Huashu Agent Swarm
alchaincyf/huashu-skills
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。
跨平台 Agent 任务协调枢纽。本技能应在多个不同平台的 Agent 需要围绕项目任务源分配任务、标记归属、能力路由和交接上下文时使用。不要用于单一平台内的本地并行执行，或 Git 分支、提交、PR、merge 安全规则。
Install Cross Agent Coordination
$ npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cat-xierluo/legal-skills cross-agent-coordination --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cross-agent-coordination .claude/skills/cross-agent-coordination && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cross-agent-coordination" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/cross-agent-coordination into .claude/skills/cross-agent-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-coordination", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cat-xierluo/legal-skills/tree/main/skills/cross-agent-coordinationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cat-xierluo/legal-skills cross-agent-coordination --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cross-agent-coordination .agents/skills/cross-agent-coordination && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cross-agent-coordination" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/cross-agent-coordination into .agents/skills/cross-agent-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-coordination", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cat-xierluo/legal-skills cross-agent-coordination --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cross-agent-coordination .cursor/skills/cross-agent-coordination && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cross-agent-coordination" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/cross-agent-coordination into .cursor/skills/cross-agent-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-coordination", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cat-xierluo/legal-skills.git --path skills/cross-agent-coordination--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cat-xierluo/legal-skills cross-agent-coordination --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cross-agent-coordination .gemini/skills/cross-agent-coordination && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cross-agent-coordination" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/cross-agent-coordination into .gemini/skills/cross-agent-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-coordination", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cat-xierluo/legal-skills cross-agent-coordinationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cross-agent-coordination .github/skills/cross-agent-coordination && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cross-agent-coordination" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/cross-agent-coordination into .github/skills/cross-agent-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-coordination", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cat-xierluo/legal-skills cross-agent-coordination --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cross-agent-coordination .opencode/skills/cross-agent-coordination && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cross-agent-coordination" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/cross-agent-coordination into .opencode/skills/cross-agent-coordination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cross-agent-coordination", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
cross-agent-coordination- GitHub stars
- 717
- Token cost
- ~1.7k tokens
- SKILL.md length
- 354 words
- Files
- 21 (incl. scripts, references)
- Skills in repo
- 62
- Repo updated
- First seen
- Licence
- MIT
At a glance
跨平台 Agent 任务协调枢纽。本技能应在多个不同平台的 Agent 需要围绕项目任务源分配任务、标记归属、能力路由和交接上下文时使用。不要用于单一平台内的本地并行执行，或 Git 分支、提交、PR、merge 安全规则。
- Works in 10 steps: 何时使用 → 核心规则 → 项目配置 → …
- Tasks that involve Multi-agent orchestration
- SKILL.md covers 1. 何时使用, 2. 核心规则, 3. 项目配置 and 4. 任务模型, plus 6 more sections
- Runs Python scripts from its folder; calls python3 and git; needs CODEX_GITHUB_TOKEN and MANUS_GITHUB_TOKEN
What it does
Cross Agent Coordination is an agent skill from cat-xierluo/legal-skills. 跨平台 Agent 任务协调枢纽。本技能应在多个不同平台的 Agent 需要围绕项目任务源分配任务、标记归属、能力路由和交接上下文时使用。不要用于单一平台内的本地并行执行，或 Git 分支、提交、PR、merge 安全规则。
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including scripts and reference files (for example `CHANGELOG.md`, `references/agent-guide.md` and `references/agent-identity.md`).
It sits in Agent Workflows, covering Multi-agent orchestration and Git workflow. It works with Git. The licence is MIT.
When your agent uses it
- Tasks that involve Multi-agent orchestration
- Tasks that involve Git workflow
Example prompts
- “/cross-agent-coordination”
Requirements
- Python 3
- A credential in CODEX_GITHUB_TOKEN
- A credential in MANUS_GITHUB_TOKEN
Workflow steps
10 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit c077fcc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 8 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
CODEX_GITHUB_TOKENMANUS_GITHUB_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cross Agent Coordination loads about 1.7k tokens when it runs, and up to ~6.7k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 354 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from cat-xierluo/legal-skills at commit c077fcc, republished under its MIT licence (© cat-xierluo). 354 words, ~1,686 tokens.
