MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
选择执行结构、委派子智能体、管理 Nexus 工作图与可复用模板；遵守本轮权限，简单任务直接完成. An agent skill from nexus-research-lab/nexus.
Install Execution Orchestrator
$ npx skills add nexus-research-lab/nexus --skill execution-orchestrator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nexus-research-lab/nexus execution-orchestrator --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/nexus-research-lab/nexus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/execution-orchestrator .claude/skills/execution-orchestrator && 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 "execution-orchestrator" agent skill from https://github.com/nexus-research-lab/nexus/tree/main/skills/execution-orchestrator into .claude/skills/execution-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution-orchestrator", 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/nexus-research-lab/nexus/tree/main/skills/execution-orchestratorType 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 nexus-research-lab/nexus --skill execution-orchestrator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nexus-research-lab/nexus execution-orchestrator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexus-research-lab/nexus.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/execution-orchestrator .agents/skills/execution-orchestrator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "execution-orchestrator" agent skill from https://github.com/nexus-research-lab/nexus/tree/main/skills/execution-orchestrator into .agents/skills/execution-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution-orchestrator", 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 nexus-research-lab/nexus --skill execution-orchestrator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nexus-research-lab/nexus execution-orchestrator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexus-research-lab/nexus.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/execution-orchestrator .cursor/skills/execution-orchestrator && 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 "execution-orchestrator" agent skill from https://github.com/nexus-research-lab/nexus/tree/main/skills/execution-orchestrator into .cursor/skills/execution-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution-orchestrator", 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/nexus-research-lab/nexus.git --path skills/execution-orchestrator--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 nexus-research-lab/nexus --skill execution-orchestrator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nexus-research-lab/nexus execution-orchestrator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexus-research-lab/nexus.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/execution-orchestrator .gemini/skills/execution-orchestrator && 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 "execution-orchestrator" agent skill from https://github.com/nexus-research-lab/nexus/tree/main/skills/execution-orchestrator into .gemini/skills/execution-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution-orchestrator", 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 nexus-research-lab/nexus execution-orchestratorInstalls 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 nexus-research-lab/nexus --skill execution-orchestrator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nexus-research-lab/nexus.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/execution-orchestrator .github/skills/execution-orchestrator && 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 "execution-orchestrator" agent skill from https://github.com/nexus-research-lab/nexus/tree/main/skills/execution-orchestrator into .github/skills/execution-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution-orchestrator", 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 nexus-research-lab/nexus --skill execution-orchestrator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nexus-research-lab/nexus execution-orchestrator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nexus-research-lab/nexus.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/execution-orchestrator .opencode/skills/execution-orchestrator && 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 "execution-orchestrator" agent skill from https://github.com/nexus-research-lab/nexus/tree/main/skills/execution-orchestrator into .opencode/skills/execution-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "execution-orchestrator", 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
execution-orchestrator- GitHub stars
- 150
- Token cost
- ~821 tokens
- SKILL.md length
- 209 words
- Files
- 8 (incl. references)
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
选择执行结构、委派子智能体、管理 Nexus 工作图与可复用模板；遵守本轮权限，简单任务直接完成. An agent skill from nexus-research-lab/nexus.
- Works in 5 steps: substantial execution 前先判断直接执行、局部… → 执行当前任务的责任图时，先调用宿主提供的 nexus.command → 执行图从 data.execution_context XML 的 、lane… → …
- Agent Workflows work in your project
- SKILL.md covers 入口与命令协议, 按当前动作读取参考 and 不变量
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Execution Orchestrator is an agent skill from nexus-research-lab/nexus. 选择执行结构、委派子智能体、管理 Nexus 工作图与可复用模板；遵守本轮权限，简单任务直接完成。
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/communication-and-continuity.md`, `references/graph-control.md` and `references/recovery-and-alignment.md`).
It sits in Agent Workflows. The repository describes itself as: Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services. The licence is Apache-2.0.
When your agent uses it
- Agent Workflows work in your project
Example prompts
- “/execution-orchestrator”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- substantial execution 前先判断直接执行、局部 Task、Subagent、WorkGraph、Room Assignment、Gate/Loop 或 Goal 中哪些结构真的降低风险；简单原子任务直接完成。
- 执行当前任务的责任图时，先调用宿主提供的 nexus.command
- 执行图从 data.execution_context XML 的 、lane 和 binding 判断权限；模板草图使用 authoring 目录。mutation 前读取 fresh exact contract
- 业务输入是 additionalProperties=false 的 closed object，直接放在工具的 input 字段中。只提交 fresh input_schema.properties 中属于当前意图的字段；opaque locator 来自…
- 先检查 is_error；Execution 操作再按 operation 解读 data.outcome：applied 表示已应用；no_op 无新增变更，结合 message 区分重放与 Plan Mode 校验；prepare 成功为 prepared，草图提取为…
What it can do on your machine
Read from SKILL.md and the folder at commit e061bd6. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Execution Orchestrator loads about 821 tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 18 tokens; SKILL.md has 209 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from nexus-research-lab/nexus at commit e061bd6, republished under its Apache-2.0 licence (© nexus-research-lab). 209 words, ~821 tokens.
