Agent skill

Skill From Masters

by GBSOSS in GBSOSS/skill-from-masters

通过真实案例创建高质量skill。先找黄金案例和失败案例,归纳什么有效什么无效,再用理论解释为什么。skill是干活的,要从实践中学习,不是从书本中学习。触发词:"帮我创建一个skill"、"我想做一个skill来..."

MITAuto-check passed

Install Skill From Masters

skills CLI
$ npx skills add GBSOSS/skill-from-masters --skill skill-from-masters -a claude-code

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

GitHub CLI
$ gh skill install GBSOSS/skill-from-masters skill-from-masters --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/GBSOSS/skill-from-masters.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill-from-masters .claude/skills/skill-from-masters && 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
skill-from-masters
GitHub stars
1.6k
Token cost
~1.2k tokens
SKILL.md length
250 words
Files
3 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

通过真实案例创建高质量skill。先找黄金案例和失败案例,归纳什么有效什么无效,再用理论解释为什么。skill是干活的,要从实践中学习,不是从书本中学习。触发词:"帮我创建一个skill"、"我想做一个skill来..."

  • Works in 6 steps: 理解和收窄任务 → 找案例(最重要的步骤)⚠️ → 归纳有效/无效模式 → …
  • SKILL.md covers 核心理念, 工作流程, 搜索策略对比 and 质量检查清单, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill From Masters is an agent skill from GBSOSS/skill-from-masters. 通过真实案例创建高质量skill。先找黄金案例和失败案例,归纳什么有效什么无效,再用理论解释为什么。skill是干活的,要从实践中学习,不是从书本中学习。触发词:"帮我创建一个skill"、"我想做一个skill来..."

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/methodology-database.md` and `references/skill-taxonomy.md`).

The repository describes itself as: Stand on the shoulders of giants — Create AI skills built on proven methodologies from domain experts. The licence is MIT.

Example prompts

  • “帮我创建一个skill”
  • “我想做一个skill来...”
  • “/skill-from-masters”

Workflow steps

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

  1. 理解和收窄任务
  2. 找案例(最重要的步骤)⚠️
  3. 归纳有效/无效模式
  4. 用理论辅助解释(可选)
  5. 生成Skill
  6. 用案例测试

What it can do on your machine

Read from SKILL.md and the folder at commit c4d27d2. 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

Skill From Masters loads about 1.2k tokens when it runs, and up to ~7.2k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 250 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.2k

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 GBSOSS/skill-from-masters at commit c4d27d2, republished under its MIT licence (© GBSOSS). 250 words, ~1,195 tokens.

Download SKILL.mdSave it as .claude/skills/skill-from-masters/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
skill-from-masters
description
通过真实案例创建高质量skill。先找黄金案例和失败案例,归纳什么有效什么无效,再用理论解释为什么。skill是干活的,要从实践中学习,不是从书本中学习。触发词:"帮我创建一个skill"、"我想做一个skill来..."

Skill From Masters

创建像实战专家一样的skill,而不是像书呆子一样的skill。

核心理念

Skill是干活的。干活的知识来自实践,不是来自理论。

实践专家 vs 理论专家
实践专家理论专家
做得最好的人写书的人
销售冠军销售方法论作者
让客户感动的客服客服培训师
招到好人的面试官面试技巧书作者
让人想继续倾诉的倾听者心理咨询教授

我们要找的是实践专家——做得最好的人。理论专家只是辅助解释。

写书的人擅长总结和教学,但不一定是做得最好的。真正的高手往往不写书,但他们的案例、做法、踩过的坑,才是最有价值的。

所以:

❌ 错误:找写书的人 → 提取他们的理论 → 生成skill
✅ 正确:找做得最好的人 → 学习他们怎么做的 → 用理论辅助解释

工作流程

Step 1: 理解和收窄任务

确保任务足够具体。太宽泛的任务无法找到有效案例。

收窄方法:

  1. 问领域:这个任务属于什么领域?
  2. 问场景:具体在什么情况下使用?
  3. 问约束:有什么限制条件?
  4. 问案例:能描述一个你实际遇到的情况吗?

收窄标准:

  • 能找到这个具体场景的真实案例吗?
  • 能判断什么是"做得好"什么是"做得差"吗?

