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/double-coding-lab/flow2spec/f2s-doc-pdfnpx skills add double-coding-lab/Flow2Spec --skill f2s-doc-pdfgit clone --depth 1 https://github.com/double-coding-lab/Flow2SpecWhat 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 | $0.00041 | $0.01301 |
| Opus 5 | $0.00020 | $0.00651 |
| Sonnet 5 | $0.00008 | $0.00260 |
| Haiku 4.5 | $0.00004 | $0.00130 |
Grade A, and why
f2s-doc-pdf 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
执行口径:技术方案文档统一落在
.Knowledge/req-docs/;规则能力仍由配置根rules/skills加载。
编排(主 / 子 agent)
- 两字段(
subAgent/switchAgentVerification)语义以统一入口为唯一事实源:Cursor/Claude 读配置根rules/f2s-flow2spec-unified-entry.*;Codex 读.codex/topics/f2s-flow2spec-unified-entry.md(与上同源,flow2spec init镜像)。本文不复述。 - 默认不拆子:追问-落盘必须在主 agent 内完成(子 agent 无法向用户追问)。
- 可选拆子:仅当
subAgent=true且 PDF 规模超阈值(> 50 页 或 > ~5MB 文本)时启用;子 agent 仅负责 PDF→MD 首稿并落盘.Knowledge/req-docs/<名>.md,不向用户追问、不写「流程说明」章节;主 agent 接手后续追问与流程图补写。 - 校验默认由落盘侧 agent 自验;本 SKILL 不绑定交叉校验。
将 PDF 技术方案文档转为 Markdown(并补全流程说明)
用户会在本技能后附带一个参数:PDF 技术方案文档的本地路径(如 ~/Downloads/技术方案.pdf,或 .Knowledge/req-docs/某草稿.pdf)。请按以下步骤执行,将 PDF 转为 Markdown 并保存到 .Knowledge/req-docs/,必要时引导用户补全流程说明。
步骤 1:读取 PDF 并转为 Markdown
- 若启用拆子(PDF > 50 页 或 > ~5MB),子 agent 仅负责 PDF→MD 首稿并落盘
req-docs/<名>.md,不追问、不写流程说明;主 agent 接手后续步骤。读取用户传入的 PDF 文件,提取其中的文字内容(表格、章节、列表、代码块等尽量保留结构),整理为 Markdown 格式。 - 保存到
.Knowledge/req-docs/,推荐路径:.Knowledge/req-docs/<方案名>.md。文件名为原 PDF 文件名去掉.pdf后加.md。 - 若目录不存在,先创建再写入。
- 保存后告知用户:「已将该 PDF 转为 Markdown 并保存为
xxx.md。」
步骤 2:向用户提问获取流程图(可选但推荐)
PDF 内嵌的流程图无法被直接解析为步骤与分支,若需按图实现代码,需用户配合提供。
- 向用户说明:「文档中可能包含流程图,我无法从 PDF 中解析图中的步骤与分支。若您后续会根据技术方案实现代码(见
implement-tech-design规则),建议补全流程说明:
- 方式一:将相关流程图以图片形式发到本次对话中,我将解析后以文字形式写入上述 MD;
- 方式二:直接以文字描述每个接口/流程的步骤(如:1. 是否登录 2. 查某表 3. 判断某字段 → 返回结果),我将原样写入上述 MD。
若文档无流程图或暂不提供,可回复「跳过」,我将结束本技能。」
- 若用户回复「跳过」或明确表示无需流程说明:告知用户「在对话中提供上述 MD 路径并说明按技术方案实现代码,我将按
implement-tech-design规则执行。」并结束。 - 若用户提供流程图(图片或文字):进入步骤 3。
步骤 3:将流程说明写入该 MD
- 若用户提供的是图片:解析图片中的步骤、判断分支与返回,整理为文字步骤。
- 若用户提供的是文字:直接采用。
- 在该 MD 文件末尾(或新增「流程说明」章节)追加流程内容,格式示例:
## 流程说明(由用户提供 / 由流程图解析)
### 示例接口 A
1. 前端发起请求
2. 后端:查询某表最后一条记录
3. 判断:是否有某 ID?是 → 返回 true,否 → 返回 false
4. 返回结果
### 示例接口 B
1. 是否登录 → 否 返回 401
2. 是否过期 → 是 返回 403
…
- 保存后告知用户:「流程说明已写入
xxx.md。接下来请在对话中提供该 MD 路径并说明要按技术方案实现代码,我将按implement-tech-design规则执行。」
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.
- 2d ago First seen · 71 lines · 41 tokens per session scan A 075af114f6b4
f2s-doc-pdf is a skill published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 1,301 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.