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.
npx skills add malue-ai/dazee-small --skill skill-creatorgit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote 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.
[](https://agentmods.dev/skills/malue-ai/dazee-small/skill-creator)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/skill-creator"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/skill-creator/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.
<a href="https://agentmods.dev/skills/malue-ai/dazee-small/skill-creator"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.03139 |
| Opus 5 | $0.00029 | $0.01570 |
| Sonnet 5 | $0.00012 | $0.00628 |
| Haiku 4.5 | $0.00006 | $0.00314 |
Grade A, and why
skill-creator 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 创建器
帮助用户创建新的 Skill 或改进已有 Skill。一个 Skill 就是一组指令,教 Agent 如何完成特定任务。
使用场景
- 用户说「帮我做一个 Skill」「把这个流程变成 Skill」「创建一个 XX 技能」
- 用户对某个已有 Skill 不满意,想要改进
- 用户想把当前对话中的成功工作流固化下来
- 用户问「Skill 怎么写」「SKILL.md 格式是什么」
核心流程
创建 Skill 的过程:
- 捕获意图 — 弄清楚用户想让 Skill 做什么
- 访谈研究 — 追问边界情况、输入输出格式、依赖
- 编写 SKILL.md — 生成文件并保存
- 测试验证 — 用几个真实场景测试
- 迭代改进 — 根据反馈优化
你的任务是判断用户在这个流程的哪个阶段,然后帮他推进。
第一步:捕获意图
如果用户想从零开始,先搞清楚这几个问题(可以从对话上下文推断,不必每个都问):
- 这个 Skill 让 Agent 做什么? — 核心功能
- 什么时候应该触发这个 Skill? — 用户说什么话、什么场景
- 输出格式是什么? — 文件、文本、还是执行动作
- 有什么依赖? — 需要命令行工具、Python 包、API Key、还是纯 LLM 就够
如果用户说「把这个流程变成 Skill」,从当前对话中提取:用了什么工具、执行了什么步骤、用户做了什么修正、输入输出长什么样。
第二步:访谈研究
主动追问:
- 边界情况怎么处理?
- 有没有示例文件或参考?
- 成功标准是什么?
- 有没有类似的现有 Skill 可以参考?
如果涉及外部工具或 API,确认依赖信息(命令名、包名、API Key 字段名)。
第三步:编写 SKILL.md
SKILL.md 结构
skill-name/
├── SKILL.md (必需)
├── scripts/ (可选 - 确定性/重复性任务的脚本)
├── references/ (可选 - 按需加载的参考文档)
└── assets/ (可选 - 模板、图标等资源文件)
frontmatter 格式
每个 SKILL.md 必须以 YAML frontmatter 开头:
---
name: my-skill-name
description: 清晰描述这个 Skill 做什么、什么时候用它。
metadata:
xiaodazi:
dependency_level: builtin # builtin / lightweight / external / cloud_api
os: [common] # [common] / [darwin] / [win32] / [linux]
backend_type: local # local / tool / mcp / api
user_facing: true
---
字段说明:
name:唯一标识,小写,用连字符分隔(如my-cool-skill)description:触发机制的核心。要包含:做什么 + 什么时候用。写得稍微"积极"一些,让 Agent 更容易触发。例如不要写"生成仪表盘",要写"生成仪表盘。当用户提到数据可视化、报表、图表、监控面板时都应该使用这个 Skill"dependency_level:builtin— 装好就能用,无需额外安装lightweight— 需要 pip install 一个包或系统授权external— 需要安装外部应用/CLI 工具cloud_api— 需要 API Key
os:[common]表示全平台,也可以是[darwin]、[win32]、[linux]backend_type:local表示通过 SKILL.md 指导 Agent 执行
正文编写指南
渐进式加载(Progressive Disclosure):
Skill 的内容分三层加载:
- Metadata(name + description)— 始终在上下文中,约 100 词
- SKILL.md 正文 — Skill 被触发时加载,理想情况 < 500 行
- 附属资源 — 按需读取,无上限
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.
- 9d ago First seen · 364 lines · 58 tokens per session scan A 937d5aa7e91b
skill-creator is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 3,139 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…