菜单
Design dense, task-relevant context for AI agents instead of stuffing everything into prompts. Use when building agent harnesses, selecting context, reducing prompt bloat, stage-gating workflows, structuring markdown/frontmatter data, or debugging context quality.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/Wolverine971/buildos-platform --skill context-engineering-for-agent-work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。
Query and manage the BuildOS Supabase database. Use for debugging data issues, checking users, LLM usage, queue jobs, schema questions, or admin database operations with safety checks.
Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and expo-haptics. Use when animating anything in an Expo app, adding gestures, sheets, screen transitions, press feedback or haptics, or fixing motion that stutters on device. For web animation use `animate`.
Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Writes the implementation. Use when asked to animate something, add motion, make a component feel alive, or build a transition. For critiquing existing motion use review-animations; for auditing a whole codebase use improve-animations.
基于 SOC 职业分类
正在显示 SKILL.md
| skill_id | context-engineering-for-agent-work |
| name | Context Engineering For Agent Work |
| description | Design dense, task-relevant context for AI agents instead of stuffing everything into prompts. Use when building agent harnesses, selecting context, reducing prompt bloat, stage-gating workflows, structuring markdown/frontmatter data, or debugging context quality. |
| skill_type | combo |
| categories | ["technology-and-agent-systems"] |
| path | docs/research/youtube-library/skill-drafts/context-engineering-for-agent-work/SKILL.md |
| status | registered |
| promoted_to | apps/web/src/lib/services/agentic-chat/tools/skills/definitions/context_engineering_for_agent_work/SKILL.md |
| last_promoted | 2026-06-10 |
Use this skill when an agent needs to decide what context to load, how to structure it, and how to keep an AI workflow reliable. Context engineering is not "more tokens." It is higher information density, deterministic selection, and explicit workflow control.
Do not use this skill when the problem is deterministic code behavior unrelated to LLM context.
Use explicit stages when the work has known steps:
Do not put all seven steps in a paragraph and hope the model remembers. Make transitions visible. Require verification before final reporting when the task changes files, data, or user-facing behavior.
Use markdown bodies for human-readable notes and YAML frontmatter for deterministic filtering.
Good frontmatter fields:
titletypestatusownersourcetagsdateprojectentitiesnext_actionUse frontmatter to answer "which files matter?" before the model reads the bodies.
Audit long prompts when:
For each instruction, ask:
Delete or move low-signal instructions into retrievable references.
Return:
Distilled from Chroma's Context Engineering Episode 1 with Dex Horthy and the existing BuildOS advanced-guide article Debug the Harness, Not the Model, based on Cat Wu's Lenny's Podcast interview.