ztl34245881-commits/dsh-task-planner ↗★ 2
dsh-task-planner
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall of past solutions + LLM-driven capability matching + auto-persisted lessons. Zero keys, zero hard-coded paths.
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。
インストール
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ztl34245881-commits/dsh-task-plannerドキュメント
README 全文を読む ↗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
plan_taskwrites a draft lesson (status: draft) automatically.- When the task closes, the agent updates it with the outcome (
status: verified). - A lesson reused successfully 3× → promote to a formal skill. A lesson rejected 2× → mark obsolete.