skill-builder

skill-builder is a skill for Codex from sanqi-cd/Sanqi-Skills. It costs 90 tokens per session (1,995 once invoked), scanned A, original, MIT.

A workflow for creating or improving an Agent Skill, which is a reusable package of instructions, scripts, references, and tests for a coding agent.

In plain words
What is it for?
Use it to define when a skill should run, design its files, add scripts or reference material, write metadata, and test normal, missing, and boundary cases.
Why use it?
It turns an informal idea into a structured, maintainable, and testable package instead of leaving it as a loose prompt.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex; $skill-name invocation.

Good fit Use it to define when a skill should run, design its files, add scripts or reference material, write metadata, and test normal, missing, and boundary cases.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sanqi-cd/sanqi-skills/skill-builder
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sanqi-cd/Sanqi-Skills --skill skill-builder
Clone the repo
git clone --depth 1 https://github.com/sanqi-cd/Sanqi-Skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/skill-builder/github.svg)](https://agentmods.dev/skills/sanqi-cd/sanqi-skills/skill-builder)
Your own site
<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/skill-builder"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/skill-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/sanqi-cd/sanqi-skills/skill-builder"><img src="https://agentmods.dev/badge/skills/sanqi-cd/sanqi-skills/skill-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.01995
Opus 5 $0.00045 $0.00997
Sonnet 5 $0.00018 $0.00399
Haiku 4.5 $0.00009 $0.00199

Measured 11d ago against content hash 4174ccdfb9c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill-builder/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

默认结构:

skill-name/
├── SKILL.md
├── agents/
│   └── openai.yaml
├── 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/
    ├── 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。

选择适合的工作流模式时读取 references/design-patterns.md

3. 编写标准元数据

顶层只使用 Agent Skills 标准字段:

---
name: skill-name
description: >
  [做什么;用户何时会需要;典型话术;相邻边界;最终交付什么。]
license: MIT
compatibility: [运行时、工具、网络或应用要求。]
metadata:
  author: "author-name"
  version: "1.0.0"
---

要求:

  • name 与目录名完全一致,只含小写字母、数字和单连字符,长度不超过 64。
  • description 非空且不超过 1024 字符,使用具体名词和用户话术,不依赖只有作者懂的简称。
  • 自定义展示信息放进 metadata,所有值使用字符串。
  • 仅在 Skill 确实需要时声明 allowed-tools;不要用它掩盖未说明的依赖。

为支持相应客户端的仓库补充 agents/openai.yaml。所有字符串加引号,default_prompt 必须明确提到 $skill-name;只有用户或项目规范明确要求时才加入品牌色等可选字段。

4. 编写可执行指令

正文使用祈使语气,包含:

  1. 一句话目标。
  2. 开始条件和输入缺失策略。
  3. 有顺序、分支和产出物的工作流。
  4. 错误、降级、重试和停止条件。
  5. 可用“通过/不通过”判断的质量标准。
  6. 最终交付内容、文件路径和已知局限。

避免重复常识、空泛角色扮演和无法验证的“高质量”“深入分析”。正文接近 500 行时必须拆分;引用文件只保留完成任务所需的信息。

5. 实现确定性资源

以下内容优先写成脚本:解析、转换、命名、批处理、结构验证、统计和可重复渲染。脚本必须:

  • 使用明确参数和非零失败码。
  • 不依赖作者机器上的固定绝对路径。
  • 对覆盖文件、网络失败、无效输入和缺失依赖给出可执行错误信息。
  • 在至少一个正常案例和一个失败案例上实际运行。

领域知识、API 规范、长模板和评分量表放 references。输出模板或二进制素材放 assets。删除未被工作流使用的资源。

Read the full file on GitHub · 157 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 157 lines · 90 tokens per session scan A 4174ccdfb9c3

Subscribe to this mod's changes

skill-builder is a skill published in the GitHub repository sanqi-cd/Sanqi-Skills (27 stars, last pushed 9d ago), licensed MIT. It adds 90 tokens to every session and 1,995 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.