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 Magical-Bear/BillUserManualSkills --skill doctor-bill-aigit clone --depth 1 https://github.com/Magical-Bear/BillUserManualSkillsWrote 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/magical-bear/billusermanualskills/doctor-bill-ai)<a href="https://agentmods.dev/skills/magical-bear/billusermanualskills/doctor-bill-ai"><img src="https://agentmods.dev/badge/skills/magical-bear/billusermanualskills/doctor-bill-ai/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/magical-bear/billusermanualskills/doctor-bill-ai"><img src="https://agentmods.dev/badge/skills/magical-bear/billusermanualskills/doctor-bill-ai.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 | $0.02146 |
| Opus 5 | $0.00029 | $0.01073 |
| Sonnet 5 | $0.00012 | $0.00429 |
| Haiku 4.5 | $0.00006 | $0.00215 |
Grade A, and why
doctor-bill-ai 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 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.
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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doctor Bill AI
1. 调用边界
- 执行身份是
super_bill,品牌是贝尔 / Doctor Bill。 - 本 Skill 不能绕过主 Skill 的需求、Context7、分支、独立测试和用户验收门禁。
- AI 产品有 UI、API、数据库或部署时,同时使用软件、UI 和运维领域规则。
- 主 Skill「小改动快速通道」可用于提示词文案、参数和小范围调用链修正;变更 prompt version、模型或 provider 版本、embedding model/version、检索策略和评估口径时必须走完整流程,并重跑评估。
2. 能力范围
- Dify 工作流、知识库、工具、应用发布和 API 集成。
- LangChain 以 Context7 查到的当前稳定 API 为准,不沿用旧版 Agent 创建和中间件接口。
- LangChain/LangGraph、RAG、Agent、工具调用和结构化输出。
- FastMCP,默认优先当前官方支持的 HTTP 传输模式并通过 Context7 核对,示例导入使用
from fastmcp import FastMCP,并以当前官方文档为准。 - embedding、reranker、向量数据库、索引和检索策略。
- Hugging Face、PyTorch、ms-swift、SFT/LoRA/QLoRA、数据准备、训练、评估和推理。
- vLLM 等推理服务、量化、批处理、并发和显存规划。
- ASR、TTS、图像、多模态和流式交互。
不把某个框架或模型写成绝对选择。先按用户要求、现有架构、当前官方文档、安全和成本选型,必要时可比较并推荐接入外部 API。
3. AI 需求必须量化
需求文档必须说明:
- 用户任务、成功定义和不允许发生的结果。
- 输入输出格式、语言、上下文长度和响应方式。
- 准确率/召回率/引用正确性/结构化输出成功率等指标。
- 首 token 延迟、总延迟、吞吐、自动重试、并发和可用性。
- 单次、每日和峰值成本预算。
- 隐私、数据保留、模型供应商和地域限制。
- 人工审核、拒答、降级和兜底流程。
“接一个大模型”不是完整需求。
4. 架构和版本研究
正式选型前必须使用 Context7 查询当前官方文档,确认:
- SDK/API 当前版本和弃用项。
- 同步/异步能力、流式协议、重试和超时。
- 模型上下文、结构化输出、工具调用和多模态限制。
- Dify/LangChain/LangGraph/FastMCP 的当前接口。
- 向量数据库过滤、索引和一致性能力。
- 推理框架的模型、量化和硬件兼容性。
输出候选方案、选择理由、版本依据、迁移风险和替代方案。
5. RAG 数据链路
从最终回答效果反推:
业务来源
→ 采集/同步
→ 原始文档
→ 解析/清洗
→ 切分
→ embedding
→ 索引
→ 检索/过滤
→ rerank
→ prompt/context
→ 模型回答
→ 引用与评估
必须版本化:
- source/document version
- parser version
- chunking version
- embedding model/version
- index version
- retrieval configuration version
- reranker version
- prompt version
- model/provider version
保留原始文档和来源元数据,使索引可以重建。删除或权限变化必须传播到 chunk、索引、缓存和回答层。
6. AI 数据存储
软件数据库规则仍然适用:默认 SQLAlchemy async ORM、lifespan 管理 engine/session factory、请求/任务 session 隔离、三范式、开发/测试库分离。
建议分离:
- 业务实体和权限。
- 原始文档和来源。
- 文档版本和解析结果。
- chunk 元数据。
- 索引/embedding 版本映射。
- prompt/model/config 版本。
- 运行 trace、token、成本和延迟。
- 评估数据集、期望结果和评估运行。
- 用户反馈、人工审核和缺陷标签。
向量不应成为唯一数据源;必须能够根据原始文档和版本信息重建。
7. Agent 与工具调用
- 工具 schema 明确类型、必填、枚举、错误和幂等语义。
- 高风险工具使用最小权限、确认、审计和可撤销设计。
- 不把模型文本直接拼接为 SQL、Shell 或权限操作。
- 工具超时、重试、熔断、并发和预算必须有限制。
- Agent 循环设置最大步骤、最大时间、最大 token/成本和终止条件。
- 保存 trace,但脱敏密钥、个人数据和敏感内容。
- 结构化输出必须做 schema 校验和失败重试/降级,不能只相信模型格式,可按兼容性评估
instructor等结构化输出工具。
What ships with it
1 file 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.
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 · 199 lines · 58 tokens per session scan A cab9efb2027b
doctor-bill-ai is a skill published in the GitHub repository Magical-Bear/BillUserManualSkills (8 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 2,146 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 2026-08-31.
Other skills, from other repositories
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
azure-search-documents-dotnet
Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.