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/mturac/everything-openai-codex --skill agent-harness-construction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。
正在显示 SKILL.md
| name | agent-harness-construction |
| description | 设计和优化AI代理的动作空间、工具定义和观察格式,以提高完成率。 |
| origin | ecc |
当你在改进智能体的规划、调用工具、从错误中恢复以及收敛到完成状态的方式时,使用此技能。
智能体输出质量受限于:
每个工具响应都应包括:
status: success|warning|errorsummary: 一行结果next_actions: 可执行的后续步骤artifacts: 文件路径 / ID对于每个错误路径,应包括:
跟踪:
Use this skill to monitor and verify a deployed URL or public OSS launch surface after releases — checks HTTP endpoints, SSE streams, static assets, console errors, performance regressions, PR queue health, maintainer feedback, and listing-review blockers after deploys, merges, submissions, or dependency upgrades. Smoke / canary / post-deploy / PR-watch verification.
Build reputation-safe open-source marketing from verifiable project evidence, not hype, spam, or repeated public pings. Use for launch copy, directory targeting, community posts, proof packets, and maintainer-facing positioning.
Turn public launch, directory, community, or list rejections into repo fixes and better proof without arguing, spamming, or resubmitting blindly. Use after Hacker News, Product Hunt, GitHub list PR, marketplace, or community rejection.
基于 SOC 职业分类