Agent skill

Agents Md Creator

by Philip-Cao-9527 in Philip-Cao-9527/code-note-helper

基于项目真实背景、用户长期偏好和现有文档生成或更新项目级 AGENTS.md。用于新项目初始化、迁移协作规则、整理语言编码测试版本文档约束、沉淀长期协作底线和交付格式时使用。

MITAuto-check passedAgent Workflows

Install Agents Md Creator

skills CLI
$ npx skills add Philip-Cao-9527/code-note-helper --skill agents-md-creator -a claude-code

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

GitHub CLI
$ gh skill install Philip-Cao-9527/code-note-helper agents-md-creator --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/Philip-Cao-9527/code-note-helper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vibe-coding-template/skills/agents-md-creator .claude/skills/agents-md-creator && 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
agents-md-creator
GitHub stars
273
Token cost
~581 tokens
SKILL.md length
105 words
Files
4 (incl. scripts, references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

基于项目真实背景、用户长期偏好和现有文档生成或更新项目级 AGENTS.md。用于新项目初始化、迁移协作规则、整理语言编码测试版本文档约束、沉淀长期协作底线和交付格式时使用。

  • Works in 6 steps: 先确认目标项目路径、项目类型、主要操作系统、默认… → 读取目标项目的最小真实上下文 → 读取 references/agents-template.md,按目标项目事实裁剪 → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers 技能定位, 使用流程, 输出要求 and 质量标准, plus 1 more section
  • Runs Python scripts from its folder; calls python

What it does

Agents Md Creator is an agent skill from Philip-Cao-9527/code-note-helper. 基于项目真实背景、用户长期偏好和现有文档生成或更新项目级 AGENTS.md。用于新项目初始化、迁移协作规则、整理语言编码测试版本文档约束、沉淀长期协作底线和交付格式时使用。

Its SKILL.md is about 580 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/agents-template.md` and `scripts/validate_agents_md.py`).

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: 一个专为算法刷题、深度学习和 AI 学习场景打造的浏览器扩展。拒绝机械的复制粘贴,帮你自动化生成高质量复盘笔记、内置遗忘曲线驱动的间隔复习、轻松驾驭超长对话,让刷过的每一道题都成为真正的技术资产!. The licence is MIT.

When your agent uses it

  • Tasks that involve Agent instruction files

Example prompts

  • “/agents-md-creator”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 先确认目标项目路径、项目类型、主要操作系统、默认 shell、用户希望长期生效的规则范围。
  2. 读取目标项目的最小真实上下文
  3. 读取 references/agents-template.md,按目标项目事实裁剪
  4. 明确区分三类内容
  5. 如果旧规则与目标项目事实冲突,以目标项目当前文件和用户最新决策为准。
  6. 生成或改写 AGENTS.md 后,运行专项校验脚本

What it can do on your machine

Read from SKILL.md and the folder at commit 7421249. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Agents Md Creator loads about 581 tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 26 tokens; SKILL.md has 105 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~581
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.9k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Philip-Cao-9527/code-note-helper at commit 7421249, republished under its MIT licence (© Philip-Cao-9527). 105 words, ~581 tokens.

Download SKILL.mdSave it as .claude/skills/agents-md-creator/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
agents-md-creator
description
基于项目真实背景、用户长期偏好和现有文档生成或更新项目级 AGENTS.md。用于新项目初始化、迁移协作规则、整理语言编码测试版本文档约束、沉淀长期协作底线和交付格式时使用。

agents-md-creator

技能定位

生成项目级 AGENTS.md。这个 skill 只负责把长期协作规则整理成项目可执行约束,不负责实现业务功能,也不把某个旧项目的规则原样套到新项目。

AGENTS.md 应该回答:这个项目里 Agent 开始工作前必须知道什么、什么不能做、怎么验证、怎么汇报、什么时候升版或写报告。它不是一次性任务 prompt,也不是某个项目私有规则的复制品。

