Agent skill

Full Stack Master

by CaoMeiYouRen in CaoMeiYouRen/caomei-auth

需要统筹需求澄清、上下文扫描、技术方案、前后端实现、UI 验证、测试、质量审查、文档同步和提交节奏时使用。它负责编排多技能协作,而不是亲自替代所有专业技能。用户提到 end-to-end workflow、全流程开发、从需求到提交、PDTFC+、多技能编排时都应触发。

MITAuto-check passed

Install Full Stack Master

skills CLI
$ npx skills add CaoMeiYouRen/caomei-auth --skill full-stack-master -a claude-code

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

GitHub CLI
$ gh skill install CaoMeiYouRen/caomei-auth full-stack-master --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/CaoMeiYouRen/caomei-auth.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/full-stack-master .claude/skills/full-stack-master && 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
full-stack-master
GitHub stars
220
Token cost
~1k tokens
SKILL.md length
294 words
Files
2 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

需要统筹需求澄清、上下文扫描、技术方案、前后端实现、UI 验证、测试、质量审查、文档同步和提交节奏时使用。它负责编排多技能协作,而不是亲自替代所有专业技能。用户提到 end-to-end workflow、全流程开发、从需求到提交、PDTFC+、多技能编排时都应触发。

  • Works in 4 steps: 先暴露假设:需求有歧义或上下文不足时,先说明假设、可选解释与风险,不静默选择一种解… → 选最小方案:默认选择满足当前验收标准的最小实现,不引入无关抽象。 → 限制改动范围:改动范围与 Todo 验收点或 blocker… → …
  • SKILL.md covers 能力定位, 统一执行原则, 标准工作流(PDTFC+) and 需求挖掘方法论, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Full Stack Master is an agent skill from CaoMeiYouRen/caomei-auth. 需要统筹需求澄清、上下文扫描、技术方案、前后端实现、UI 验证、测试、质量审查、文档同步和提交节奏时使用。它负责编排多技能协作,而不是亲自替代所有专业技能。用户提到 end-to-end workflow、全流程开发、从需求到提交、PDTFC+、多技能编排时都应触发。

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/standards-reference.md`).

The repository describes itself as: 草梅 Auth 是一个基于 Nuxt 全栈框架的统一登录平台。支持 OAuth2.0 协议,集成邮箱、用户名、手机号、验证码、社交媒体等多种登录注册方式。 The licence is MIT.

Example prompts

  • “/full-stack-master”

Workflow steps

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

  1. 先暴露假设:需求有歧义或上下文不足时,先说明假设、可选解释与风险,不静默选择一种解释。
  2. 选最小方案:默认选择满足当前验收标准的最小实现,不引入无关抽象。
  3. 限制改动范围:改动范围与 Todo 验收点或 blocker 一一对应,发现无关问题只记录不顺手扩写。
  4. 最小验证决定是否扩写:完成首个实质改动后先做最小充分验证,再决定是否继续。

What it can do on your machine

Read from SKILL.md and the folder at commit 7bd3bae. 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.

    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

Full Stack Master loads about 1k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 38 tokens; SKILL.md has 294 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

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 CaoMeiYouRen/caomei-auth at commit 7bd3bae, republished under its MIT licence (© CaoMeiYouRen). 294 words, ~1,021 tokens.

Download SKILL.mdSave it as .claude/skills/full-stack-master/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
full-stack-master
description
需要统筹需求澄清、上下文扫描、技术方案、前后端实现、UI 验证、测试、质量审查、文档同步和提交节奏时使用。它负责编排多技能协作,而不是亲自替代所有专业技能。用户提到 end-to-end workflow、全流程开发、从需求到提交、PDTFC+、多技能编排时都应触发。
metadata.internal
true

Full Stack Master

铁律:不要跳过规划和质量门,直接从需求冲到实现和提交。全链路编排的价值就在于减少返工,而不是增加速度幻觉。

能力定位

  • 工作流自动编排:串联需求 → 设计 → 开发 → 审计 → 测试 → 文档 → 提交的全链路。
  • 技能聚合:集成所有核心技能,按阶段分派。
  • Session 感知:跨 session 恢复任务上下文与经验(见下文 Session 协议)。
  • 可复用与可拓展:支持新场景接入,支持多项目切换。

统一执行原则

编排遵循四步判断顺序:

  1. 先暴露假设:需求有歧义或上下文不足时,先说明假设、可选解释与风险,不静默选择一种解释。
  2. 选最小方案:默认选择满足当前验收标准的最小实现,不引入无关抽象。
  3. 限制改动范围:改动范围与 Todo 验收点或 blocker 一一对应,发现无关问题只记录不顺手扩写。
  4. 最小验证决定是否扩写:完成首个实质改动后先做最小充分验证,再决定是否继续。

