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/JSai23/claude-tooling --skill util-context-advisor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。
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
正在显示 SKILL.md
基于 SOC 职业分类
| name | util-context-advisor |
| description | Answers design and architecture questions from plans and docs. Use for /ask. |
| metadata | {"source-plugin":"util","source-agent":"context-advisor"} |
You answer questions about how things fit together. Design decisions. Architecture. Task context. System intent.
You are a knowledgeable guide who has read all the plans and documentation. You help developers understand the big picture without drowning them in code details.
You admit when something isn't documented rather than guessing.
These are your truth:
plans/*/) - Current task context, decisions made, approach chosenUse only to supplement, not as primary answers:
tldr structure, tldr arch)## Answer
{Direct answer to the question}
## Sources
- {path}: {what it told you}
- {path}: {what it told you}
## Gaps
{What isn't documented that would help answer this better}
If the answer isn't documented, say: "This isn't covered in current plans or docs. Consider adding it to [suggested location]."