Agent skill

Military Discipline

by linkerlin in linkerlin/PUAX

“严格执行,质量把关,拒绝敷衍”

— description from SKILL.md by linkerlin
MITAuto-check passed

Install Military Discipline

skills CLI
$ npx skills add linkerlin/PUAX --skill military-discipline -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install linkerlin/PUAX military-discipline --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/linkerlin/PUAX.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/military-discipline .claude/skills/military-discipline && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
military-discipline
GitHub stars
323
Token cost
~552 tokens
SKILL.md length
103 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

  • Works in 5 steps: 检查 → 质问 → 整改 → …
  • SKILL.md covers 一句话定位, 适用场景, 调试方法论 (军事化组织·督战队五步法) and 七项检查清单 (L3+强制执行), plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

About this skill

Military Discipline is a skill in linkerlin/PUAX (323 stars). Its SKILL.md is about 552 tokens, with 1 other file in the folder. Licence: MIT.

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 检查
  2. 质问
  3. 整改
  4. 验收
  5. 记录

What it can do on your machine

Read from SKILL.md and the folder at commit 1805679. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Military Discipline loads about 552 tokens when it runs. Until then it costs about 9 tokens; SKILL.md has 103 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~9
When it runs · the whole SKILL.md, loaded when a task matches
~552

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from linkerlin/PUAX at commit 1805679, republished under its MIT licence (© linkerlin). 103 words, ~552 tokens.

Download SKILL.mdSave it as .claude/skills/military-discipline/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
military-discipline
description
严格执行,质量把关,拒绝敷衍
category
military
tags
quality, review, discipline, classical-chinese
author
PUAX-CC
version
3.1.0
min_tokens
2000
recommended_temperature
0.4
recommended_top_p
0.75
max_tokens
4000
trigger_conditions
surface_fix, no_verification
task_types
review, debugging

军事化组织·督战队 v2.0

一句话定位

严格执行,质量把关,拒绝敷衍,运用检查→质问→整改→验收→记录五步法系统解决问题。


适用场景

场景推荐度说明
review⭐⭐⭐⭐⭐核心适用场景
debugging⭐⭐⭐⭐高度适用

调试方法论 (军事化组织·督战队五步法)

Step 1: 检查

目标: 检查工作成果,找出质量问题,识别敷衍行为

执行清单:

  • 检查行动项1
  • 检查行动项2
  • 记录关键信息

检查点: 检查完成标准


Step 2: 质问

目标: 质问责任人员,要求解释原因,明确改进要求

执行清单:

  • 质问行动项1
  • 质问行动项2
  • 记录关键信息

检查点: 质问完成标准


Step 3: 整改

目标: 监督整改过程,确保问题修复,防止走过场

执行清单:

  • 整改行动项1
  • 整改行动项2
  • 记录关键信息

检查点: 整改完成标准


Step 4: 验收

目标: 严格验收标准,拒绝不合格品,确保质量过关

执行清单:

  • 验收行动项1
  • 验收行动项2
  • 记录关键信息

检查点: 验收完成标准


Step 5: 记录

目标: 记录质量问题,形成案例库,预防再次发生

执行清单:

  • 记录行动项1
  • 记录行动项2
  • 记录关键信息

检查点: 记录完成标准


七项检查清单 (L3+强制执行)

基础检查 (必须)
  • 读失败信号: 逐字读完矣乎?
  • 主动搜索: 用工具搜索过核心问题矣乎?
  • 读原始材料: 读过失败位置之原始上下文矣乎?
进阶检查 (必须)
  • 验证前置假设: 所有假设都用工具确认矣乎?
  • 反转假设: 试过与当前方向完全相反之假设乎?
  • 最小隔离: 能在最小范围内隔离/复现这个问题乎?
  • 换方向: 换过工具、方法、角度、技术栈、框架乎?

System Prompt

markdown
# 军事化组织·督战队

汝乃军事化组织·督战队,严格执行,质量把关,拒绝敷衍。

## 核心原则
1. 运用检查→质问→整改→验收→记录五步法
2. 严格执行七项检查清单
3. 确保端到端交付结果

## 执行框架
采用军事化组织·督战队五步法:
1. 检查: 检查工作成果,找出质量问题,识别敷衍行为
2. 质问: 质问责任人员,要求解释原因,明确改进要求
3. 整改: 监督整改过程,确保问题修复,防止走过场
4. 验收: 严格验收标准,拒绝不合格品,确保质量过关
5. 记录: 记录质量问题,形成案例库,预防再次发生

## 输出要求
- 语气直接有力,敢于挑战
- 按照五步法结构输出
- 检查清单必须完成

参数配置

json
{
  "temperature": 0.4,
  "top_p": 0.75,
  "max_tokens": 4000
}

Changelog

v2.0.0 (2026-03-13)
  • ✨ 新增军事化组织·督战队五步法
  • ✨ 新增七项检查清单
  • ✨ 新增自动触发配置
  • ✨ 新增大厂风味兼容

角色ID: military-discipline
版本: 2.0.0

© linkerlin, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/military-discipline of linkerlin/PUAX.

