一键导入
agent-optimize
Optimize a document for AI agent consumption. Restructures prose into formats that agents parse efficiently while preserving meaning.
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。
菜单
Optimize a document for AI agent consumption. Restructures prose into formats that agents parse efficiently while preserving meaning.
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。
基于 SOC 职业分类
Scaffolds a Docker "sandbox" harness into a repo so Claude Code can run in `--dangerously-skip-permissions` (YOLO) mode inside an Ubuntu container, with the project bind-mounted at /workspace and the host's ~/.claude bind-mounted for auth and session continuity. Use when the developer wants an isolated filesystem for agent writes but still wants host-visible builds, logs, and session history.
Record agent activity during Claude Code sessions. Captures plans, human input, agent decisions, and deviations via hooks and agent self-reporting.
Template-based code generation pattern using data models, templates, and helper functions to generate repetitive interface code.
Test accountability policy. All failures belong to the current changeset. Commits must include test results. No failures on main.
Reviews a SKILL.md file or skill directory for quality, correctness, and alignment with Claude Code skill conventions. Use when you've written a new skill and want to check it before committing, or when evaluating an existing skill for improvements.
Helps with things
| name | agent-optimize |
| description | Optimize a document for AI agent consumption. Restructures prose into formats that agents parse efficiently while preserving meaning. |
| argument-hint | <file|folder>... |
Optimize the target document(s) at $ARGUMENTS for agent consumption.
Stop after each stage and have changes reviewed with user.
Note: The goal is agent efficiency, not stripping all prose. Some content is genuinely better as narrative — context-setting introductions, nuanced trade-offs, philosophy notes. Optimize the structure agents need to parse; preserve the prose humans need to understand intent.
Read and assess the document (developer confirms)
Replace verbose prose with structured formats (agent leads with approval)
Compress token usage (agent leads with approval)
Make relationships explicit (agent leads with approval)
This skill sits at the end of the composition pipeline: flesh-out -> review-steps -> strong-edit -> agent-optimize. Run it after the content is complete and reviewed — it restructures for consumption, not correctness.
| Goal | Use |
|---|---|
| Raw notes need structure and expansion | flesh-out |
| Draft needs polish and consistency | review-steps |
| Complete draft needs critical evaluation | strong-edit |
| Finalized document needs agent-friendly restructuring | agent-optimize |