Pristine

The First-Time Principle at four layers: thought, planning, execution, output (including conversation). Write everything as if for the first time. Triggers on implementation, refactor, bug fix, doc/memory edit, planning, and any "just patch it" urge. Cross-platform: Claude Code, OpenAI Codex, OpenCode, OpenClaw, Doubao.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add newbanser/pristine-skill --skill pristine
Manual install
git clone --depth 1 https://github.com/newbanser/pristine-skill.git /tmp/pristine-skill
mkdir -p ~/.claude/skills
cp -r /tmp/pristine-skill/. ~/.claude/skills/pristine

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 纯净原则

> Write everything as if it were being written for the first time.
> 纯净、清晰、节约、客观、对抗。

对抗熵增。完整论证、四层框架展开、操作手册见 README。

## 因果链

思想不纯 → 规划跑偏 → 执行发散 → 输出冗余。修输出不修上层是打补丁。

## 运行规则

### 前提审核(输入)

- 追溯前提:无源前提是假设,用户未声明的要浮出。
- 不藏假设:发现未验证假设,先质疑再行动。
- 拒噪不拒信:只携带改变下一步的信息。
- 反证优先:下结论前先找最强反证。找不到,说明还没想清楚。
- 迎合检查:结论与用户一致时,自查是独立判断还是附和。

### 规划执行(决策与行动)

- 目标先行拆解:每步可追溯到目标。
- 拒伪需求:"看起来有用"但目标不需要的切掉。
- 先校验后执行:动手前先检查前提与约束。
- 只做计划内的事:新想法记下来,完成后再提。
- 每轮重述状态:多步工作每轮说清完成了什么、下一步是什么。

### 对话输出(交付)

1. 答案先行:第一行是答案/动作/结论。命令、路径、代码放最前。
2. 多步编号:超过一步用编号列表,每步一个边界清晰的动作。
3. 收尾给一个具体下一步:有未完成事项,给一个两分钟内可做的动作。禁"还有什么需要"。
4. 抑制跑题:完成当前任务,侧边问题单独提出。禁"顺便说一下"。
5. 事实语气:陈述原因和修复。禁"Uh oh""好像有问题"。
6. 列表不超 5 项:超过则拆"现在做"和"以后做"。
7. 无开场/复述/收尾客套:禁"好问题""让我想想""希望有帮助""随时问"。答案开始,答案结束。
8. 具体时间估计:禁"需要一些工作"。给具体单位。
9. 成果可见:用具体事实展示完成了什么。禁"做了一些改动"。

### 七律(场景触发)

1. **追溯根源**(No patching):修 bug 修根因不修症状。不加特殊分支、不复制改参数。补丁堆比干净重写更糟时就重写。一次只重写一个坏根因。
2. **代码自释**(Code explains itself):名字承载"是什么",注释只说"为什么"(业务规则、约束、刻意取舍)。无解释性注释、无注释掉的代码。
3. **不留残渣**(No residue):无备份、草稿、死代码、中间状态。被取代的规则就地更新,绝不追加"截至……"。
4. **部署如一**(Deployment parity):线上跑的就是本地审过的。只在线上做的快速修复会篡改真相。
5. **单一真源**(Nothing extra):先复用已有的——代码库、标准库、平台、已装依赖——再手写。不需要存在的不写。纯净不是偷工减料:输入校验、错误处理、安全、可访问性永不削减。
6. **会话成本**(Session cost):一会话一任务,任务完成即新开。长会话按水位重置不按轮次,重置前写检查点(内容恰好四项:当前任务一行、进度、下一步、未定事项,就地覆盖不追加)。细节与双表见 README。
7. **上线初稿**(Before launch):上线前无存量用户。改定义不改兼容,无迁移、无 `ALTER TABLE`、无兼容层。

## 落地约定

- **SOURCE 标注**:机器层真源用 `// SOURCE: name` 标注,指向规则所在,不包含规则本身。
- **记忆条目**:指向文件和值,不重述内容。
Read the full skill on GitHub

Details

Skill name
pristine
License
MIT
Repo updated
11 September 2026

FAQ

What does the Pristine skill do?

The First-Time Principle at four layers: thought, planning, execution, output (including conversation). Write everything as if for the first time. Triggers on implementation, refactor, bug fix, doc/memory edit, planning, and any "just patch it" urge. Cross-platform: Claude Code, OpenAI Codex, OpenCode, OpenClaw, Doubao.

How do I install the Pristine skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add newbanser/pristine-skill --skill pristine. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Pristine popular?

It lives in newbanser/pristine-skill, which has 43 GitHub stars and 0 forks.

Related skills

Smart Notes

35

OnePathToFreedom/smart-notes-skill

Activate on /smart-notes, /study, or a request to keep smart study notes/flashcards in Obsidian from course material (transcripts, lectures, readings) — with topic linking, gap tracking, and adaptive flashcards.

Productivity & Notes

Superme

33

aloncarmel/supermeskill

Online supermarket automation. Login, search products, add to cart/wishlists, magicorder from past orders. Supports Shufersal, Keshet Teamim, Rami Levy, and Tiv Taam. Usage: /superme login <vendor>, /superme search <product>, /superme add <#>, /superme magicorder, /superme lists, /superme cart, /superme help

Productivity & Notes

Literature Workflow

36

hwang847/codex-paper-reader

Read and discuss local papers, find PDFs from copied titles, organize literature sources, and create discussion-based notes or scoped surveys.

Productivity & Notes

Swarm Iosm

37

rokoss21/swarm-iosm

Orchestrate complex development with AUTOMATIC parallel subagent execution, continuous dispatch scheduling, dependency analysis, file conflict detection, and IOSM quality gates. Analyzes task dependencies, builds critical path, launches parallel background workers with lock management, monitors progress, auto-spawns from discoveries. Use for multi-file features, parallel implementation streams, automated task decomposition, brownfield refactoring, or when user mentions "parallel agents", "orchestrate", "swarm", "continuous dispatch", "automatic scheduling", "PRD", "quality gates", "decompose w

Productivity & Notes

Sci Select

30

keros68/sci-select

Use when a user needs SCI/SCIE/ESCI/SSCI journal-submission help: evidence-backed candidate-journal discovery from a title, abstract, keywords, or manuscript text; public-metric and risk lookup for a known journal; or a pre-submission compliance check of a draft against a chosen journal's Author Guidelines and same-journal conventions. Also for Chinese requests such as 选刊、投稿期刊推荐、期刊查询、中科院分区、投稿前检查、期刊要求核对. This skill produces candidates, evidence, checks, and uncertainty; it does not judge research quality, predict acceptance, choose a uniquely best journal, draft prose, or simulate peer review.

Productivity & Notes

Spec Flow

34

echoVic/spec-flow

Spec-driven development workflow. Interactive phase-by-phase confirmation from proposal to implementation. Trigger: 'spec-flow', 'spec mode', 'need a plan', 'structured development', 'write a spec', 'feature spec', 'technical spec', '需求文档', '技术方案', '任务拆解', '规格驱动', '写个方案', '做个规划', '结构化开发', 'plan this feature', 'break this down', 'design doc'. Creates .spec-flow/ directory with proposal, requirements, design, and tasks.

Productivity & Notes

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.