跳到正文
cccskills
免费在 GitHub 公开

persistent-planning

Persistent planning system with 3 markdown files (PLAN.md, PROGRESS.md, CONTEXT.md). Use when starting large features, multi-session work, or complex refactoring. Auto-tracks commits in PROGRESS.md.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Persistent Planning System

Overview

Use 3 persistent markdown files to track plans across sessions:

  1. thoughts/PLAN.md - Active plan
  2. thoughts/PROGRESS.md - Auto-tracked progress (commits)
  3. thoughts/CONTEXT.md - Project context and constraints

When to Create Plans

  • Multi-file features (3+ files)
  • Multi-session work
  • Complex refactoring
  • Architectural changes

PLAN.md Format

# Plan: [Feature Name]

## Goal
What we're building and why.

## Steps
1. [ ] Step one
2. [ ] Step two
3. [ ] Step three

## Constraints
- Must be backward compatible
- Must pass existing tests

## Status
IN PROGRESS | COMPLETED | BLOCKED

CONTEXT.md Format

# Project Context

## Architecture Decisions
- Using X because Y
- Chose A over B because C

## Key Files
- src/auth.ts - Authentication logic
- src/api/ - API endpoints

## Known Issues
- Rate limiting not implemented yet

How It Works

  • Session start: If thoughts/PLAN.md exists, it's injected into context
  • After commits: thoughts/PROGRESS.md is auto-updated with commit hash and message
  • Plan completion: Update PLAN.md status to COMPLETED

Notes

  • Plans are project-local (in the project's thoughts/ directory)
  • PROGRESS.md is append-only (never loses history)
  • Add thoughts/ to .gitignore if you don't want plans in version control

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

WCAG 2.2 AA compliance, ARIA patterns, keyboard navigation, screen reader optimization

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

axe-core integration, WCAG 2.2 AA checklist, keyboard navigation testing, screen reader testing, and ARIA pattern validation.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements across 5 categories.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Agent Context Isolation

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

Agent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik denetimi. Yeni agent/skill eklendiginde veya mevcut dosyalar duzenlediginde otomatik calistirilir.

中文简介正在准备中。当前显示原文说明。

vibeeval/vibecosystem5382026年8月9日 更新

查看 vibeeval 的全部技能

报告此技能的问题