
partitions: 5
replication: 3
# Create distributed task queue
npx ruv-swarm github multi-repo-queue \
--backend redis \
--workers 10 \
--priority-routing \
--dead-letter-queue
# Run integration tests across repos
npx ruv-swarm github multi-repo-test \
--setup-test-env \
--link-services \
--run-e2e \
--tear-down
# Assist in monorepo migration
npx ruv-swarm github to-monorepo \
--analyze-repos \
--suggest-structure \
--preserve-history \
--create-migration-prs
# Launch monitoring dashboard
npx ruv-swarm github multi-repo-dashboard \
--port 3000 \
--metrics "agent-activity,task-progress,memory-usage" \
--real-time
# Visualize repo dependencies
npx ruv-swarm github dep-graph \
--format mermaid \
--include-agents \
--show-data-flow
# Monitor swarm health across repos
npx ruv-swarm github health-check \
--repos "org/*" \
--check "connectivity,memory,agents" \
--alert-on-issues
// Eventual consistency for non-critical updates
{
"sync": {
"strategy": "eventual",
"max-lag": "5m",
"retry": {
"attempts": 3,
"backoff": "exponential"
}
}
}
// Strong consistency for critical operations
{
"sync": {
"strategy": "strong",
"consensus": "raft",
"quorum": 0.51,
"timeout": "30s"
}
}
// Mix of consistency levels
{
"sync": {
"default": "eventual",
"overrides": {
"security-updates": "strong",
"dependency-updates": "strong",
"documentation": "eventual"
}
}
}
# Coordinate microservices development
npx ruv-swarm github microservices \
--services "auth,users,orders,payments" \
--ensure-compatibility \
--sync-contracts \
--integration-tests
# Update shared library across consumers
npx ruv-swarm github lib-update \
--library "org$shared-lib" \
--version "2.0.0" \
--find-consumers \
--update-imports \
--run-tests
# Apply org-wide policy changes
npx ruv-swarm github org-policy \
--policy "add-security-headers" \
--repos "org/*" \
--validate-compliance \
--create-reports
# Implement cross-repo caching
npx ruv-swarm github cache-strategy \
--analyze-patterns \
--suggest-cache-layers \
--implement-invalidation
# Optimize parallel operations
npx ruv-swarm github parallel-optimize \
--analyze-dependencies \
--identify-parallelizable \
--execute-optimal
# Pool resources across repos
npx ruv-swarm github resource-pool \
--share-agents \
--distribute-load \
--monitor-usage
# Diagnose connectivity problems
npx ruv-swarm github diagnose-connectivity \
--test-all-repos \
--check-permissions \
--verify-webhooks
# Debug memory sync issues
npx ruv-swarm github debug-memory \
--check-consistency \
--identify-conflicts \
--repair-state
# Identify performance issues
npx ruv-swarm github perf-analysis \
--profile-operations \
--identify-bottlenecks \
--suggest-optimizations
# Update full-stack application
npx ruv-swarm github fullstack-update \
--frontend "org$web-app" \
--backend "org$api-server" \
--database "org$db-migrations" \
--coordinate-deployment
# Facilitate cross-team work
npx ruv-swarm github cross-team \
--teams "frontend,backend,devops" \
--task "implement-feature-x" \
--assign-by-expertise \
--track-progress
See also: swarm-pr.md, project-board-sync.md
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
对照HuggingFace router的模型列表与chat-ui配置,研究尚未收录的模型,编写简短英文说明,并同步添加到生产和开发配置。
为技术选型和设计决策创建ADR文档,沿用现有文件的连续编号,生成模板并登记到AgentDB,同时为找到的相关历史决策添加链接和依赖关系。
读取记录架构决策及其原因的ADR,创建并更新搜索索引和依赖关系图。支持两种文档格式,并汇总引用与状态的不一致情况。
删除ADR设计决策记录或关系信息后,清空并重建索引,移除残留的旧条目,再核对当前文件数与索引记录数是否一致;也可预览重建内容而不作更改。
将代码差异与记录已采纳设计决策的ADR进行核对,整理违反决策、引用过时记录及缺少相关记录的变更,并提出代码修正或决策调整建议。
检查已保存的架构决策记录(ADR),报告失效引用、替代关系中的循环和状态不一致问题,适合导入后的校验与发布前的数据检查。