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 SummerSec/SumSec-Skills --skill workflow-skill-creatorgit clone --depth 1 https://github.com/SummerSec/SumSec-SkillsWrote 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/summersec/sumsec-skills/workflow-skill-creator)<a href="https://agentmods.dev/skills/summersec/sumsec-skills/workflow-skill-creator"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/workflow-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/summersec/sumsec-skills/workflow-skill-creator"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/workflow-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 | $0.00129 | $0.01405 |
| Opus 5.5 | $0.00052 | $0.00562 |
| Sonnet 5.5 | $0.00026 | $0.00281 |
| Haiku 4.5 | $0.00013 | $0.00140 |
Grade A, and why
workflow-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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Skill Creator
核心角色
将多步骤、有状态、需跨步骤传递数据的复杂任务转化为结构化的流程编排 Skill。
适用场景
以下信号使用本 skill（≥3 个即适用）：
- 任务需要 ≥3 个顺序步骤，步骤间有依赖关系
- 步骤间需传递和累积状态数据（中间分析结果）
- 需要确定性脚本辅助重复操作（路径生成、数据匹配、格式转换）
- 有明确判定规则和领域知识需引用
- 输出需标准化格式（报告模板、JSON 结构）
- 需强制执行顺序，跳步导致分析不完整
不适用场景 — 使用普通 skill-creator：
- 单步操作（格式转换、代码生成）
- 无状态传递的简单指导
- 纯知识检索
六大架构模式
详细原理与反模式见 架构模式参考。
| 模式 | 核心思想 | 解决的问题 |
|---|---|---|
| 1. 进度文件驱动 | 一个 Markdown 文件贯穿全流程，追加不覆盖 | 跨步骤状态丢失 |
| 2. 步骤框架分离 | SKILL.md <200行，每步详细框架独立文件 | SKILL.md 膨胀 |
| 3. 三阶段执行 | 每步：前置校验 → 执行记录 → 后置校验 | 跳步、结果不验证 |
| 4. 脚本自动化 | 确定性任务提取为独立脚本 | 输出不一致 |
| 5. 资源分层 | 元数据→主体→框架→参考 四级加载 | 上下文浪费 |
| 6. 路径一致性 | {progress_file_path} 占位符全程传递 |
路径断裂 |
创建流程（6 步）
详细操作指南见 创建流程详细指南。
Step A: 需求梳理与步骤分解
先收集具体示例（用户原句写法、典型场景、期望输出），再确认任务画像（输入/输出/步骤数）。将任务分解为 3-8 个有明确依赖关系的顺序步骤，识别需跨步骤传递的状态数据。
Step B: 目录结构设计
使用脚手架脚本一键生成标准目录：
python3 ~/.claude/skills/workflow-skill-creator/scripts/scaffold_workflow_skill.py \
--name {skill-name} \
--steps {n} \
--step-names "步骤1,步骤2,..." \
--output ~/.claude/skills/{skill-name}/
脚本生成：SKILL.md 骨架、步骤框架文件、路径生成脚本、进度文件规范、模板文件。生成后逐文件填写具体内容。
Step C: 撰写 SKILL.md
遵循 Skill 模板，保持主体 <200 行。核心区块：角色 → 场景 → 架构模式 → 步骤概要 → 资源索引。用祈使语气，解释"为什么"而非仅仅"必须"。
Step D: 撰写步骤框架文件
每个 references/step_frameworks/stepN_xxx.md 遵循 Step 框架模板。必须包含：校验规则（前置+后置 checklist）、核心执行流程（可复制执行的命令）、完成标准与验收。开头必须有 ⚠️ 路径一致性要求 警告块。
Step E: 撰写脚本和模板
必建：路径生成脚本 — 根据输入参数生成确定性进度文件路径。可选：数据匹配脚本、格式转换脚本、校验脚本。模板：进度文件结构模板 + 最终输出模板。
Step F: 迭代优化
创建完成后，用真实场景测试 skill，根据执行表现调整步骤粒度、校验规则和模板。详细方法见 创建流程详细指南 Step F。
参考资源
方法论文档
What ships with it
8 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.
- assets/progress_template.md 802 B
- assets/skill_template.md 2.2 KB
- assets/step_framework_template.md 1.3 KB
- references/architecture_patterns.md 6.1 KB
- references/creation_workflow.md 7.4 KB
- references/progress_file_spec.md 2.0 KB
- references/quality_checklist.md 1.8 KB
- scripts/scaffold_workflow_skill.py 12 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.
- 1mo ago First seen · 99 lines · 129 tokens per session scan A ccf5d7ac5c35
workflow-skill-creator is a skill published in the GitHub repository SummerSec/SumSec-Skills (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 129 tokens to every session and 1,405 once invoked, about $0.0005 per session on Opus 5.5. 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
novel-reviewer
A review and editing workflow for existing novel chapters. It checks story logic, timelines, character states, unresolved clues, world rules, and writing style.
audit-playbook
A code-security audit playbook covering source-code review, runtime checks, software dependencies, deployment settings, and AI-agent security risks.
x64dbg-reversing
Perform dynamic reverse engineering and debugging using X64dbg/X32dbg through natural language commands powered by X64dbg MCP. Use this skill whenever the user wants to: debug executables, analyze program behavior at runtime, set breakpoints, inspect memory and registers, trace execution flow, bypass anti-debug…
video-recap
A workflow that turns a supplied video into a Chinese narrated recap by combining video understanding, story planning, editing, voiceover, and final assembly.
ida-reversing
Perform reverse engineering and binary analysis in IDA Pro using natural language commands powered by IDA MCP. Use this skill whenever the user wants to: analyze executable files, understand function behavior, decompile code, explore cross-references, search for strings or bytes, patch binary code, document reverse…
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.