Download SKILL.mdSave it as
.claude/skills/cross-agent-coordination/SKILL.md (or your agent's skills folder). This skill also uses 20 other files; get the full folder from GitHub.- name
- cross-agent-coordination
- description
- 跨平台 Agent 任务协调枢纽。本技能应在多个不同平台的 Agent 需要围绕项目任务源分配任务、标记归属、能力路由和交接上下文时使用。不要用于单一平台内的本地并行执行，或 Git 分支、提交、PR、merge 安全规则。
- license
- MIT
- homepage
- https://github.com/cat-xierluo/legal-skills
- author
- 杨卫薪律师（微信ywxlaw）
- version
- 1.0.0
Cross-Agent Coordination
跨平台 Agent 任务协调枢纽。核心职责是让不同平台的 Agent 围绕项目配置或项目上下文指定的任务源分配任务、保留交接上下文，并在提交/PR 中标记 Agent 归属。
1. 何时使用
使用本 Skill：
- 多个不同平台的 Agent 需要在同一仓库协作
- 需要追溯某个提交/PR 是哪个 Agent 完成的
- 需要把任务派给 Manus、AnyGen、Coze 等外部 Agent
- 需要跨会话保留任务上下文、依赖和交接记录
不使用本 Skill：
- 单一平台内的并行执行：使用
multi-agent-orchestration - 纯 Git 安全规范：使用
git-workflow
2. 核心规则
- 任务源由项目定义：常规任务状态以项目配置或项目上下文指定的任务源为准；任务文件夹只是材料包、产物包和交接包。
- 归属优先：提交前必须设置 Git Author；PR 正文应包含 Agent Attribution。
- 任务按分配执行：默认只处理项目任务源中负责人/委托对象匹配当前 Agent 的任务。
- 项目可配置：任务类型、模板、状态映射、认领策略由项目级配置决定，不改 Skill 源码。
- 交接可追溯：Issue、任务 README 或
.agent-context/handoff.md必须记录目标、来源、决策、阻塞和下一步。
3. 项目配置
项目根目录使用本地忽略配置：
cp .claude/skills/cross-agent-coordination/config/collab.yaml.example config/collab.yaml关键字段（示例；具体任务源由项目决定）：
project:
mode: task_folders # task_folders | single_repo
default_agent: codex
issue_file: project-tasks.md
task_context_mode: issues_primary
status_map:
"⬜": pending_confirmation
"✅": ready
"🟢": created
available_statuses: [ready, created, todo]
dependency_done_statuses: [ready, created, done, resolved, closed]
claim_policy: assigned_only # assigned_only | claim_pool
task_types_file: config/task-types.yaml
template_dir: templates/tasks
agents:
codex:
name: "Codex"
email: "codex@agents.local"
github_user: "codex-bot"
token_env: "CODEX_GITHUB_TOKEN"配置路径固定为 config/collab.yaml。旧的 github-monorepo-collab 和 config/monorepo.yaml 不再读取。
4. 任务模型
项目配置中的 project.issue_file 或项目上下文指定的任务文件，是脚本读取任务的默认入口。脚本可解析如下格式：
### ✅ Issue #9: 触发 Manus 调研任务
- **类型**: 研究（委托 Manus）
- **依赖**: Issue #7 确定后
- **目标**: 为 ch03 法律 AI 基础设施章节提供调研支撑
#### 验收标准
- [ ] 形成产品对比表解析字段包括 Issue 编号、标题、状态标记、类型、负责人/委托 Agent、依赖、目标、素材来源和验收标准。状态由 project.status_map 映射；find_task.py --available 只返回状态可执行、依赖满足、负责人匹配的 Issue。
任务文件夹模式仍可使用 {YYMMDDNNN}-{type}-{title}/README.md，但它是重任务材料包/产物包/交接包，不覆盖主任务源状态：
---
id: 260517001
title: 法律AI产品生态调查
type: 研究
status: todo
assignee: manus
dependencies: []
artifact_paths: []
progress: 0
created: 2026-05-17
updated: 2026-05-17
---assignee 是材料包负责人字段；agent 只作为旧任务兼容读取，不再作为新任务必填字段。任务文件夹依赖仍按 done / resolved / closed 判断；Issue 依赖按 dependency_done_statuses 判断。
项目可在 config/task-types.yaml 扩展任务类型：
task_types:
整合:
aliases: [integration]
