Keeps task_plan.md, findings.md and progress.md on disk so an agent's multi-step work survives /clear, compaction and context loss.
Keeps task_plan.md, findings.md and progress.md on disk so an agent never loses its goal or progress across long, multi-step work.
Gives Claude persistent on-disk working memory — task_plan.md, findings.md, progress.md — so long multi-step work survives context loss and compaction.
Turns complex work into three persistent markdown files — task_plan.md, findings.md, progress.md — so the agent plans, logs, and recovers context reliably.
Keeps task_plan.md, findings.md, and progress.md on disk so the agent never loses its goal or progress across long, multi-step work.
Keeps task_plan.md, findings.md and progress.md on disk so an AI agent never loses its goal or progress across long, multi-step work.
Keeps task_plan.md, findings.md and progress.md on disk so multi-step work survives /clear, compaction and context loss.
Turns complex multi-step work into three persistent Markdown files — task_plan.md, findings.md, progress.md — so context survives compaction and /clear.
A Manus-style planning skill that tracks complex work in task_plan.md, findings.md and progress.md, and restores context automatically after a cleared session.
A Manus-style planning skill that breaks complex work into task_plan.md, findings.md, and progress.md, and restores context automatically after /clear.
Manus-style persistent planning that keeps task_plan.md, findings.md, and progress.md on disk so multi-step work survives context loss and /clear.
Keeps task_plan.md, findings.md, and progress.md on disk so multi-step work survives /clear, compaction, and session breaks.
A Manus-style workflow that keeps task_plan.md, findings.md and progress.md on disk as durable working memory for multi-step tasks, with Arabic-language instructions.
Manus-style planning that keeps task_plan.md, findings.md, and progress.md on disk so multi-step work survives /clear and context compaction.
A German-language planning skill that breaks complex work into task_plan.md, findings.md and progress.md, and restores context automatically after a session is cleared.
Keeps plans, findings, and progress in markdown files so long multi-step tasks survive context loss and session gaps.
Distills chat logs, docs, and public material about a colleague, relationship, or celebrity into reusable Person Profile skills for agents.
Clusters a GitHub issue backlog by root cause into a handful of plan-master issues plus design docs, then bundles PRs that close each cluster atomically.
Operate Gemini Notebook (NotebookLM) end to end via the notebooklm-py CLI or typed async Python API — auth, sources, grounded chat, research, and artifact generation.