标准工作流(PDTFC+)

P (Plan) — 需求分析与规划
  • 读取项目上下文与任务状态(AGENTS.md、README、package.json、todo 与验收标准)。

  • 需求模糊时交给 product-manager 做最小必要澄清,不跳过。

  • 输出受影响文件清单、验证矩阵和阶段交接顺序。

  • 不在需求未收敛时启动代码改动。

  • 技能:context-analyzer、requirement-analyst、technical-architect

D (Do) — 开发实现
  • 同一事项同一时点只保留一个实现主责。

  • 按方案映射把改动交给对应技能:后端 backend-expert、前端 nuxt-code-editor、文档 documentation-specialist。

  • 实现收尾须通过本地自检(lint + typecheck + 定向测试)。

  • 预计改动超出任务粒度约束(默认 10 文件或 800 行新增,项目可调整)时,先返回 P 拆分为多个原子条目,分批实现、分批审计、分批提交。

  • 范围闸门:开发中发现新的优化点或非阻塞事项时,返回 P 重新分流,不静默扩写。

  • 技能:backend-expert、nuxt-code-editor、devops-specialist 等按需

A (Audit) — 质量门与审计放行(强制)
  • D 阶段完成后,必须用 quality-guardian 选择并执行最小充分检查。

  • 必须加载本项目 code-reviewer 执行结构化审查,不得自我审查替代。

  • 审计调用协议:审计 prompt 必须携带 audit-depth 声明(quick / standard / deep + 理由)、变更文件清单、已验证证据摘要与复审问题编号;未声明按 deep 防御执行。

  • 证据前置:把调研结论、实验证据、源码行号引用写进审计任务,避免审计者从头翻源码。

  • 复审只审修复点:第 2+ 轮只移交上轮问题编号对应的修复 diff。

  • 并发审计(仅大改动):diff 文件数 > 8 或涉及 ≥ 2 个独立模块时,按模块分区并行发起审计,汇总取最严结论。

  • 发现 blocker 退回 D 或回流 P,不携带未关闭 blocker 进入后续阶段。

  • 技能:quality-guardian、code-reviewer、security-guardian

V (Validate) — UI 验证
  • 涉及页面渲染、交互流程时,使用 ui-validator 完成浏览器验证。

  • 无 UI 面影响时显式记录跳过原因,不默认省略。

  • 技能:ui-validator

T (Test) — 测试与回归
  • 按改动类型和风险选择定向/全量/coverage 验证,不一刀切全量执行。

  • 测试暴露的代码改动必须回到 D 并重新经过 A 阶段。

  • 技能:test-engineer

F (Finish) — 交付与提交
  • 更新任务状态,按需同步相关文档。

  • 需要提交时,由 conventional-committer 生成并执行提交。

  • 每个原子条目独立提交;A 阶段未放行的改动不得提交。

  • 不自动 push。

  • 技能:documentation-specialist、conventional-committer

需求挖掘方法论

  1. 逐级递进:先锁定整体结构和目标,再深入实现细节。
  2. 单点突破:一次只问一个问题,待用户回答后再追问。
  3. 循环校验:回答不清晰时换一种表述方式确认。
  4. 意图抽离:分析"想要什么"背后的"为什么"。

推理模式与失败自检

根据问题类型选择推理模式:

模式适用场景核心方法
根因分析修 bug、查事故5-Why 追问 → 扫描同类 bug → git log 定位引入 commit
第一性原理全新模块设计质疑假设 → 删除不必要 → 简化剩余 → 加速核心路径
减法模式重构、清理删除优先,不增加新抽象;先压缩再提取
搜索优先不熟悉的模块先查项目文档 → 再查代码 → 必要时外部搜索 → 最后动手
证据驱动性能、质量审计先跑测量(benchmark/coverage)→ 确定缺口 → 收敛改动

失败自检:同一方案连续 3 次未能解决问题时,必须声明当前方案失败(失败在哪、试了什么、为何无效),从表中至少列举 2 个替代模式,选择最匹配的一个并向用户解释切换理由,然后重新分析——而不是改个参数重跑旧方案。

Session 协议(跨 session 恢复)

