Skip to content

Planning with Files (Chinese)

Gives an AI agent persistent Markdown plan files on disk to track multi-step work in Chinese.

Stars
27,822
Licence
MIT
Files
15 files

What it does

When installed, the agent keeps a written plan, research notes and a progress log as Markdown files in your project folder, instead of relying only on its short-term memory. Lifecycle hooks inject the selected project plan into the agent's context and can check whether phases are marked complete before the agent stops. The skill's text and templates are in Chinese.

Great for

  • Developers running long, multi-step coding or research tasks with an AI agent who want progress recorded on disk
  • Users who want a Chinese-language version of the planning workflow
  • Teams that need separate plan folders per task when running several agents in parallel

Skip it if

  • Simple one-off questions or tasks needing fewer than about five tool calls, where the overhead is not worth it
  • Environments where you cannot review hook scripts, since the hooks run shell commands automatically on agent events
  • Sensitive projects where plan files should not sit in the repository, since plans are written into the project folder

Try asking

  • “帮我规划一个数据迁移项目,分解成多个阶段并记录进度”
  • “制定一个多步骤的研究计划,并把发现保存到文件中”
  • “恢复上次未完成的任务,先读取当前计划再继续”
  • “拆解这个功能开发项目并跟踪每个阶段的状态”
Step-by-step guide: how to use Planning with Files (Chinese)Install, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    planning-with-files-zh.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip planning-with-files-zh.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip planning-with-files-zh.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Create one plan folder per task and pin it with PLAN_ID so parallel agents do not overwrite each other's plans
  • Run the provided check-complete validation after creating a plan to confirm each phase has exactly one status line
  • Review the hook commands in SKILL.md before installing, since they execute automatically on prompt, tool use and stop events

What's inside

  • plan-inventory.md
  • scripts/attest-plan.sh
  • scripts/check-complete.sh
  • scripts/gate-stop.sh
  • scripts/init-session.sh
  • scripts/ledger-append.sh
  • scripts/ledger-summary.sh
  • scripts/phase-status.sh
  • scripts/plan-doctor.sh
  • scripts/resolve-plan-dir.sh
  • scripts/session-catchup.py
  • scripts/set-active-plan.sh
  • scripts/skill-hook.sh
  • SKILL.md
  • templates/findings.md

Redistributed unmodified from OthmanAdi/planning-with-files under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.