description: 多来源材料融合
output_hint: 统一稿/整合报告
审阅:
aliases: [review]
description: 质量审查/事实核查
output_hint: 审阅意见/修订稿项目可在 templates/tasks/{type}.md 或 templates/tasks/default.md 定义任务 README 模板。模板变量使用 {{ id }}、{{ slug }}、{{ title }}、{{ type }}、{{ assignee }}、{{ created }}、{{ updated }}。
5. 依赖
Python 包
| 包名 | 用途 | 安装命令 |
|---|---|---|
PyYAML | 读取 collab.yaml、task-types.yaml 和 frontmatter | python3 -m pip install -r scripts/requirements.txt |
安装依赖（仅在脚本提示缺失时）：
python3 -m pip install -r scripts/requirements.txt6. 常用脚本
| 脚本 | 用途 |
|---|---|
scripts/task_scaffold.py | 创建任务文件夹，分配稳定 Task ID，按项目模板写 README |
scripts/find_task.py | 按主题搜索项目任务源和任务文件夹，支持 --available 依赖/分配过滤 |
scripts/gh_git.py | 带 Agent 归属的 clone/branch/commit/push/PR/merge |
scripts/email_trigger.py | 为外部 Agent 生成标准邮件触发草稿 |
scripts/audit_repo.py | 审计任务 metadata 与项目类型注册表是否一致 |
示例：
python3 scripts/task_scaffold.py create --root . --type 研究 --topic "法律AI产品生态调查" --assignee manus
python3 scripts/task_scaffold.py create --root . --type 写作 --topic "ch01 Agent发展阶段" --field chapter=ch01 --field target_words=15000
python3 scripts/find_task.py . --available --agent manus
python3 scripts/gh_git.py commit --dest . --agent manus --message "docs: update handoff"
python3 scripts/gh_git.py pr --dest . --agent manus --title "docs: Manus handoff update"
python3 scripts/email_trigger.py . --agent manus --issue 97. Agent 归属
每次提交涉及两层身份：
| 层级 | 控制方式 | 证明什么 |
|---|---|---|
| Git Author | git config user.name / user.email | 谁写了提交内容 |
| GitHub Actor / PR Opener | 使用的 Token 或 GitHub App | 哪个账号执行平台操作 |
脚本会设置 Git Author。PR Opener 由 token 决定；如果要让 PR actor 区分 Agent，需要给该 Agent 配置独立 token 环境变量。详细规则见 references/agent-identity.md。
8. 工作流
Show full SKILL.md (154 more words)Show less
Issue / Task 主状态模式
- 读取
config/collab.yaml、config/task-types.yaml、项目模板和项目上下文。 - 用
find_task.py --available --agent <agent-id>从项目任务源领取可执行任务。 - 只有任务需要较多材料、产物或交接记录时，才用
task_scaffold.py create创建或复用任务文件夹。 - 在
agent/{agent-id}/{slug}分支上工作。 - 提交时用
gh_git.py commit标记 Git Author。 - 完成后更新项目任务源状态；若有任务文件夹，同时更新 README 交接记录，并开 PR。
若某个 Issue / Task 不通过 PR，而是在当前分支或 main 上直接解决，提交信息仍必须保留任务来源。GitHub Issue、项目本地任务条目或任务文件夹 ID 的具体提交格式、引用格式和关闭规则遵循 git-workflow；本 Skill 只负责确认任务来源和交接上下文。
单 Repo 模式
不创建任务文件夹；仍需用 Agent 分支、Git Author、PR Attribution 和 .agent-context/handoff.md 保留交接上下文。
邮箱触发
对支持邮箱入口的外部 Agent，使用 email_trigger.py 生成草稿。邮件可通过 --issue 绑定项目任务源中的任务，并包含目标、验收标准、来源材料、依赖、查重命令、分支和 PR 要求。默认不发送真实邮件。
外部 Agent Adapter
外部 Agent（如 Manus、AnyGen、Coze）只作为执行通道或能力 adapter，不拥有任务状态。项目应在 config/collab.yaml 的 agents.<id> 中声明该 Agent 的能力和触发方式：
agents:
manus:
name: "Manus Bot"
email: "manus@agents.local"
github_user: "manus-bot"
token_env: "MANUS_GITHUB_TOKEN"
