planning-with-files

仓库创建 2026年1月3日最近提交 2 天前SkillHot 收录 4 小时前
▸ 精选理由

让长期或多步骤任务在上下文丢失后可恢复,适合编码或研究型代理。

▸ 风险提示

会在磁盘写入持久文件,注意路径权限和敏感信息存储。

这个 Skill 做什么

用持久化 Markdown 文件在磁盘上保存任务计划、发现与进度,支持长期多步工作。

把任务计划、发现和进度用本地的 Markdown 文件(如 task_plan.md、findings.md、progress.md)持久化保存,让长期多步工作不会因会话清空而丢失。适合需要分多次调用工具、跨天或复杂的项目规划与执行(5+ 步骤)。特点是能自动恢复上下文、支持 /clear 后重启,把临时记忆搬到磁盘便于追踪与协作。

▸ 展开 SKILL.md 英文原文

Manus-style persistent file-based planning for AI coding agents: keeps task_plan.md, findings.md, and progress.md on disk so work survives context loss and /clear. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.

开发编程持久化记忆任务规划文件驱动通用
2.6w
Stars
2.2k
Forks
18
仓库内 Skill
+860
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/OthmanAdi/planning-with-files/master/.agents/skills/planning-with-files/SKILL.md
或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/OthmanAdi/planning-with-files/master/.agents/skills/planning-with-files/SKILL.md"
SKILL.MD 节选查看完整文件 ↗
# Planning with Files

Work like Manus: Use persistent markdown files as your "working memory on disk."

## FIRST: Restore Context (v2.2.0)

**Before doing anything else**, check if planning files exist and read them:

1. If `task_plan.md` exists, read `task_plan.md`, `progress.md`, and `findings.md` immediately.
2. Then check for unsynced context from a previous session:

```bash
# Linux/macOS — auto-detects skill directory (plugin env or default install path)
SKILL_DIR="${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/skills/planning-with-files}"
$(command -v python3 || command -v python) "${SKILL_DIR}/scripts/session-catchup.py" "$(pwd)"
```

```powershell
# Windows PowerShell
& (Get-Command python -E
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有