skill-builder SKILL.md skillA
skill-builder from sanqi-cd/sanqi-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sanqi-cd/sanqi-skills/skill-builder@v1.1.0Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sanqi-cd/sanqi-skills
- Path
skill-builder/SKILL.md- Versions recorded
- 4
- Latest version
- v1.1.0, committed Sep 29, 2026
- First version recorded
- Jun 4, 2026
- Size
- 8,530 bytes
- Repository stars
- 28
- License
- MIT
通过渐进式需求澄清、工作流设计、资源拆分、实现和评测，创建或优化高质量 Agent Skill。适用于“创建一个 skill”“把工作流封装成 skill”“优化 SKILL.md”“补充 scripts、references、assets 或 evals”等请求。Use when a user wants a standards-compliant, maintainable, testable Agent Skill package rather than prompt text alone.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Agent Skill 构建器
## 目标
把一个想法或已有 Skill 直接推进到结构合规、指令清晰、资源克制、脚本可靠、评测可复现的完整能力包。除非关键信息确实无法推断，不要停在建议或模板阶段。
## 核心原则
- 先读现状：修改已有 Skill 时，先完整读取 `SKILL.md`、已引用资源、脚本、测试和仓库约定。
- 只问阻塞问题：能从上下文合理推断的内容直接处理；必须提问时每轮不超过 3 个。
- 渐进披露：主文件保留触发、决策、流程和质量门槛，长知识放 references，确定性操作放 scripts。
- 验证比例随风险增长：至少覆盖正常输入、缺失输入和边界输入；共享脚本需要单元测试。
- 描述决定发现：`description` 同时写清任务、典型触发、边界和交付结果，不塞入完整工作流。
- 自动推进：用户已经授权实施时，各阶段通过后直接进入下一阶段，不重复索要确认。
## 工作流程
### 1. 建立任务契约
从用户输入和现有文件中提取：
- 用户要反复完成的具体任务。
- 典型触发话术与相邻但不应触发的请求。
- 必需输入、可选输入和合理默认值。
- 最终交付物、保存位置和完成信号。
- 依赖的工具、网络、凭据、运行时或应用。
- 至少 3 条可判定的质量标准和主要失败模式。
只有触发边界、交付格式或高风险行为仍不明确时才提问。用户给出完整规格时直接进入设计；用户只给一句模糊想法时，优先询问“最终交付什么”“谁会在什么场景触发”“什么算成功”。
产出一份内部任务契约。只有存在会改变实现方向的互斥选择时才展示给用户确认，不把确认仪式当成固定门槛。
### 2. 设计最小能力包
先区分目标：可移植的 Agent Skills 包只要求根目录有 `SKILL.md`；下面是需要适配 Codex 展示并满足本仓库发布门禁时采用的 Sanqi 完整结构，不是开放标准的强制目录：
```text
skill-name/
├── SKILL.md
├── agents/
│ └── openai.yaml # 仅在目标客户端需要时
├── scripts/ # 仅在确定性操作能提高可靠性时添加
├── references/ # 仅放按需读取的领域知识或长规范
├── assets/ # 仅放最终输出会直接使用的模板或素材
└── evals/ # 本仓库的发布约定
├── evals.json
└── trigger-evals.json
```
不要为了目录完整而创建空目录。脚本、引用和资产必须在主文件中说明何时使用；每个引用从 `SKILL.md` 直接链接，避免多层引用链。
…Read the whole file at its exact version.
How to install
mdr add sanqi-cd/sanqi-skills/skill-builder@sha256:4309b595c8e3c459The line at the top of this page pins the label v1.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_erdxw3ywnv7ucfmz)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jun 4, 2026 and Sep 29, 2026, about one every 39 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.1.0 latest | 2026-09-29 | 297b429 | 8,530 B | A | view · diff |
| v1.0.0 | 2026-08-03 | df6d69c | 7,647 B | A | view · diff |
| git:20260604.010b92e | 2026-06-04 | 010b92e | 8,410 B | A | view · diff |
| git:20260604.7d1dc62 | 2026-06-04 | 7d1dc62 | 8,164 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8530 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
sanqi-cd/sanqi-skills · 28 stars · license MIT · pushed 2026-10-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_erdxw3ywnv7ucfmz GET https://markdownregistry.com/api/v1/resolve?ref=sanqi-cd/sanqi-skills/skill-builder GET https://markdownregistry.com/api/v1/blob/4309b595c8e3c459d50501e3a35a4b3b5dd95d337665c92e5d361442eee0d0b2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from sanqi-cd/sanqi-skills
Every file in sanqi-cd/sanqi-skills