trigger_email: "manus-agent-inbox@example.com"
capabilities: [web_research, citation_collection]
trigger_modes: [email_draft]
handoff_format: pull_requestAdapter 选择规则：
- 复杂网络搜索、资料收集、网页操作：优先分配给具备
web_research/browser_ops能力的 Agent。 - 图片生成、视觉资产：优先分配给具备
image_generation能力的 Agent。 - 代码修改、本地测试、worktree 执行：交给本地 Agent，并由
multi-agent-orchestration管 session。 - 任何 adapter 都必须绑定项目任务源中的任务或先查重；结果通过分支、PR、handoff note 回到仓库。
9. 参考文档
references/naming.md：任务命名、frontmatter、归档规则references/agent-guide.md：Agent 启动、交接和完成检查清单references/agent-identity.md：Git Author 与 GitHub Actor 归属references/email-trigger.md：邮箱触发协议references/legacy-migration.md：旧任务迁移提示
10. Related Skills
| 维度 | cross-agent-coordination | multi-agent-orchestration | git-workflow |
|---|---|---|---|
| 定位 | 任务协调层 | 本地执行层 | Git 安全层 |
| 主责 | 项目任务源状态、Agent 归属、交接上下文 | Agent Teams / tmux 会话、worktree、PM 巡检 | 分支、PR、diff、review、merge 安全规则 |
| 不负责 | 本地会话管理、Git 合并策略 | 任务主状态、外部 Agent 邮件触发 | 任务分配、本地 Agent 调度 |
协作模式：先由 cross-agent-coordination 从项目任务源确定任务；同平台需要并行执行时使用 multi-agent-orchestration；涉及分支、PR、review 或 merge 时遵循 git-workflow。
© cat-xierluo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 20 other files (scripts, references) in skills/cross-agent-coordination of cat-xierluo/legal-skills.
- SKILL.md
- CHANGELOG.md
- LICENSE.txt
- config/collab.yaml.example
- references/agent-guide.md
- references/agent-identity.md
- references/email-trigger.md
- references/legacy-migration.md
- references/naming.md
- references/task-types.yaml
- scripts/audit_repo.py
- scripts/collab_lib.py
- scripts/email_trigger.py
- scripts/find_task.py
- scripts/gh_git.py
- scripts/requirements.txt
- scripts/task_scaffold.py
- scripts/test_cross_agent_coordination.py
- … and 3 more
Open the folder on GitHubat commit c077fcc
Compare with similar skills
Cross Agent Coordination next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cross Agent Coordination this skillcat-xierluo/legal-skills | 717 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Huashu Agent Swarmalchaincyf/huashu-skills | 1.7k | — | ~576 | Automated safety check: Pass | MIT | |
| Polyphonyalinaqi/maggy | 707 | — | ~980 | Automated safety check: Pass | MIT | |
| Tick CoordLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.9k | Automated safety check: Pass | MIT | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Agtx Task Sweepfynnfluegge/agtx | 1.7k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Polyphony
alinaqi/maggy
Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches
Tick Coord
LeoYeAI/openclaw-master-skills
Multi-agent task coordination via Git-backed Markdown (tick-md).