Download SKILL.mdSave it as
.claude/skills/execution-orchestrator/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- execution-orchestrator
- description
- 选择执行结构、委派子智能体、管理 Nexus 工作图与可复用模板；遵守本轮权限，简单任务直接完成。
Execution Orchestrator
Execution 管理当前责任交付；Goal 管理跨轮目标。按需独立选择或显式绑定，不按任务长度或人数推断。
入口与命令协议
substantial execution 前先判断直接执行、局部 Task、Subagent、WorkGraph、Room Assignment、Gate/Loop 或 Goal 中哪些结构真的降低风险；简单原子任务直接完成。 子任务使用
nexus.command/subagent，按下方参考操作；不要求先创建工作图。执行当前任务的责任图时，先调用宿主提供的
nexus.command：json {"domain":"execution","action":"inspect"}明确读取同一可信 scope 的历史图时才传
input.execution_id。 inspect 不回放成功工具历史；恢复优先使用交付、验收与产物证据，避免重做。 查询、提取、编辑、选择或保存模板草图则直接走 WorkGraph authoring 参考；这些操作不要求 active Execution，也不先运行 execution inspect。执行图从
data.execution_contextXML 的<allowed_actions>、lane 和 binding 判断权限；模板草图使用 authoring 目录。mutation 前读取 fresh exact contract：json {"domain":"execution","action":"contract","operation":"<operation>"}字段、identity、authority 和 revision 以本轮 contract 为准。
业务输入是
additionalProperties=false的 closed object，直接放在工具的input字段中。只提交 freshinput_schema.properties中属于当前意图的字段；opaque locator 来自 inspect/receipt，不从标题或正文猜。相同语义重试复用request_id，operation、目标或输入变化时换新 ID。先检查
is_error；Execution 操作再按 operation 解读data.outcome：applied表示已应用；no_op无新增变更，结合 message 区分重放与 Plan Mode 校验；prepare 成功为prepared，草图提取为ready，版本选择为selected。rejected/superseded不能当成功。next_actions是建议，不授权，始终服从同一结果里的最新 lane、binding 和allowed_actions。
get_execution 只用 action=inspect，省略 operation/request_id，不走 invoke。Room 当前负责人自行 inspect 恢复协调权限，成员只获得观察。lane/background 不是界面模式；不要让用户切模式或再发“开始”。
context_status=refresh_required 时 inspect；round_refresh_required 结束旧轮。DM/Room 共用 Execution 但 session 独立；DM continuation 仅宿主 claim 后有 exact authority。
按当前动作读取参考
- 选择直接执行、Task、Subagent、Room 或 WorkGraph：references/structure-selection.md
- 派生、读取、等待、续聊或停止子智能体：references/subagents.md
- Plan 创建、替换、放弃或提交：references/graph-control.md
- assign、submit、review 或 takeover：references/responsibility-and-delivery.md
- 恢复、审计与 Goal 跨域收口：references/recovery-and-alignment.md
- 工作图查询、草图编辑与模板复用：references/workgraph-distillation.md
- Room/父子 Agent 的内容传递、并行与连续执行：references/communication-and-continuity.md
只完整读取当前决策需要的参考；不要为调用一个 operation 加载全部说明。
不变量
- 图 materialize 前不能 assign；持久责任先建 Work Item，再由最新 context 建 Assignment。裸
@只用于讨论或一次性帮助。 - observation 只授予读取共享图的可见性，不授予 coordination、WorkBinding、ReviewBinding、Submission 或 Plan mutation。
- Goal+WorkGraph 创建必须串行：先由
goal-manager创建 Goal 并取得 applied receipt，再用goal_binding=currentprepare Plan。已有 transient WorkGraph 后出现明确 Goal 意图时使用promote_execution_to_goal，不创建第二张图。 - required Work Item 的最终 accepted review 可以自动终止无 blocker Execution；确认绑定 Goal 时，再按 receipt 切到 Goal domain 执行
audit_objective_alignment与update_goal。execution/audit_execution_alignment只是非终态 Execution 的可选 Gate，不能替代 Goal 审计。 /workgraph只启用当前协作。模板查询、提取、编辑、版本选择与保存走 authoring 参考，已有 Draft 直接复用。修改后展示草图，不机械增加确认；保存须展示后的明确确认。UI 保存直接提交宿主事务，编辑结果不回传来源聊天。- mutation、分派和交付推进到真实结果、明确外部 blocker 或终态；不因 handoff 要求用户发送“继续”。
© nexus-research-lab, Apache-2.0. 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 7 other files (references) in skills/execution-orchestrator of nexus-research-lab/nexus.
