菜单
Toy skill used by the hello-harbor example. Teaches an agent to answer a question by writing the value, wrapped in <answer></answer> tags, to the file the task names.
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/kernel/pi-skillopt --skill format-answer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。
Playbook for running a manual, end-to-end test of the pi-skillopt plugin in a real pi session — drive the skillopt-create / taskpack / finalize skills against an example, watch the loop progress, and analyze the run. Use when asked to "manually test skillopt", "smoke-test the plugin", "run a skillopt session and see how it goes", or to reproduce/verify a reported skillopt behavior. Repo-local dev tooling — not shipped to plugin users.
Set up and run a SkillOpt-style optimization loop for a single agent SKILL.md, scored by Harbor rollouts. Gathers the skill, the rollout environment (backend, agent, model, preloads), generates a task pack if none exists, then starts the loop. Use when asked to "optimize this skill", "skillopt this SKILL.md", "train my skill", or "improve my agent skill against evals".
Close out a skillopt run — measure the optimized skill on the held-out test split, produce best_skill.md, and emit a clean diff + report against the original skill. Use when a skillopt loop has plateaued or the user asks to "finalize", "wrap up the skillopt run", or "get the final number".
正在显示 SKILL.md
基于 SOC 职业分类
| name | format-answer |
| description | Toy skill used by the hello-harbor example. Teaches an agent to answer a question by writing the value, wrapped in <answer></answer> tags, to the file the task names. |
When a task asks you to answer a question or extract a value:
/app/answer.txt).<answer> and </answer> tags.<answer>...</answer> — the grader reads what is between the tags.