build-session
由 stevenartzt 提供
AI & LLMs简介
A framework for productive autonomous agent sessions.
描述
该技能的功能
A structured framework for autonomous agent sessions focused on shipping tangible outputs. It defines a five-step loop: quick context check, pick one task, do the work, log it, and commit. Includes named anti-patterns and session type variants for build, research, maintenance, and exploration modes.
Gives agents explicit anti-patterns and decision rules that prevent defaulting to narration, idle check-ins, or perfectionism when running unsupervised.
何时使用
- Running a scheduled cron agent without letting the session go idle
- Deciding what to work on when no urgent tasks are queued
- Keeping an unsupervised agent focused on a single deliverable per session
- Logging completed work and insights from autonomous agent runs
- Structuring low-priority agent time without forcing unnecessary productivity
示例工作流
User asks: Run a build session
- 1
Checks for urgent messages and unresolved blockers from the previous session
- 2
Selects one concrete task from the available categories: code, research, writing, exploration, or maintenance
- 3
Completes the task without excessive narration or scope creep
- 4
Writes a session log entry to memory with what was built and key insights
- 5
Runs git add, commit, and push if code was produced
A committed deliverable and a structured session log entry saved to the agent's memory system
安装
clawhub install stevenartzt/build-session运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。