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 simbajigege/book2skills --skill skill-to-workflowgit clone --depth 1 https://github.com/simbajigege/book2skillsWrote 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/simbajigege/book2skills/skill-to-workflow)<a href="https://agentmods.dev/skills/simbajigege/book2skills/skill-to-workflow"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/skill-to-workflow/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/simbajigege/book2skills/skill-to-workflow"><img src="https://agentmods.dev/badge/skills/simbajigege/book2skills/skill-to-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00120 | $0.02266 |
| Opus 5 | $0.00060 | $0.01133 |
| Sonnet 5 | $0.00024 | $0.00453 |
| Haiku 4.5 | $0.00012 | $0.00227 |
Grade A, and why
skill-to-workflow 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 转 Workflow
把一个面向 Agent 的 Skill 转换为可实现的 Workflow 规格。转换的目标不是照抄原文中的编号,而是恢复它的真实执行图,并让每个节点都具有明确责任、结构化输入输出、工具权限、停止条件和失败处理。
输入与默认交付
- 输入可以是 Skill 目录、
SKILL.md、Prompt、SOP、操作手册或用户描述的 Agent 流程。 - 用户指定目标平台时,使用该平台支持的节点、变量、分支和子工作流能力;未指定时输出平台无关规格,不猜测 Dify、Coze、n8n、LangGraph 等具体实现。
- 用户只要求概括时,先给阶段数、主链路和关键回路;用户要求设计或转换时,再给完整节点规格。
- 未明确要求实现、创建文件或部署时,只交付设计,不修改原 Skill,也不创建平台配置。
需要输出完整 Workflow 规格时,读取 references/workflow-spec-template.md。
开始前
- 完整读取源 Skill 及其声明的必读 references;不要只根据
SKILL.md的表层编号拆解。 - 检查源 Skill 使用的 scripts、schema、模板、校验器和正式产物路径。只需读取会改变流程设计的资源。
- 区分三类信息:
- 业务语义与判断规则;
- 执行机制与工具操作;
- 输出格式与验收约束。
- 记录原 Skill 的授权边界、隐私边界、禁止事项和不可破坏的事实来源。
- 不执行源 Skill 的业务任务,除非用户同时要求运行或验证转换后的 Workflow。
转换流程
1. 建立源 Skill 契约
提取:
- 触发条件与不适用范围;
- 必需输入、可选输入和输入选择规则;
- 最终产物及其消费者;
- 事实来源、数据契约和质量门槛;
- 禁止行为、权限限制和人工确认点;
- 可复用历史产物与幂等要求。
这些约束必须在 Workflow 中找到承接位置,不能因拆节点而消失。
2. 恢复真实执行图
不要把原文的“七步”机械转换成七个节点。先识别:
- 批次级步骤与单对象循环;
- 串行依赖和可并行任务;
- 条件分支、回退、补充调研和重试;
- 阻断失败、允许继续的部分完成和正常空结果;
- 中间分析状态与正式交付物。
用一句主链路和必要的回路表示真实执行图,再决定节点数量。
3. 划分节点
一个节点应完成一种稳定责任,并产生可验证的状态变化。满足任一条件时优先拆开:
- 判断依据、工具权限或失败策略不同;
- 结果需要单独缓存、复用、人工检查或重试;
- 下游只依赖其中一部分输出;
- 确定性处理与模型判断混在一起;
- 一个节点同时在找事实、做业务判断、评分和写最终报告。
不要拆分纯粹的格式搬运、无法独立验收的思维碎片,或只会增加上下文传递成本的微小步骤。
4. 给节点分类
为每个节点选择主要执行类型:
- **确定性节点:**解析、清洗、计算、字段映射、文件生成、Schema 校验;优先使用代码或平台原生节点。
- **LLM 判断节点:**分类、推理、提炼、取舍和结构化写作;必须约束输入证据与输出 Schema。
- **工具节点:**搜索、网页读取、数据库查询、API 调用或文件解析;只授予本节点需要的工具。
- **人工节点:**需要业务授权、主观定案或高风险外部变更时使用。
- **路由节点:**根据显式状态或规则选择下一步,不承担额外业务分析。
能由确定性逻辑可靠完成的计算、组装和校验,不交给 LLM。
5. 抽取共享能力子工作流
当两个或以上节点重复使用同一种外部机制,并且能够形成稳定输入输出契约时,将机制抽成共享子工作流。例如:
- 搜索规划 → Web Search → URL 去重 → Web Open → 证据提取;
- 文件解析 → 格式规范化 → 字段质量检查;
- 结构化产物组装 → 构建 → 正式校验;
- 通知发送、审批或外部系统写入。
分析节点只提交“需要回答什么”,共享子工作流负责“如何调用工具并返回材料”。共享的是获取或处理机制,不是不同节点的业务结论。
共享子工作流至少定义:请求类型、问题或目标、已知上下文、工具与来源偏好、预算、停止条件、返回数据、未解决问题、限制、缓存键和错误状态。
不要在以下情况强行抽象:
- 只有工具名称相同,但输入语义、权限或失败风险完全不同;
- 共用后会让子工作流直接替业务节点作结论;
- 一次性操作没有稳定复用价值;
- 抽象会隐藏人工授权或高风险副作用。
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.
- 11d ago First seen · 187 lines · 120 tokens per session scan A c5b96fbbf314
skill-to-workflow is a skill published in the GitHub repository simbajigege/book2skills (162 stars, last pushed 16d ago), licensed MIT. It adds 120 tokens to every session and 2,266 once invoked, about $0.0006 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
marketing-strategy-pmm
Product marketing, positioning, GTM strategy, and competitive intelligence. Includes ICP definition, April Dunford positioning methodology, launch playbooks, competitive battlecards, and international market entry guides. Use when developing positioning, planning product launches, creating messaging, analyzing…
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention.…
email-sequence
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
content-research-writer
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.