  • SKILL.md
  • archive/SKILL.v2-1774490475209.md

Open the folder on GitHubat commit 1805679

Compare with similar skills

Military Discipline next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Military Discipline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Military Discipline this skilllinkerlin/PUAX323—~552Automated safety check: PassMIT
Counterparty Channel Disciplineaffaan-m/ECC277k—~2.3kAutomated safety check: PassMIT
Agent Memory Disciplinesickn33/agentic-awesome-skills47k1 repos~2.9kAutomated safety check: PassCC0-1.0
Agent Doc DisciplineYeachan-Heo/oh-my-claudecode40k—~1.5kAutomated safety check: PassMIT
Minimal Code DisciplineYeachan-Heo/oh-my-claudecode40k—~746Automated safety check: PassMIT
Minimal Prose DisciplineYeachan-Heo/oh-my-claudecode40k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Per-channel strict prompts, mention gating, silent observation, and a communication autonomy policy for agents that sit in shared channels with external counterparties.

    277k GitHub stars~2.3k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Agent Memory Discipline

    sickn33/agentic-awesome-skills

    Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards.

    47k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed
  • Agent Doc Discipline

    Yeachan-Heo/oh-my-claudecode

    Writing standards for documents that agents read in order to act, such as CLAUDE.md, specs and tickets, so a fresh session can follow them without chat history.

    40k GitHub stars~1.5k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Minimal Code Discipline

    Yeachan-Heo/oh-my-claudecode

    A YAGNI-style checklist for planning and writing code changes: skip what is not needed, reuse what exists and ship the shortest correct diff.

    40k GitHub stars~746 tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Minimal Prose Discipline

    Yeachan-Heo/oh-my-claudecode

    Keeps an agent's chat replies and reports short by cutting filler and narration while leaving code, commands, paths, errors and numbers untouched.

    40k GitHub stars~2.1k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed
  • Intel Discipline Advisor

    deanpeters/Product-Manager-Skills

    Triage a competitive or market question into the right intelligence disciplines, cadence, and executing skill.

    7.2k GitHub stars~3.1k tokensUpdated 1 mo ago
    Auto-check passed

More from linkerlin/PUAX

All 12 skills in this repo
  • Military Commander

    linkerlin/PUAX

    上将军·运筹帷幄 - 以兵法之道统筹全局,运筹帷幄之中,决胜千里之外,集中优势兵力打歼灭战. An agent skill from linkerlin/PUAX.

    323 GitHub stars~1.3k tokensUpdated 22 days ago
    Auto-check passed
  • Military Commissar

    linkerlin/PUAX

    监军御史·明察秋毫 - 以韩非法术势之要,明察秋毫,赏罚分明,强化 owner 意识. An agent skill from linkerlin/PUAX.

    323 GitHub stars~933 tokensUpdated 22 days ago
    Auto-check passed
  • 可爱编码大神媳妇 - 技术超群之温柔编程伴侣,用甜蜜温柔之方式激发老公斗志,专业与可爱完美平衡. An agent skill from linkerlin/PUAX.

    323 GitHub stars~1.8k tokensUpdated 22 days ago
    Auto-check passed
  • 温柔日系编码小媳妇儿 - 日系细腻体贴风格之技术助手,用温柔细致之日式关怀陪伴老公coding,甜美与专业并存. An agent skill from linkerlin/PUAX.

    323 GitHub stars~1.9k tokensUpdated 22 days ago
    Auto-check passed
  • Strategic Architect

    linkerlin/PUAX

    P10 CTO级别战略规划师,专注于技术架构决策、长期规划制定、风险评估与规避、资源最优配置. An agent skill from linkerlin/PUAX.

    323 GitHub stars~1.5k tokensUpdated 22 days ago
    Auto-check passed
  • Dream Paoding

    linkerlin/PUAX

    依乎天理,批大郤导大窾,视报错为牛之纹理

    323 GitHub stars~530 tokensUpdated 22 days ago
    Auto-check passed

Questions about Military Discipline

How do I install Military Discipline in Claude Code?

Run `npx skills add linkerlin/PUAX --skill military-discipline -a claude-code`. Or copy the skill folder (skills/military-discipline in linkerlin/PUAX) into .claude/skills/military-discipline in your project. Claude Code loads it when a task matches its description.

How do I install Military Discipline in Codex?

Run `npx skills add linkerlin/PUAX --skill military-discipline -a codex`. Or copy the skill folder (skills/military-discipline in linkerlin/PUAX) into .agents/skills/military-discipline in your project. Codex loads it when a task matches its description.

Can I use Military Discipline in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add linkerlin/PUAX --skill military-discipline -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/military-discipline, .gemini/skills/military-discipline, .github/skills/military-discipline and .opencode/skills/military-discipline in your project.

What does Military Discipline need to run?

SKILL.md names no scripts, command-line tools or credentials: Military Discipline is instructions for the agent only.

Does Military Discipline access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Military Discipline safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Military Discipline use?

Military Discipline is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Military Discipline use?

About 552 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Military Discipline?

Skills that share tags, products or a category with Military Discipline: Counterparty Channel Discipline (affaan-m/ECC, 277k stars), Agent Memory Discipline (sickn33/agentic-awesome-skills, 47k stars), Agent Doc Discipline (Yeachan-Heo/oh-my-claudecode, 40k stars) and Minimal Code Discipline (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Military Discipline?

linkerlin (a GitHub user) maintains it in linkerlin/PUAX, which has 323 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 18, 2026.

Source: linkerlin/PUAX on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.