如果答案是否,继续收窄。


Step 2: 找案例(最重要的步骤)⚠️

这是整个流程的核心。先找案例,不要先找理论。

2.1 找黄金案例(做得最好的人怎么做的)

关键:找实践中做得最好的人,不是写书的人。

搜索策略:

"[具体任务] top performer"
"[具体任务] how the best do it"
"[具体任务] real example from [top company]"
"[角色] who is the best at [任务]"
"[具体任务] interview with [practitioner]"
"[具体任务] behind the scenes"

目标:找到3-5个实践中公认做得好的真实案例。

识别实践专家的信号:

  • 有具体的成果/数据("成交率提升X%"、"客户满意度最高")
  • 被同行认可("团队里大家都学他")
  • 有真实的案例细节,不是泛泛的原则

对于每个黄金案例,记录:

  • 这个人具体是怎么做的?
  • 和普通人做法有什么不同?
  • 有什么具体的细节让他做得更好?
2.2 找失败案例(什么是做得差的)⚠️ 同样重要

搜索策略:

"[具体任务] common mistakes"
"[具体任务] what not to do"
"[具体任务] fails"
"[具体任务] I learned the hard way"
"[具体任务] before after comparison"
"why [具体任务] doesn't work"

目标:找到常见的失败模式和踩过的坑。

对于每个失败案例,记录:

  • 具体做错了什么?
  • 为什么这样做是无效的?
  • 应该怎么做才对?
2.3 找对比(有效 vs 无效)

搜索策略:

"[具体任务] good vs bad example"
"[具体任务] before after"
"[具体任务] do this not that"
"[具体任务] comparison"

对比是最有价值的素材,因为它直接展示了差异。

案例收集标准:

  • 找到至少3个黄金案例了吗?
  • 找到至少5个常见失败模式了吗?
  • 找到有效/无效的直接对比了吗?
  • 案例足够具体,能看到实际细节吗?

如果任何一项答案是否,继续搜索。


Step 3: 归纳有效/无效模式

从案例中提炼规律,而不是从理论中推导。

归纳方法:

  1. 列出所有黄金案例的共同点

    • 它们都做了什么?
    • 它们有什么共同的特征?
    • 为什么这些做法是有效的?
  2. 列出所有失败案例的共同点

    • 它们都犯了什么错?
    • 这些错误的根源是什么?
    • 如何避免这些错误?
  3. 形成对比表格

| 有效做法 | 无效做法 | 为什么 |
|----------|----------|--------|
| [具体做法A] | [对应的错误做法] | [原因] |
| [具体做法B] | [对应的错误做法] | [原因] |
| ... | ... | ... |

归纳标准:

  • 每个有效做法都有对应的无效做法对比吗?
  • 能用一句话说清楚"做这个,不要做那个"吗?
  • 这些规律来自案例,而不是来自理论假设吗?

Step 4: 用理论辅助解释(可选)

理论专家(写书的人)在这一步才登场,作为辅助。

理论的作用是解释为什么实践专家的做法有效,而不是指导怎么做。

搜索策略:

"why [有效做法] works"
"[领域] psychology behind"
"[理论专家名] explains [现象]"

理论的价值:

  • 给实践规律提供"为什么"的解释
  • 帮助用户理解背后的逻辑
  • 增加可信度

注意:

  • 理论是辅助,不是主体
  • 如果找不到理论解释,也没关系——实践专家的案例本身就是最好的证据
  • 不要让理论盖过实践。Skill的核心应该是"做得最好的人怎么做",而不是"书上怎么说"

Step 5: 生成Skill

将案例中归纳的规律转化为skill指令。

生成原则:

  1. 用案例说话

    • 每个规则都要有具体的"这样做"和"不要这样做"的例子
    • 例子来自真实案例,不是编造的
  2. 先说怎么做,再说为什么

    • 用户首先需要知道该怎么做
    • 理论解释放在后面
  3. 失败案例和黄金案例同等重要

    • 知道"不要做什么"往往比知道"要做什么"更实用
    • 专门设置"常见错误"或"避免这样做"的章节
  4. 保持具体

    • 避免抽象的原则(如"要有同理心")
    • 用具体的做法替代(如"当用户说X时,回应Y而不是Z")

调用skill-creator生成:

Use the Skill tool with: skill: "skill-creator:skill-creator"

确保:

  • 添加 model: opus(如果是需要判断力的skill)
  • 包含黄金案例和失败案例的对比
  • 用命令式语气写作

Step 6: 用案例测试

用真实案例测试生成的skill。

  1. 拿一个黄金案例,看skill是否能产出类似质量的结果
  2. 故意触发一个失败模式,看skill是否能避免
  3. 让用户用自己的真实场景测试

如果测试失败,回到Step 2找更多案例。


搜索策略对比

❌ 旧的(偏理论)
"[domain] best practices expert"
"[domain] framework methodology"
"[expert name] methodology"
"[domain] principles"

这些搜索会返回书籍摘要、学术框架、抽象原则——都是"书本知识"。

✅ 新的(偏实践)
"[task] real example"
"[task] case study"
"[task] common mistakes"
"[task] what not to do"
"[task] before after"
"[task] I learned the hard way"
"how [company] does [task]"

这些搜索会返回真实案例、失败教训、对比——都是"实战知识"。


质量检查清单

在完成skill之前,确认:

案例质量:

  • 找到了足够多的黄金案例(至少3个)?
  • 找到了足够多的失败案例(至少5个常见错误)?
  • 案例来自真实实践,不是理论假设?
  • 案例足够具体,能看到实际细节?

