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 GarrusHuang/biz-skill-creator --skill biz-skill-creatorgit clone --depth 1 https://github.com/GarrusHuang/biz-skill-creatorWrote 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/garrushuang/biz-skill-creator/biz-skill-creator)<a href="https://agentmods.dev/skills/garrushuang/biz-skill-creator/biz-skill-creator"><img src="https://agentmods.dev/badge/skills/garrushuang/biz-skill-creator/biz-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/garrushuang/biz-skill-creator/biz-skill-creator"><img src="https://agentmods.dev/badge/skills/garrushuang/biz-skill-creator/biz-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 | $0.00143 | $0.06300 |
| Opus 5 | $0.00072 | $0.03150 |
| Sonnet 5 | $0.00029 | $0.01260 |
| Haiku 4.5 | $0.00014 | $0.00630 |
Grade A, and why
biz-skill-creator scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
有接口调用的 Skill，所有接口必须封装为 `scripts/` 下的 Python 脚本，不可只在 SKILL.md 中写 curl 示例。*（无接口的纯 prompt Skill 不需要 scripts/。）* How it starts
The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Biz Skill Creator
业务Skill的全生命周期管理：创建、修改、参数调整、测试验证。支持任意业务领域，首次接触新领域时自动从设计文档提取并积累领域知识。
模式选择
根据用户意图判断进入哪个模式：
| 用户意图 | 模式 |
|---|---|
| "我要做一个新的Skill" / 从零开始 | 创建模式 |
| "帮我改一下这个Skill" / 修改已有 | 修改模式 |
| "换个客户部署" / 只改参数 | 参数调整模式 |
| "先把这个领域的知识导进来" / 只导知识不做Skill | 知识导入模式 |
判断不了就直接问："你是要新建Skill、修改已有Skill、调整参数、还是先导入领域知识？"
灵活度指引： 下面的流程是完整版，但不是每个场景都需要走完每一步。流程服务于用户，不是用户服务于流程。根据实际情况灵活调整：
- 用户已经带着完整方案来了 → Phase 1 仍然逐步检查三维度（数据来源/判断逻辑/异常处理），但用户已明确的维度标 ✅ 跳过展开，只追问未覆盖的
- 用户说"不用测试，先用起来" → 尊重用户的判断，交付后提醒后续可以补测
- Skill 的输出是主观的（写作风格、设计审美） → 不强求断言式评分，人工审核更合适
- 纯 prompt 逻辑、无接口调用 → Phase 3 和 scripts/ 可以跳过
- 简单参数调整 → 不需要完整测试流程
如果某个标记"必须"的步骤在当前场景下明显多余，跳过它是合理的。下面各阶段会标注何时可以省略。
创建模式
Phase 0: 领域知识准备
在需求追问之前，先确保拥有足够的领域知识。（纯工具类 Skill——不涉及专业业务术语和领域概念——可跳过本阶段。）
0.1 初步了解场景：
先问用户一句话描述要做什么，判断涉及哪个业务领域、哪些业务模块。
0.1b 从对话上下文捕获意图：
当前对话中可能已包含用户想要封装为Skill的工作流（如用户说"把刚才的流程做成Skill"）。如果是，先从对话历史中提取：
- 使用了哪些工具和脚本
- 执行步骤的顺序
- 用户做过的修正
- 观察到的输入/输出格式
提取后让用户确认并补充遗漏，再进入后续Phase。如果不是从对话捕获，正常继续。
0.2 检查领域知识是否已有：
领域知识存放在 {SKILL_DIR}/references/domains/ 下，按领域分目录：
{SKILL_DIR}/references/domains/
├── <领域名>/
│ ├── _index.md # 该领域总览（模块清单、通用术语、模块间关联）
│ ├── <模块1>.md # 模块知识文件
│ ├── <模块2>.md
│ └── ...
└── <其他领域>/
└── ...
