context-engineering

mvschwarz/openrig/packages/daemon/specs/agents/shared/skills/process/context-engineering

Use when designing, reviewing, or debugging how an agent's context window gets filled, pruned, or shared — choosing what loads at boot versus on demand, sizing an install or an always-loaded file, fixing an agent that drifts, repeats itself, or forgets constraints mid-task, planning compaction or summarization, deciding single-agent versus subagents, engineering handoffs between agents, or picking a tool loadout. NOT for rewording a prompt's tone, choosing which model to pin, or debugging business logic — those are adjacent moments this skill does not serve. Historical 2024–2025 snapshot; not normative for present-day frontier models — see the Status section.

把下面的话发给 Claude Code、Codex 或 Cursor。智能体会先检查内容，经你确认再安装。

请帮我安装这个 Agent Skill：https://github.com/mvschwarz/openrig/tree/main/packages/daemon/specs/agents/shared/skills/process/context-engineering

1. 先读取该目录下的 SKILL.md 和其他文件，检查是否有可疑内容（执行未知脚本、读取密钥、向外发送数据等），用中文告诉我它会做什么、需要哪些权限；
2. 等我确认后，再把整个目录安装到 ~/.claude/skills/context-engineering/（如果你不是 Claude Code，安装到你自己约定的 skills 目录）；
3. 安装后告诉我怎么触发它。

安装到个人 Skill 目录（对所有项目生效）。只想在当前项目用，改为 .claude/skills/。

git clone --depth 1 --filter=blob:none --sparse https://github.com/mvschwarz/openrig.git /tmp/context-engineering-src
cd /tmp/context-engineering-src && git sparse-checkout set "packages/daemon/specs/agents/shared/skills/process/context-engineering"
mkdir -p ~/.claude/skills && cp -r "packages/daemon/specs/agents/shared/skills/process/context-engineering" ~/.claude/skills/context-engineering

Skill 可以让智能体执行脚本。安装第三方 Skill 前务必看一遍内容，详见「安全」一课。

SKILL.md

在 GitHub 查看

正在从 GitHub 读取……