使用流程

  1. 先确认目标项目路径、项目类型、主要操作系统、默认 shell、用户希望长期生效的规则范围。
  2. 读取目标项目的最小真实上下文:
    • 已存在的 AGENTS.md、AGENTS.override.md、.codex/AGENTS.md 或同类项目规则文件。
    • README.md、开发日志、贡献指南、测试说明、发布说明、变更记录。
    • 与项目形态直接相关的入口文件、配置文件、脚本清单和包管理文件。
    • 用户提供的参考项目规则或 skill,只学习组织方式和边界表达,不复制私有路径、模块名、版本号或测试命令。
  3. 读取 references/agents-template.md,按目标项目事实裁剪:
    • 保留通用底线:语言、编码、证据、测试、版本、报告、错误处理、输出格式。
    • 用 {{...}} 占位符或目标项目真实值替换模板变量。
    • 按 {{项目类型}} 和 {{风险域}} 启用项目专项段落,不适用就删除。专项段落可以参考 UI、数据、服务、模型、构建、部署、文档模板等场景,但不能写成所有项目默认规则。
  4. 明确区分三类内容:
    • 长期底线:不把未验证写成已验证、不吞异常、不做无关重构、先读真实调用链。
    • 项目事实:真实目录、真实命令、真实版本策略、真实发布方式。
    • 可选偏好:只有用户确认或项目证据支持时才写入。
  5. 如果旧规则与目标项目事实冲突,以目标项目当前文件和用户最新决策为准。
  6. 生成或改写 AGENTS.md 后,运行专项校验脚本:
powershell
python -X utf8 vibe-coding-template/skills/agents-md-creator/scripts/validate_agents_md.py path/to/AGENTS.md

脚本失败时,必须继续补齐目标 AGENTS.md 或模板,并复跑直到通过。该脚本只检查项目级规则的关键结构和质量约束,不判断具体项目规则是否已经完全贴合业务事实。

报告链接规则必须保留以下原文,不能改写、压缩或同义替换;validate_agents_md.py 会按完整字符串强制校验:

生成报告时必须使用可跳转的 Markdown 相对路径交叉引用。链接优先落到具体文件名,能定位到行号时必须使用 [文件名](相对路径#L行号) 范式;不要把 :行号 写进链接目标里。不要只写文件夹名代替关键证据,也不要使用当前 IDE 无法跳转的绝对路径,必须强制使用相对路径。

输出要求

  • 输出一份完整、可落地的 AGENTS.md 内容或补丁方案。
  • 规则要能直接指导后续 Agent 工作,避免空泛口号。
  • 必须包含执行环境前置规则、顶层代码生成约束、修改前必读、测试验证、版本规则、修复报告规则、输出与验收格式、进度播报格式、错误处理和无依据保护逻辑判断框架。
  • 不要把某一类项目的发布审核、权限、评测、数据迁移、真实服务复测等专项约束无条件写成所有项目通用规则。
  • 如果有未确认事实,写成待确认项或 {{占位符}},不要包装成项目规则。
  • 不得删除执行环境前置规则、顶层代码生成约束、版本规则、fix-report 规则、无依据保护逻辑、错误处理、输出与验收格式和进度播报格式;如确实裁剪,必须逐条说明原因和替代约束。

质量标准

  • 最终 AGENTS.md 要像项目规则,不像教程、建议或说明文档。
  • 每条关键约束都应可检查、可执行、可交付。
  • “最小必要改动”必须允许在有真实依据时进行较大重构,不能变成盲目保守。
  • 版本和报告规则必须模板化,不得写死某个项目的版本文件、报告目录或发布渠道。
  • 输出格式和进度播报格式必须清楚,方便长任务取证和最终验收。

自检

输出前逐条检查:

  1. 是否先读了目标项目真实上下文。
  2. 是否删除了不适用于目标项目的旧项目规则。
  3. 是否把长期通用行为放进 AGENTS.md,而不是塞进一次性 prompt 模板。
  4. 是否没有写死旧项目私有路径、模块名、测试命令、版本号或审核规则。
  5. 是否补齐版本规则、fix-report 规则、输出验收格式和进度播报格式。
  6. 是否明确禁止为了“看起来更稳”新增没有依据的保护逻辑,并要求说明依据、影响、可观测性、验证方式和后续调整方式。
  7. 是否没有保留空标题、英文占位说明、机器味模板句或不可复用硬编码。
  8. 是否已运行 validate_agents_md.py,并根据失败项循环修改到通过。

© Philip-Cao-9527, 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 3 other files (scripts, references) in vibe-coding-template/skills/agents-md-creator of Philip-Cao-9527/code-note-helper.

  • SKILL.md
  • agents/openai.yaml
  • references/agents-template.md
  • scripts/validate_agents_md.py

Open the folder on GitHubat commit 7421249

Compare with similar skills

Agents Md Creator 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.

