본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

innovation-catalyst

autogame-17 제작

Notes & PKM
—아직 평가 없음
내 평가

요약

Analyzes system state (memory, tools, events) and generates strategic innovation proposals to break evolution.

설명

이 스킬이 하는 일

Analyzes an agent system's memory, tools, and recent events to detect evolution stagnation. When progress plateaus or tasks keep failing repeatedly, it generates actionable proposals such as new skills to acquire, optimizations to apply, or structural changes to make. Results are sent as a formatted Feishu card report.

Combines stall detection, gap analysis, and proposal generation in one automated step instead of requiring manual system audits between evolution cycles.

사용 시점

  • Detecting recurring task failures in an autonomous agent loop
  • Identifying skill category gaps when an agent stops improving
  • Generating new skill suggestions after a stable success plateau
  • Sending system health summaries to a Feishu team channel
  • Seeding the next evolution cycle with targeted proposals

예시 워크플로

입력

User asks: 'The agent hasn't made progress in several cycles, what should it do next?'

에이전트
  1. 1

    Reads MEMORY.md, TOOLS.md, and RECENT_EVENTS.md to assess current system state

  2. 2

    Identifies under-represented skill categories via gap analysis

  3. 3

    Detects blocked tasks or repeated failures using stall detection

  4. 4

    Generates actionable proposals: new skills, optimizations, structural changes

  5. 5

    Sends a rich card report to the specified Feishu user or group

출력

A Feishu card listing prioritized innovation proposals and detected stall points for the agent to act on in the next cycle

요구 사항

  • Feishu account with bot messaging permissions or webhook access
  • Feishu user or group ID (ou_xxx format) to target the report

설치

clawhub install autogame-17/innovation-catalyst

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크