ztl34245881-commits/dsh-task-planner2

dsh-task-planner

具备经验肌肉记忆的 DeepSeek Harness 任务规划插件:支持历史方案条件反射式检索、LLM 驱动能力匹配与教训自动持久化

AI 分析

核心用途是在复杂任务开始前进行规划,并自动沉淀、复用历史经验。适合需要提升 Agent 复杂任务规划成功率和经验积累能力的场景。

包名
dsh-task-planner
版本
1.0.0
许可证
MIT
最近更新
2026年8月14日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ztl34245881-commits/dsh-task-planner

Usage

  • plan_task { task, goal?, constraints? } — plan before starting complex work.
  • task_memory save { task, plan, outcome } — persist a lesson (auto-called by plan_task for the draft).
  • task_memory recall { task } — condition-reflex lookup.
  • task_memory list — show all lessons.

Lesson lifecycle

  1. plan_task writes a draft lesson (status: draft) automatically.
  2. When the task closes, the agent updates it with the outcome (status: verified).
  3. A lesson reused successfully 3× → promote to a formal skill. A lesson rejected 2× → mark obsolete.