检查用户场景涉及的领域目录和模块文件是否存在。
0.3 根据检查结果决定下一步：
- 领域目录和模块文件已存在 → 读取
_index.md和对应模块文件，直接进入Phase 1 - 领域目录不存在或模块文件缺失 → 向用户要该领域/模块的设计文档（产品文档、需求文档、数据库设计文档等均可），然后执行0.4
0.4 从设计文档提取领域知识（如需）：
从用户提供的文档中提取以下信息，写入对应的知识文件：
| 提取什么 | 不提取什么 |
|---|---|
| 该模块有哪些业务对象/概念（名称+一句话解释） | 具体业务规则（流程怎么走、字段怎么算） |
| 业务对象之间的关联关系 | 具体的流程步骤 |
| 该模块涉及的专业术语 | 具体的字段定义和取值范围 |
| 与其他模块的关联点 | 具体的接口定义 |
| 该模块场景下应该追问的方向 | UI/页面相关的内容 |
模块知识文件格式：
# [模块名]
## 业务对象
| 对象 | 说明 | 关联 |
|------|------|------|
## 术语
| 术语 | 含义 |
|------|------|
## 与其他模块的关联
- [描述]
## 追问方向
涉及[xxx]时问：[...]
领域总览 _index.md 格式：
# [领域名] 领域知识总览
## 模块清单
| 模块 | 知识文件 | 涉及的业务对象 |
|------|---------|--------------|
## 通用术语
| 术语 | 含义 |
|------|------|
## 模块间关联
- [描述]
What ships with it
25 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.
- _meta.json 123 B
- agents/analyzer.md 10 KB
- agents/comparator.md 7.1 KB
- agents/grader.md 8.8 KB
- assets/eval_review.html 6.9 KB
- docs/PRD-biz-skill-creator-v1.1.md 15 KB
- eval-viewer/generate_review.py 16 KB runs code
- eval-viewer/viewer.html 44 KB
- references/output-patterns.md 1.8 KB
- references/progressive-disclosure-patterns.md 2.7 KB
- references/schemas.md 13 KB
- references/templates.md 2.0 KB
- references/testing-basics.md 4.4 KB
- references/testing-iteration.md 5.3 KB
- references/testing-tools.md 15 KB
- references/workflows.md 816 B
- 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 6.6 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.
- 12d ago First seen · 490 lines · 143 tokens per session scan A 394c39f26d0f
biz-skill-creator is a skill published in the GitHub repository GarrusHuang/biz-skill-creator (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 143 tokens to every session and 6,300 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ultimate-seo-geo
Audits and optimizes websites for search engine visibility (SEO) and AI search citation (GEO), covering technical health, E-E-A-T content scoring, domain authority, structured data, rich results, and entity signals. Use when running SEO audits, diagnosing traffic drops or ranking losses, generating Schema.org JSON-LD…
ilana
Ìlànà is a strict software engineering process operating system for coding agents. Load it whenever work touches requirements, elicitation, SRS, user stories, traceability, architecture or interface design, UI design principles, coding standards, code review, testing (unit, integration, system, acceptance), test…
eli5
Explain any topic, code, concept, or error tailored to a specific audience's level of understanding. Use this skill whenever the user says 'explain like I am', 'ELI5', 'explain this to my', 'break this down for', 'dumb it down', 'simplify this for', or asks you to explain something to a specific person or audience…
mentor
Use when the user asks how to learn a technology, wants a docs-first learning direction, mentorship compass, reading path, roadmap, or curated resources for a technical subject. Triggers: "how do I learn X", "what should I read for X", "learning path for X", "docs to learn X", "resources to learn X", "best way to pick…
bumblebee
Surgical phrase splicing from real movies and TV shows via yarn.co. Takes any English phrase and slices it into the longest possible runs of words actually spoken on screen, then assembles a final reel where every word is delivered by a real actor. Triggers — "splice a line from movies", "make a fragmovie", "build a…
douyin-pro
A Douyin data and content analysis tool for looking up public videos, comments, users, searches, trending lists, live streams, and creator metrics. Douyin is the Chinese short-video platform also known internationally as TikTok.