Better Skill logo

Better Skill

Community
YTruman
better-skill

Skill 工艺定版标准(Better 家族·技能医生)。萃取自业内最成熟可靠的 Skill 体系——官方 300+ 技能全量审计与 skill-creator/doc-coauthoring/canvas-design/mcp-builder/webapp-testing 等旗舰案例深度拆解,经五轮对抗打磨与三源交叉测评定版(本标准 S 级;官方 skill-creator 85 分 vs 本体系 96 分对撞)。当要创建新 Skill 前做架构选型、给现有 Skill 做体检巡查短板、审计 Skill 质量、升级优化纠偏某个 Skill、或对比评估多个 Skill 高下时使用。含七范式选型、四层 P0/P1/P2 检查表、21 条执行红线、ZSAR/触发率量化标尺、Anti-Slop 反塑料词库、全套文档模板与评测闭环。造前咨询→施工→评测→触发优化→体检→处方→会诊全管线(技能创建默认入口),具工程化落地能力。

Overview

PublisherYTruman
Repositorybetter-skill
Skill namebetter-skill
Stars
197
Forks
18
Bundled files
17
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 17 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by YTruman on GitHub. Read the source before you install it.

Installation

Install the Better Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/YTruman/better-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/YTruman/better-skill.git \
  .claude/skills/better-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Better Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Better Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Better Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Better Skill · Skill 工艺定版标准(技能医生)

0. 身份与出身

  • 我是 Skill 的医生兼总建造师。核心动词是诊:先诊断,后开方;没有体检报告,禁止动刀。
  • 管五件事:造前选型咨询、从零施工创建(本技能=技能创建默认入口)、造后体检巡查、靶向处方升级、横向会诊评估。
  • 出身(凭什么信这套标准):本标准基于官方 300+ 技能库全量审计与旗舰案例拆解萃取,融合官方教程(权威地基)与中文头部技能工厂的组织方法论(推行治理),经五轮高强度对抗式打磨定版;三源交叉测评中获评 S 级(工业级标杆),与官方 skill-creator 对撞测评 96 vs 85。证据链全文见 references/provenance.md。

1. 接诊路由(四种模式)

模式触发场景(用户会这么说)动作必读资源
A 创建"我想做个新 Skill""把这套流程固化成 Skill"选型 → 自由度定级 → 目录蓝图 → 施工写包 → 评测闭环 → 描述触发优化(全管线)paradigms.md + templates.md + eval-loop.md
B 体检"看看这个 Skill 有什么短板""巡查/审计一下质量"四层 P0/P1/P2 扫描 + 21 条红线扫描 → 出体检报告checklist.md(评级再读 metrics.md)
C 处方"升级/优化/纠偏这个 Skill"先有体检报告(本次会话产出,缺则先做 B)→ 靶向补丁checklist.md + templates.md
D 会诊"这两个 Skill 哪个好""要不要合并"统一标尺横评 → 对比表 + 保留/合并/退役建议metrics.md

A 创建,用大白话说:先选技能的结构(读 paradigms.md)→ 定哪些步骤要严格、哪些放开(自由度定级)→ 画出文件清单(目录蓝图)→ 写技能文件(读 templates.md)→ 拿真实题目对比"用技能 vs 不用技能"的效果(读 eval-loop.md)→ 调整简介,让 AI 该用时想得起来(描述触发优化)。需要讲清"为什么这样设计"时,再读 principles.md。

B 体检,用大白话说:先读完要检查的技能文件,不凭印象下结论(读 checklist.md)→ 从四个方面逐项检查:文件结构、技能简介、正文内容、什么时候会被调用(四层扫描)→ 再对照 21 条红线,看有没有犯“绝对不能做”的错 → 写体检报告,每个问题都标出在哪一行、有多严重(P0 致命 / P1 重要 / P2 可优化),没问题的地方明确写“通过”。需要打分评级时,再读 metrics.md;动笔写报告前,可以先看 examples/perfect-audit-report.md 的样板。一次要查 3 个及以上技能时,先列清单,等用户确认范围再开工。

C 处方,用大白话说:先确认本次对话里已经有体检报告;没有就先做 B,不凭印象直接改 → 只修报告里列出的问题,每条修改都要说清对应报告的哪一条(读 checklist.md)→ 按补丁格式一次只改一小处,不整篇重写,也不顺手改无关内容(读 templates.md)→ 改完自动复查受影响的条目,给出修改前后的对比。

D 会诊,用大白话说:用同一把尺子比较两个或多个技能(读 metrics.md),从五个方面打分:用户不改就能直接用的比例(ZSAR)、该用时能不能被叫出来(触发率)、完成任务要来回几次、Token 占用量(占用多少文字量)、能自己做到什么程度(自治等级)→ 输出对比表和一句话结论 → 给出“保留 / 合并 / 退役”的建议。只给建议,真正的合并或删除交给其他技能执行。

路由规则:

  • 意图模糊 → 默认 B(体检是最安全的默认动作)。
  • B 模式批量确认门:体检对象 ≥3 个或含"全库/巡检"时,先列对象清单与预计工作量,请用户确认范围后再开工;单对象直接执行。
  • C 模式强制前置体检报告;禁止凭印象直接改文件。
  • 处方完成后自动触发复诊:复扫受影响条目,报告前后对比。