- SKILL.md
- references/communication-and-continuity.md
- references/graph-control.md
- references/recovery-and-alignment.md
- references/responsibility-and-delivery.md
- references/structure-selection.md
- references/subagents.md
- references/workgraph-distillation.md
Open the folder on GitHubat commit e061bd6
Compare with similar skills
Execution Orchestrator 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 |
|---|---|---|---|---|---|---|
| Execution Orchestrator this skillnexus-research-lab/nexus | 150 | — | ~821 | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
- Official
Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
More from nexus-research-lab/nexus
All 17 skills in this repoImagegen
nexus-research-lab/nexus
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, UI mockups, product shots, or transparent-background…
Caixun Work Hours
nexus-research-lab/nexus
彩讯（RichPMS）工时填报助手：把当前会话、代码记录或用户口述整理成日报，按 8 小时分配，经用户确认后写入工时系统。用户提到“填日报、报工、补报、本周工时、日报被驳回”时使用。
Wechat Article Search
nexus-research-lab/nexus
搜索微信公众号文章，并整理标题、摘要、发布时间、来源公众号和链接。用户提到微信公众号、 公众号文章、微信文章、搜一批公众号资料、按关键词找公众号内容、查某公众号相关报道， 或需要为中文研究收集微信公众平台文章时使用；即使用户只说“搜微信里的文章”也应触发。
XLSX
nexus-research-lab/nexus
只要电子表格文件（.xlsx、.xlsm、旧版 .xls、.csv、.tsv）是任务的主要输入或输出，或者需要 被打开、读取、创建、修改，就使用本 Skill。也适用于公式、格式、图表、数据清洗和表格格式转换。
Automation
nexus-research-lab/nexus
通过宿主提供的 nexus.command 结构化工具查询、规划、确认并管理 scheduled task。用户要求提醒、延迟执行、周期检查、定时报表、补跑、结果重投递、持续关注、修改或删除任务、处理任务权限阻塞时使用；同时适用于定时任务后台 run 检查自身状态。
Goal Manager
nexus-research-lab/nexus
在当前 Nexus round 中创建、读取、明确纠正、审计、完成或阻塞 durable Goal。只处理用户或系统明确的跨轮目标生命周期；普通任务、提醒和执行图责任分别使用直接执行、Automation 或 Execution。
Related
Categories
Questions about Execution Orchestrator
What does Execution Orchestrator do?
选择执行结构、委派子智能体、管理 Nexus 工作图与可复用模板；遵守本轮权限，简单任务直接完成. An agent skill from nexus-research-lab/nexus. Execution Orchestrator is an agent skill from nexus-research-lab/nexus.
When should I use Execution Orchestrator?
Execution Orchestrator fits situations like: agent Workflows work in your project.
How do I install Execution Orchestrator in Claude Code?
Run `npx skills add nexus-research-lab/nexus --skill execution-orchestrator -a claude-code`. Or copy the skill folder (skills/execution-orchestrator in nexus-research-lab/nexus) into .claude/skills/execution-orchestrator in your project. Claude Code loads it when a task matches its description.
How do I install Execution Orchestrator in Codex?
Run `npx skills add nexus-research-lab/nexus --skill execution-orchestrator -a codex`. Or copy the skill folder (skills/execution-orchestrator in nexus-research-lab/nexus) into .agents/skills/execution-orchestrator in your project. Codex loads it when a task matches its description.
Can I use Execution Orchestrator 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 nexus-research-lab/nexus --skill execution-orchestrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/execution-orchestrator, .gemini/skills/execution-orchestrator, .github/skills/execution-orchestrator and .opencode/skills/execution-orchestrator in your project.
What does Execution Orchestrator need to run?
SKILL.md names no scripts, command-line tools or credentials: Execution Orchestrator is instructions for the agent only.
Does Execution Orchestrator access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Execution Orchestrator 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. Review the folder before installing.
What licence does Execution Orchestrator use?
Execution Orchestrator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Execution Orchestrator use?
About 821 tokens (SKILL.md is roughly 3.3k 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 12k tokens, read only when the agent opens those files.
What are the alternatives to Execution Orchestrator?
Skills that share tags, products or a category with Execution Orchestrator: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Execution Orchestrator?
nexus-research-lab (a GitHub organization) maintains it in nexus-research-lab/nexus, which has 150 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 7, 2026.
Source: nexus-research-lab/nexus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.