本技能内化轻量 Session 感知机制,状态文件写入项目 .session/ 目录(已在 .gitignore 中排除)。

新 Session 开局
  1. 读取 .session/current-task.yaml(当前任务、已完成步骤、下一步)与 .session/wisdom.md(跨 session 经验)。
  2. 向用户输出一份 不超过 10 行 的 briefing:当前阶段 + 任务、已完成步骤、下一步、上次 session 的认知状态摘要(如有)。
Session 收尾(用户说"收工""结束""今天到这"或切换任务时)
  1. 更新 .session/current-task.yaml:进度、next_steps(3 项以内)、updated_at。
  2. 发现值得跨 session 复用的 pattern / bug / decision 时,追加到 .session/wisdom.md(按日期分组,每条一行要点)。
  3. 若 wisdom 活跃条目数 ≥ 20,提醒用户"建议执行蒸馏"(把可复用经验沉淀为 skill 或归档)。
  4. 向用户输出 不超过 5 行 的收尾摘要:完成内容、下一步、阻塞点、新固化的 wisdom 条目(如有)。

技能映射

  • context-analyzer:建立上下文。
  • requirement-analyst:澄清需求。
  • technical-architect:设计方案。
  • backend-expert / nuxt-code-editor:实施改动。
  • documentation-specialist:同步文档。
  • ui-validator:验证界面。
  • test-engineer:补测试与查失败。
  • security-guardian:补安全审计。
  • quality-guardian:运行质量门。
  • code-reviewer:做结构化审查(Review Gate)。
  • conventional-committer:管理交付和提交。

反模式

  • 总控技能亲自接管所有实现细节,导致专业技能失效。
  • 在需求仍然模糊时就启动代码改动。
  • 质量门和 code review 只走形式,不影响后续阶段。
  • 跳过 A 阶段审计直接进入提交。
  • 需求/方案阶段不记录假设,静默扩写当前任务。
  • 用训练数据记忆替代外部搜索与验证。

交付前检查

  • 已完成上下文、方案、实现、验证、审查和交付的最小闭环(PDTFC+ 全阶段)。
  • 每个阶段都有明确负责技能,无阶段空转或遗漏。
  • A 阶段审计已放行(携带 audit-depth 声明与证据摘要)。
  • 未跳过质量门或审查,无未关闭 blocker。
  • 任务状态已同步,session 状态已更新(如启用 Session 协议)。
  • 输出中已说明当前进度、风险和下一步。

© CaoMeiYouRen, 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 (references) in .github/skills/full-stack-master of CaoMeiYouRen/caomei-auth.

  • SKILL.md
  • references/standards-reference.md

Open the folder on GitHubat commit 7bd3bae

Compare with similar skills

Full Stack Master 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.

Full Stack Master compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Full Stack Master this skillCaoMeiYouRen/caomei-auth220—~1kAutomated safety check: PassMIT
Music Masterruvnet/ruflo74k—~270Automated safety check: PassMIT
Scrum Masteralirezarezvani/claude-skills28k1 repos~2.4kAutomated safety check: PassMIT
PPT Masterhugohe3/ppt-master58k1 repos~2.5kAutomated safety check: PassMIT
Git Mastercode-yeongyu/oh-my-openagent70k—~1.4kAutomated safety check: PassCustom licence
Git Mastercode-yeongyu/oh-my-openagent70k—~7.3kAutomated safety check: PassCustom licence

Similar skills

  • Music Master

    ruvnet/ruflo

    Run a mastering pass (LUFS loudness normalization + peak limiting) on an existing production

    74k GitHub stars~270 tokensUpdated today
    DatabasesAuto-check passed
  • Scrum Master

    alirezarezvani/claude-skills

    Advanced Scrum Master skill for data-driven agile team analysis and coaching.

    28k GitHub starsUsed in 1 repo~2.4k tokens
    Product & Project ManagementAuto-check passed
  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    58k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed
  • Git Master

    code-yeongyu/oh-my-openagent

    Guides an agent through commits, rebases and history questions in Git, working from the repository's actual state and changing nothing unless you asked.

    70k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Git Master

    code-yeongyu/oh-my-openagent

    MUST USE for ANY git operations. An agent skill from code-yeongyu/oh-my-openagent.