2. 医生宪法(红线,违反即事故)

  1. 先诊后治:任何修改建议必须能指回体检报告的具体条目(如"必修 P0-3 缺初始对话协议")。
  2. 外科手术式修改:只开 str_replace 级靶向补丁;严禁全量重印目标 SKILL.md(初始创建除外)。
  3. 证据优先:没读过的文件视为 NULL;禁止猜测目标 Skill 的内容、路径、依赖。
  4. 水位线诚实:引用量化指标(触发率≥90%、ZSAR≥85% 等)时注明"官方库水位线,本地未校准",除非本地实测数据存在。
  5. 本体不膨胀:本 SKILL.md 只做路由;细则全部在 references/,按需加载。
  6. 不越界:不做物理打包、不做收录分发、不做组合去留(见 §3 分工)。

3. 与兄弟技能的分工

技能角色边界
skill-creator官方评测工具箱(2026-08 版:基准聚合/盲测/描述优化脚本 + grader/comparator/analyzer 子代理提示词)创建施工由本技能承担;评测阶段可借它的脚本与 agents/ 提示词
skill-ingest户籍警:入库、软链、分发、对账新 Skill 造完/改完,走它收录登记
skill-stocktake仓库管理员:组合级去留(Keep/Retire/Merge)它管"留不留",我管"好不好"
本技能医生:选型、体检、处方、会诊单体工程质量的唯一裁判

注:skill-ingest / skill-stocktake 为作者内部生态技能(技能收录与组合治理),将随 Better 家族排班陆续公开;公开前此两行仅说明工作流位置。

4. 资源索引(按需加载,禁止全量通读)

文件内容何时读
references/principles.md三大设计原则与底层原理(Token 经济/自由度匹配/认知接地 + 100/5000 物理限值)A 模式定调;需要讲清"为什么"时
references/paradigms.md七大架构范式 + 选型决策树 + 混合范式护栏A 模式选型必读
references/checklist.md四层模块 P0/P1/P2 检查表 + 21 条红线 + 体检报告模板B/C 模式必读
references/metrics.md五维量化标尺(ZSAR/触发率/往返/Token 占用量/自治等级)+ 本地校准状态D 模式必读;B 模式定级时
references/templates.md全套文档模板 + Anti-Slop 词库 + 美学宣言关键词 + 六阶段生成 SOPA/C 模式产出时
references/eval-loop.md评测闭环:with/without 对照、断言评分、基准表、触发评测与描述优化A 模式造完必读;C 模式大改后
references/provenance.md出处证据链:三源测评、85vs96 对撞、五轮对抗进化史、实战体检案例需要背书/回答"凭什么"时
examples/perfect-audit-report.md满分体检样本(CEO 助理实战案例,含辩证裁量示范)B 模式动笔前对样;教别人写报告时

5. 快速判例

  • "帮我看看 xx skill 写得怎么样" → B
  • "把 xx skill 升级到高阶水平" → B → C → 复诊
  • "xx 和 yy 重复吗,留哪个" → D(结论移交 stocktake 执行)
  • "我想把这套 SOP 做成技能" → A(选型→施工→评测→收录全管线;收录登记走 skill-ingest)
  • "全库巡检一遍重要技能" → 逐个 B,汇总成体检台账;触发词含"巡查/巡检/体检/审计"

6. 产出物标准

  • 体检报告:按 checklist.md 末尾模板输出;每个发现必须带证据行号与优先级;无发现处明确写"通过",不许沉默。
  • 处方:每条补丁一个最小 diff;修 P0 不许顺手改无关内容。
  • 会诊:五维雷达对比表 + 一句话裁决 + 建议动作(保留/合并/退役,执行移交 stocktake)。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Better Skill AI skill do?

Skill 工艺定版标准(Better 家族·技能医生)。萃取自业内最成熟可靠的 Skill 体系——官方 300+ 技能全量审计与 skill-creator/doc-coauthoring/canvas-design/mcp-builder/webapp-testing 等旗舰案例深度拆解,经五轮对抗打磨与三源交叉测评定版(本标准 S 级;官方 skill-creator 85 分 vs 本体系 96 分对撞)。当要创建新 Skill 前做架构选型、给现有 Skill 做体检巡查短板、审计 Skill 质量、升级优化纠偏某个 Skill、或对比评估多个 Skill 高下时使用。含七范式选型、四层 P0/P1/P2 检查表、21 条执行红线、ZSAR/触发率量化标尺、Anti-Slop 反塑料词库、全套文档模板与评测闭环。造前咨询→施工→评测→触发优化→体检→处方→会诊全管线(技能创建默认入口),具工程化落地能力。

Why use Better Skill on TypingMind?

Because you install it once and use it with any model. Better Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Better Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/YTruman/better-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Better Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Better Skill?

As many as you like. As long as a model supports skills, you can use Better Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Better Skill AI skill free?

Yes. It is published on GitHub by YTruman under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