归纳质量:

  • 有效/无效做法形成了清晰的对比?
  • 每个规则都有"做这个"和"不要做那个"的配对?
  • 规律是从案例中归纳的,不是从理论中推导的?

Skill质量:

  • Skill中包含了具体的例子,而不只是抽象原则?
  • 失败案例和黄金案例都被体现了?
  • 用真实案例测试过了?

最终检验:

  • 这个skill像一个"做过无数次的老手",还是像一个"读过很多书的人"?

示例:员工关怀Skill的正确做法

❌ 错误做法(旧流程)
  1. 搜索"active listening methodology"
  2. 找到卡尔·罗杰斯的三原则
  3. 找到厚生劳动省的傾聴指南
  4. 提取原则,生成skill
  5. 结果:skill很学术,用户反馈"没有被关怀的感觉"
✅ 正确做法(新流程)
  1. 搜索"employee care conversation example"
  2. 搜索"what makes people feel heard"
  3. 搜索"bad listening examples"
  4. 搜索"therapist response good vs bad"
  5. 找到大量真实对话对比:
    • ❌ "您感到疲惫了呢" → 冷漠,像回音壁
    • ✅ "怎么了?最近发生什么事了?" → 温暖,有兴趣
  6. 归纳规律:
    • 不要オウム返し(回音壁式重复)
    • 要表现出真正的好奇心和关心
    • 具体追问,而不是泛泛共情
  7. 生成skill,包含大量"这样说 vs 不要这样说"的对比
  8. 结果:skill有温度,用户感觉被关心

核心记住

  1. 找做得最好的人,不是写书的人 — 实践专家 > 理论专家
  2. 先案例,后理论 — 理论只是辅助解释
  3. 黄金案例 + 失败案例 — 知道什么不能做,比知道什么能做更实用
  4. 对比是最有价值的 — "这样做 vs 那样做"的对比最直观
  5. Skill是干活的 — 生成的应该是"实战高手",不是"读过很多书的人"

© GBSOSS, 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 2 other files (references) in skill-from-masters of GBSOSS/skill-from-masters.

  • SKILL.md
  • references/methodology-database.md
  • references/skill-taxonomy.md

Open the folder on GitHubat commit c4d27d2

Compare with similar skills

Skill From Masters 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.

Skill From Masters compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill From Masters this skillGBSOSS/skill-from-masters1.6k—~1.2kAutomated safety check: PassMIT
Music Masterruvnet/ruflo74k—~270Automated safety check: PassMIT
Scrum Masteralirezarezvani/claude-skills28k1 repos~2.4kAutomated safety check: PassMIT
PPT Masterhugohe3/ppt-master59k1 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 yesterday
    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.

    59k 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.

    277k GitHub stars~2.9k tokensUpdated today
    Legal & ComplianceAuto-check passed

More from GBSOSS/skill-from-masters

  • Skill From GitHub

    GBSOSS/skill-from-masters

    Create skills by learning from high-quality GitHub projects. An agent skill from GBSOSS/skill-from-masters.

    1.6k GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check passed
  • Skill From Notebook

    GBSOSS/skill-from-masters

    Extract methodologies from documents or examples to create executable skills

    1.6k GitHub stars~2k tokensUpdated 7 mo ago
    Auto-check passed
  • Search Skill

    GBSOSS/skill-from-masters

    Search and recommend Claude Code skills from trusted marketplaces

    1.6k GitHub stars~1.3k tokensUpdated 7 mo ago
    Auto-check: warnings

Questions about Skill From Masters

What does Skill From Masters do?

通过真实案例创建高质量skill。先找黄金案例和失败案例,归纳什么有效什么无效,再用理论解释为什么。skill是干活的,要从实践中学习,不是从书本中学习。触发词:"帮我创建一个skill"、"我想做一个skill来...". Skill From Masters is an agent skill from GBSOSS/skill-from-masters.

How do I install Skill From Masters in Claude Code?

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

How do I install Skill From Masters in Codex?

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

Can I use Skill From Masters 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 GBSOSS/skill-from-masters --skill skill-from-masters -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-from-masters, .gemini/skills/skill-from-masters, .github/skills/skill-from-masters and .opencode/skills/skill-from-masters in your project.

What does Skill From Masters need to run?

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

Does Skill From Masters 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 Skill From Masters 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 Skill From Masters use?

Skill From Masters 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 Skill From Masters use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 6k tokens, read only when the agent opens those files.

What are the alternatives to Skill From Masters?

Skills that share tags, products or a category with Skill From Masters: Music Master (ruvnet/ruflo, 74k stars), Scrum Master (alirezarezvani/claude-skills, 28k stars), PPT Master (hugohe3/ppt-master, 59k 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 Skill From Masters?

GBSOSS (a GitHub organization) maintains it in GBSOSS/skill-from-masters, which has 1,588 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on February 16, 2026.

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