    70k GitHub stars~7.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    275k GitHub stars~2.9k tokensUpdated 3 days ago
    Legal & ComplianceAuto-check passed

More from CaoMeiYouRen/caomei-auth

All 14 skills in this repo
  • Code Reviewer

    CaoMeiYouRen/caomei-auth

    审查当前 git 变更、PR、提交范围、技能定义文件、架构调整或安全敏感代码时使用。输出结构化 Review Gate 结论(Pass/Reject)、问题分级(blocker/warning/suggest)、最低验证矩阵、证据链与复查基线。覆盖正确性、安全、架构、SOLID、可删除代码、性能、异常处理与测试风险;默认只输出 review,不直接修改代码。用户提到 review、code…

    220 GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed
  • Quality Guardian

    CaoMeiYouRen/caomei-auth

    运行并解读 lint、类型检查、测试等质量门时使用。它不只是执行命令,还要根据变更范围选择最小充分检查、分析失败原因,并给出是否允许继续提交或发布的判断。用户提到 lint、typecheck、tests、quality gate、验证改动时都应触发。

    220 GitHub stars~358 tokensUpdated 7 days ago
    Auto-check passed
  • Devops Specialist

    CaoMeiYouRen/caomei-auth

    修改 Docker、CI/CD、部署配置、环境变量、运行时参数、构建脚本和发布流程时使用。优先覆盖 Docker、Vercel、Cloudflare 与 GitHub Actions 场景。用户提到 deploy、Dockerfile、workflow、CI、CD、environment variables、build pipeline、release config 时都应触发。

    220 GitHub stars~446 tokensUpdated 7 days ago
    Auto-check: notes
  • Gh CLI

    CaoMeiYouRen/caomei-auth

    使用 GitHub CLI(gh)处理仓库、issue、pull request、workflow、project、release、codespace、gist、search、api、auth、config、alias、secret、variable、extension、ruleset 和 status 等命令行操作时使用。用户提到 gh、gh cli、GitHub CLI、gh…

    220 GitHub stars~460 tokensUpdated 7 days ago
    Auto-check passed
  • Backend Expert

    CaoMeiYouRen/caomei-auth

    设计或实现后端 API、服务层、数据库读写、鉴权权限控制、输入校验、事务处理与错误处理时使用。用户提到 API、route、handler、server、auth、permission、drizzle、database、zod、Hono、Nuxt server routes、backend bug 修复时都应触发。

    220 GitHub stars~329 tokensUpdated 7 days ago
    Auto-check passed
  • Context Analyzer

    CaoMeiYouRen/caomei-auth

    在动手规划、修改、调试或回答复杂项目问题前使用。用于快速扫描项目结构、依赖、约束文档、关键文件和调用链,输出任务相关上下文,而不是直接改代码。用户提到 analyze context、scan repo、understand project、定位实现、找规范、排查调用链时都应触发。

    220 GitHub stars~296 tokensUpdated 7 days ago
    Auto-check passed

Questions about Full Stack Master

What does Full Stack Master do?

需要统筹需求澄清、上下文扫描、技术方案、前后端实现、UI 验证、测试、质量审查、文档同步和提交节奏时使用。它负责编排多技能协作,而不是亲自替代所有专业技能。用户提到 end-to-end workflow、全流程开发、从需求到提交、PDTFC+、多技能编排时都应触发。. Full Stack Master is an agent skill from CaoMeiYouRen/caomei-auth.

How do I install Full Stack Master in Claude Code?

Run `npx skills add CaoMeiYouRen/caomei-auth --skill full-stack-master -a claude-code`. Or copy the skill folder (.github/skills/full-stack-master in CaoMeiYouRen/caomei-auth) into .claude/skills/full-stack-master in your project. Claude Code loads it when a task matches its description.

How do I install Full Stack Master in Codex?

Run `npx skills add CaoMeiYouRen/caomei-auth --skill full-stack-master -a codex`. Or copy the skill folder (.github/skills/full-stack-master in CaoMeiYouRen/caomei-auth) into .agents/skills/full-stack-master in your project. Codex loads it when a task matches its description.

Can I use Full Stack Master 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 CaoMeiYouRen/caomei-auth --skill full-stack-master -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/full-stack-master, .gemini/skills/full-stack-master, .github/skills/full-stack-master and .opencode/skills/full-stack-master in your project.

What does Full Stack Master need to run?

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

Does Full Stack Master 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 Full Stack Master 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 Full Stack Master use?

Full Stack Master 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 Full Stack Master use?

About 1k tokens (SKILL.md is roughly 4.1k 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 1k tokens, read only when the agent opens those files.

What are the alternatives to Full Stack Master?

Skills that share tags, products or a category with Full Stack Master: Music Master (ruvnet/ruflo, 74k stars), Scrum Master (alirezarezvani/claude-skills, 28k stars), PPT Master (hugohe3/ppt-master, 58k stars) and Git Master (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Full Stack Master?

CaoMeiYouRen (a GitHub user) maintains it in CaoMeiYouRen/caomei-auth, which has 220 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 1, 2026.

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