executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
context-memory-keeperManages persistent memory. Invoke to read active context or archive old tasks. Structure: Long-term Principles (Rules) + Short-term Workbench (Tasks).
Independent GitHub snapshot · Automated classification · Original documentation governs
paper-workflow-orchestrator 判断当前 S0-S8 阶段。python .agents/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --skill context-memory-keeper
[WORKFLOW FAIL] 或报告 status != "PASS",停止本 skill,按 paper_output/qa/workflow_guard_report.json 的失败项回补前置阶段,不得凭记忆继续。paper_output/ 产物;完成后必须回到 paper-workflow-orchestrator 判断下一步,并用 context-memory-keeper 记录已完成产物、阻塞项和下一步。python .agents/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --status
再读取 paper_output/qa/workflow_guard_report.json、paper_output/preflight_report.json、paper_output/input_manifest.json、paper_output/results/run_manifest.json 和本 skill 的上游 JSON 契约,按报告里的 recommended_skill 与 next_action 继续。paper_output/context/workflow_memory.json 视为长期断点记录;若其中的 current_step、next_step、recommended_skill 与 workflow_guard.py --status 不一致,以 guard 报告为准。paper-workflow-orchestrator 或运行 workflow_guard.py --status,再更新 workflow memory:
python .agents/skills/context-memory-keeper/scripts/update_workflow_memory.py
更新后读取 paper_output/context/workflow_memory.json / .md,确认下一步和推荐 skill 已记录。memoryskill.md;当短期工作台过长时,将旧任务摘要归档到 memory_archive.md。memoryskill.md,避免遗忘当前模型路线、数据来源和用户要求。paper-workflow-orchestrator 判断后续阶段。此 Skill 维护双层记忆结构,旨在解决模型上下文遗忘问题,同时保持上下文窗口的整洁。
workflow_guard.py --status or after a skill handoff, run:
python .agents/skills/context-memory-keeper/scripts/update_workflow_memory.py
paper_output/qa/workflow_guard_report.json plus key workflow artifacts and writes:
paper_output/context/workflow_memory.jsonpaper_output/context/workflow_memory.mdworkflow_memory.json before relying on chat history.memoryskill.md (Active Memory):
memory_archive.md (Archive):
memoryskill.md。memoryskill.md 的“短期工作台”。memoryskill.md 的“长期准则”。memory_archive.md,并在 memoryskill.md 中仅保留关键结论。memoryskill.md 超过 100 行 时,必须执行压缩。memory_archive.md。memory_archive.md 或直接删除。memoryskill.md 轻量(建议 < 100 行),以便随时快速读取。