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
Agtx Task Sweep
fynnfluegge/agtx
Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.
PRP Workstream Orchestrator
Wirasm/prp
Coordinates several PRP workstreams in isolated Git worktrees from one session, verifying proof, holding merge gates and sequencing the merges.
More from cat-xierluo/legal-skills
All 62 skills in this repoElements-Style Complaint Generator
cat-xierluo/legal-skills
Converts a lawyer's ordinary complaint or a described case into the Supreme People's Court's elements-style Word template, with layout checks on the result.
Lecture Performance Review
cat-xierluo/legal-skills
Analyzes raw lecture transcripts for verbal tics, pacing, time use and promise follow-through, with optional slide-by-slide comparison and cross-session tracking.
De-AI Polish for Chinese Articles
cat-xierluo/legal-skills
Detects and rewrites machine-sounding patterns in the body text of Chinese articles while keeping the author's facts, headings and legal terms intact.
GitHub Star Manager
cat-xierluo/legal-skills
Finds GitHub projects mentioned in articles or screenshots and stars them, tracks updates to your starred repos, and builds an HTML dashboard to browse them.
Legal Harness Initializer
cat-xierluo/legal-skills
Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.
Moot Court Simulation Builder
cat-xierluo/legal-skills
Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.
Related
Works with
Categories
Questions about Cross Agent Coordination
What does Cross Agent Coordination do?
跨平台 Agent 任务协调枢纽。本技能应在多个不同平台的 Agent 需要围绕项目任务源分配任务、标记归属、能力路由和交接上下文时使用。不要用于单一平台内的本地并行执行，或 Git 分支、提交、PR、merge 安全规则。. Cross Agent Coordination is an agent skill from cat-xierluo/legal-skills.
When should I use Cross Agent Coordination?
Cross Agent Coordination fits situations like: tasks that involve Multi-agent orchestration; tasks that involve Git workflow.
How do I install Cross Agent Coordination in Claude Code?
Run `npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a claude-code`. Or copy the skill folder (skills/cross-agent-coordination in cat-xierluo/legal-skills) into .claude/skills/cross-agent-coordination in your project. Claude Code loads it when a task matches its description.
How do I install Cross Agent Coordination in Codex?
Run `npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a codex`. Or copy the skill folder (skills/cross-agent-coordination in cat-xierluo/legal-skills) into .agents/skills/cross-agent-coordination in your project. Codex loads it when a task matches its description.
Can I use Cross Agent Coordination in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cat-xierluo/legal-skills --skill cross-agent-coordination -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cross-agent-coordination, .gemini/skills/cross-agent-coordination, .github/skills/cross-agent-coordination and .opencode/skills/cross-agent-coordination in your project.
What does Cross Agent Coordination need to run?
Going by SKILL.md and its folder, Cross Agent Coordination needs Python for the scripts in its folder, the command-line tools its instructions call (python3 and git) and credentials named CODEX_GITHUB_TOKEN and MANUS_GITHUB_TOKEN. Our summary lists: Python 3; A credential in CODEX_GITHUB_TOKEN; A credential in MANUS_GITHUB_TOKEN.
Does Cross Agent Coordination access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Cross Agent Coordination safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Cross Agent Coordination use?
Cross Agent Coordination is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cross Agent Coordination use?
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5k tokens, read only when the agent opens those files.
What are the alternatives to Cross Agent Coordination?
Skills that share tags, products or a category with Cross Agent Coordination: Huashu Agent Swarm (alchaincyf/huashu-skills, 1.7k stars), Polyphony (alinaqi/maggy, 707 stars), Tick Coord (LeoYeAI/openclaw-master-skills, 2.2k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cross Agent Coordination?
cat-xierluo (a GitHub user) maintains it in cat-xierluo/legal-skills, which has 717 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 8, 2026.
Source: cat-xierluo/legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.