用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/nearai/ironclaw --skill new-project命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Use when adding or changing a Reborn integration — a new extension, a channel surface, model-callable tools, or a shared auth provider — or when deciding whether something is "a channel", "an extension", or "a tool". Maps the unified extension model (NEA-25) to the exact manifest sections, crates, seams, and tests.
Use when creating or editing agent guidance in this repo — anything under .claude/ (skills, commands, rules), AGENTS.md or CLAUDE.md files, or the runtime skills/ directory — or when guidance is found citing files, branches, or checks that no longer exist.
Use when adding or reviewing tests for Reborn behavior — choosing a test tier, covering a bug fix, testing model/tool-choice behavior, touching tests/integration or tests/fixtures/llm_traces, or when a test needs Postgres, Docker, or a live LLM.
基于 SOC 职业分类
正在显示 SKILL.md
| name | new-project |
| version | 0.2.0 |
| description | Create and structure a new autonomous project — "/new-project <what project does>" |
| activation | {"keywords":["project","create project","new project","set up project","autonomous workspace","campaign","department","company project"],"patterns":["create a (new )?project","set up.*project","organize.*into.*project","new.project","/new.project"],"tags":["project-management","organization","goals"],"max_context_tokens":2000} |
Create an autonomous project workspace using memory_write and mission_create.
Given the user's description of what the project does, derive a short slug (lowercase, hyphens, e.g. ai-research). Then execute these steps sequentially (one tool call at a time — do NOT batch calls that depend on each other):
memory_write(target: "projects/{slug}/AGENTS.md", content: "# {Project Name}\n\n{What the agent should know about this project: domain, stakeholders, priorities, constraints, tools/APIs to use.}")
This file is loaded into the system prompt for every mission in this project. Make it specific and actionable.
memory_write(target: "projects/{slug}/context.md", content: "# {Project Name} — Context\n\n## Overview\n{What the project is and why it exists.}\n\n## Current State\n{What is known so far.}")
memory_write(target: "projects/{slug}/goals.md", content: "# Goals\n\n- Goal 1\n- Goal 2\n...")
Include measurable targets when possible. If the project would benefit from tracked metrics, add a metrics section:
## Metrics
| Metric | Unit | Target | How to measure |
|--------|------|--------|----------------|
| {name} | {unit} | {target} | {evaluation instruction — tell the agent HOW to check this: API call, file to read, command to run} |
Create recurring missions scoped to the project. Use the project name or slug as project_id (the engine resolves it to the correct project):
mission_create(name: "...", goal: "...", cadence: "daily", project_id: "{Project Name}")
Choose appropriate cadences: hourly, daily, weekly, monthly, or cron expressions like 0 9 * * 1-5.
projects/
{slug}/
AGENTS.md # Agent instructions (loaded into system prompt)
context.md # Background knowledge, current state
goals.md # Goal breakdown with optional metrics
research/ # Research and analysis outputs
reports/ # Generated reports
project_id when creating missions. Without it, missions land in the Default project.