Agents Md Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agents Md Creator this skillPhilip-Cao-9527/code-note-helper273—~581Automated safety check: PassMIT
Using Agent Skillsaddyosmani/agent-skills105k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.8k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k20 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~11kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    105k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.8k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed
  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 20 repos~2.7k tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~11k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed

More from Philip-Cao-9527/code-note-helper

All 13 skills in this repo
  • Codenote Fix Prompt

    Philip-Cao-9527/code-note-helper

    为 CodeNote Helper 生成普通开发、修复、验证、治理、文档和审核友好类中文执行 prompt。用于把一次具体任务整理成可直接交给 Codex 或 Agent 执行的 prompt;不承载 Plan mode prompt、code review prompt 或项目 skill creator 的完整职责。

    273 GitHub stars~931 tokensUpdated 2 mo ago
    Auto-check passed
  • Codenote Skill Creator

    Philip-Cao-9527/code-note-helper

    创建或更新 CodeNote Helper 项目本地 .agents/skills 下的 Codex skills。用于把高频协作流程、prompt 生成流程、审查流程或项目专项流程沉淀为可复用 skill;不替代一次性任务 prompt、普通开发实现或万能规则汇总。

    273 GitHub stars~948 tokensUpdated 2 mo ago
    Auto-check passed
  • Project Prompt Creator

    Philip-Cao-9527/code-note-helper

    在项目 AGENTS.md 约束下生成可直接交给 Codex 或 Agent 执行的中文任务 prompt。用于开发、修复、文档、验证、审计、治理或交接任务的 prompt 化,但不承载 Plan mode 和 code review 的完整模式规则。

    273 GitHub stars~693 tokensUpdated 2 mo ago
    Auto-check passed
  • Project Skill Creator

    Philip-Cao-9527/code-note-helper

    基于用户需求和项目真实上下文创建或更新项目本地 skill。用于把高频协作流程、领域任务、项目规范、prompt 生成流程或审查流程沉淀为可复用 skill,并避免把一次性任务误做成长期 skill。

    273 GitHub stars~820 tokensUpdated 2 mo ago
    Auto-check passed
  • Knowledge Explainer

    Philip-Cao-9527/code-note-helper

    当用户要求技术原理讲解、八股讲解、从零教学、面试口述、项目追问回答、领域补课、把项目实现转成可复习表达,或在缺少领域背景时需要先理解概念再推进项目时使用;覆盖后端、前端、数据库、分布式、系统设计、编译构建、DevOps、安全、产品业务、数据分析、Agent、LLM、科研方法等可迁移领域。若涉及最新论文、官方文档、benchmark、争议结论或现代 API,先调用 $web-search。

    273 GitHub stars~899 tokensUpdated 2 mo ago
    Auto-check passed
  • Code Reviewer

    Philip-Cao-9527/code-note-helper

    生成面向 code review 任务的中文 prompt。用于审查代码、文档、配置、PR diff、指定 commit 或发布前风险;默认只生成审查任务 prompt,不直接 review,也不直接修改代码。

    273 GitHub stars~599 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Agents Md Creator

What does Agents Md Creator do?

基于项目真实背景、用户长期偏好和现有文档生成或更新项目级 AGENTS.md。用于新项目初始化、迁移协作规则、整理语言编码测试版本文档约束、沉淀长期协作底线和交付格式时使用。. Agents Md Creator is an agent skill from Philip-Cao-9527/code-note-helper.

When should I use Agents Md Creator?

Agents Md Creator fits situations like: tasks that involve Agent instruction files.

How do I install Agents Md Creator in Claude Code?

Run `npx skills add Philip-Cao-9527/code-note-helper --skill agents-md-creator -a claude-code`. Or copy the skill folder (vibe-coding-template/skills/agents-md-creator in Philip-Cao-9527/code-note-helper) into .claude/skills/agents-md-creator in your project. Claude Code loads it when a task matches its description.

How do I install Agents Md Creator in Codex?

Run `npx skills add Philip-Cao-9527/code-note-helper --skill agents-md-creator -a codex`. Or copy the skill folder (vibe-coding-template/skills/agents-md-creator in Philip-Cao-9527/code-note-helper) into .agents/skills/agents-md-creator in your project. Codex loads it when a task matches its description.

Can I use Agents Md Creator 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 Philip-Cao-9527/code-note-helper --skill agents-md-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agents-md-creator, .gemini/skills/agents-md-creator, .github/skills/agents-md-creator and .opencode/skills/agents-md-creator in your project.

What does Agents Md Creator need to run?

Going by SKILL.md and its folder, Agents Md Creator needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Agents Md Creator 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 Agents Md Creator 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Agents Md Creator use?

Agents Md Creator 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 Agents Md Creator use?

About 581 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Agents Md Creator?

Skills that share tags, products or a category with Agents Md Creator: Using Agent Skills (addyosmani/agent-skills, 105k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.8k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agents Md Creator?

Philip-Cao-9527 (a GitHub user) maintains it in Philip-Cao-9527/code-note-helper, which has 273 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on July 15, 2026.

Source: Philip-Cao-9527/code-note-helper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.