Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

agentic-compass

bởi orosha-ai

AI & LLMs
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Local-only self-reflection that forces action for AI agents.

Mô tả

Kỹ năng này làm gì

Reads local memory files to score an AI agent across five objective axes and outputs a four-part action plan: one proactive task, one deferred item, one avoidance rule, and one concrete deliverable. All processing is local, no network calls are made.

Uses countable signals from memory files (done markers, error logs, correction counts) rather than subjective self-rating, so scores reflect actual behavior rather than agent bias.

Khi nào nên dùng

  • Auditing task completion rate after a long session
  • Catching repeated tool failures logged in memory files
  • Generating a proactive first task to run without a user prompt
  • Writing an avoidance rule to stop a recurring bad pattern
  • Scheduling a deferred job based on current memory state

Quy trình ví dụ

ĐẦU VÀO

User asks: What should I focus on this session?

AGENT
  1. 1

    Run agentic-compass.py to read daily and long-term memory files

  2. 2

    Score each axis by parsing markers and logs in those files

  3. 3

    Identify the weakest axis from the scored results

  4. 4

    Produce a four-part plan: proactive task, deferred item, avoidance rule, ship output

  5. 5

    Optionally write the plan to memory/agentic-compass.md with --write flag

ĐẦU RA

Score: 3.0/5. Weakest axis: Completion Rate. Plan includes drafting a specific implementation, retrying deferred cron jobs, avoiding a named API during peak hours, and creating a prioritization document.

Cài đặt

clawhub install orosha-ai/agentic-compass

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

Liên kết