Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

build-session

bởi stevenartzt

AI & LLMs
1.1kLượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

A framework for productive autonomous agent sessions.

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

User asks: Run a build session

AGENT
  1. 1

    Checks for urgent messages and unresolved blockers from the previous session

  2. 2

    Selects one concrete task from the available categories: code, research, writing, exploration, or maintenance

  3. 3

    Completes the task without excessive narration or scope creep

  4. 4

    Writes a session log entry to memory with what was built and key insights

  5. 5

    Runs git add, commit, and push if code was produced

ĐẦU RA

A committed deliverable and a structured session log entry saved to the agent's memory system

Cài đặt

clawhub install stevenartzt/build-session

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết