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 agentmods add skills/vibeinging/yiyi/skill_creatornpx skills add vibeinging/YiYi --skill skill_creatorgit clone --depth 1 https://github.com/vibeinging/YiYiWrote 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/vibeinging/yiyi/skill_creator)<a href="https://agentmods.dev/skills/vibeinging/yiyi/skill_creator"><img src="https://agentmods.dev/badge/skills/vibeinging/yiyi/skill_creator.svg" alt="Measured on agentmods" 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 | $0.00106 | $0.02517 |
| Opus 5 | $0.00053 | $0.01259 |
| Sonnet 5 | $0.00021 | $0.00503 |
| Haiku 4.5 | $0.00011 | $0.00252 |
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 6d 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
创建新技能并迭代改进的核心技能。
YiYi 技能系统说明
YiYi 的技能目录位于 ~/.yiyi/active_skills/，每个技能是一个包含 SKILL.md 的文件夹。SKILL.md 使用 YAML frontmatter 定义元数据（name, description, metadata），正文为 Markdown 指令。
技能结构：
skill-name/
├── SKILL.md (必须)
│ ├── YAML frontmatter (name, description, metadata.yiyi.emoji/requires)
│ └── Markdown 指令
└── 附带资源 (可选)
├── scripts/ - 可执行脚本
├── references/ - 按需加载的文档
└── assets/ - 模板、图标等资源文件
流程概览
创建技能的整体流程：
- 明确技能要做什么、大致怎么做
- 编写技能草稿
- 用几个测试提示词试运行
- 帮助用户定性和定量评估结果
- 在后台运行测试期间，起草定量评估断言
- 使用
eval-viewer/generate_review.py脚本展示结果
- 根据用户反馈重写技能
- 重复直到满意
- 扩大测试集，更大规模验证
你的任务是判断用户处于这个流程的哪个阶段，然后帮助他们推进。灵活应变——如果用户说「不需要跑一堆评估，直接和我聊就行」，那就按他们的方式来。
技能完成后，还可以运行描述优化器来提升技能的触发精度。
与用户沟通
注意根据上下文线索调整沟通方式。默认情况下：
- 「评估」和「基准测试」这类词可以直接用
- 对于 JSON、assertion 等技术术语，先确认用户是否熟悉再使用
- 不确定时简短解释术语即可
创建技能
捕获意图
先理解用户的意图。当前对话可能已经包含用户想要捕获的工作流（比如他们说「把这个变成一个技能」）。如果是，先从对话历史中提取信息——使用的工具、步骤序列、用户做的修正、观察到的输入输出格式。
- 这个技能应该让 AI 能做什么？
- 什么时候应该触发这个技能？（什么用户短语/上下文）
- 期望的输出格式是什么？
- 是否需要设置测试用例来验证？
调研与访谈
主动询问边缘情况、输入输出格式、示例文件、成功标准和依赖。在确定这些之前不要急着写测试提示词。
编写 SKILL.md
基于用户访谈，填写这些组件：
- name: 技能标识符（使用下划线命名，如
my_skill） - description: 触发条件和功能描述。这是主要的触发机制——同时包含技能做什么和什么时候使用。为了对抗「触发不足」的倾向，描述要稍微「积极主动」一些
- metadata: YiYi 特有的元数据
metadata: { "yiyi": { "emoji": "适合的emoji", "requires": {} } } - 技能正文: Markdown 格式的指令
技能编写指南
渐进式披露
技能使用三层加载系统：
- 元数据（name + description）- 始终在上下文中（~100词）
- SKILL.md 正文 - 技能触发时加载（理想<500行）
- 附带资源 - 按需加载（不限大小，脚本可直接执行）
关键模式：
- SKILL.md 控制在 500 行以内
- 从 SKILL.md 清晰引用参考文件，说明何时读取
- 大参考文件（>300行）包含目录
安全原则
技能不得包含恶意软件、漏洞利用代码或任何可能危及系统安全的内容。
编写模式
优先使用祈使语气编写指令。
定义输出格式：
## 报告结构
始终使用这个模板：
# [标题]
## 摘要
## 关键发现
## 建议
示例模式：
## 提交信息格式
**示例 1:**
输入: 添加了使用JWT令牌的用户认证
输出: feat(auth): implement JWT-based authentication
编写风格
解释为什么某些事情很重要，而不是堆砌死板的 MUST。利用心智理论让技能通用而不是局限于特定示例。先写草稿，然后用新鲜眼光审视改进。
What ships with it
17 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.
- agents/analyzer.md 10 KB
- agents/comparator.md 7.1 KB
- agents/grader.md 8.8 KB
- assets/eval_review.html 6.9 KB
- eval-viewer/generate_review.py 16 KB runs code
- eval-viewer/viewer.html 44 KB
- LICENSE.txt 11 KB
- references/schemas.md 12 KB
- scripts/__init__.py 0 B runs code
- scripts/aggregate_benchmark.py 14 KB runs code
- scripts/generate_report.py 13 KB runs code
- scripts/improve_description.py 11 KB runs code
- scripts/package_skill.py 4.1 KB runs code
- scripts/quick_validate.py 3.9 KB runs code
- scripts/run_eval.py 11 KB runs code
- scripts/run_loop.py 13 KB runs code
- scripts/utils.py 1.6 KB runs code
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.
- 6d ago First seen · 295 lines · 106 tokens per session scan A 1b99bfff84cf
skill_creator is a skill published in the GitHub repository vibeinging/YiYi (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 106 tokens to every session and 2,517 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.
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…