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/ht426/skillseed/processing-pdfsnpx skills add ht426/skillseed --skill processing-pdfsgit clone --depth 1 https://github.com/ht426/skillseedWhat 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 | $0.00096 | $0.00684 |
| Opus 5 | $0.00048 | $0.00342 |
| Sonnet 5 | $0.00019 | $0.00137 |
| Haiku 4.5 | $0.00010 | $0.00068 |
Grade A, and why
processing-pdfs 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.
What it actually says
processing-pdfs
从 PDF 提取表格和文字内容, 输出结构化数据 (CSV / JSON / Markdown)。聚焦发票、收据、报表类 PDF。
何时使用
当用户想: 从 PDF 提取表格、读取 PDF 文字、解析发票/收据、把 PDF 内容转成结构化数据时。
工作流
1. 确认目标
- PDF 文件路径 (或用户已打开的文件)
- 要提取什么: 表格 / 纯文字 / 两者
- 输出格式: CSV / JSON / Markdown / 直接展示
2. 选工具
加载 references/extraction-tools.md 选工具。速记:
- 表格: pdfplumber —— 表格提取最稳
- 文字: PyMuPDF (fitz) —— 比 pdfplumber 快数倍
- 扫描件 / 图片 PDF: 需 OCR (pytesseract + pdf2image)
3. 提取
- 先探查 PDF: 页数、是否含可选中的文字 (还是扫描件)
- 表格:
pdfplumber.open(path).pages[i].extract_tables() - 文字:
page.extract_text()或 PyMuPDFpage.get_text() - 发票特有: 字段对齐 (发票号、金额、日期、商品明细) 常需按坐标或正则定位
4. 结构化输出
- 表格 → CSV 或 Markdown 表
- 发票字段 → JSON (键值对)
- 多页 → 合并或分页输出, 注明页码
5. 校验
- 抽查 1-2 页对照原文, 确认无遗漏 / 错位
- 表格列对齐正确, 数字无串行
- 扫描件 OCR 结果须人工复核
References 索引
| 文件 | 内容 | 何时加载 |
|---|---|---|
references/extraction-tools.md |
PDF 提取工具用法速查 (pdfplumber / PyMuPDF / OCR) + 发票字段定位技巧 | 步骤 2 选工具时 |
重要约束
- 优先用 pdfplumber 提取表格 (最稳); 纯文字用 PyMuPDF 更快
- 扫描件 (extract_text 返回空) 必须走 OCR, 不要硬用 extract_text
- 输出前对照原文抽查, 避免静默错位
- 路径用正斜杠 (含 Windows)
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.
- 2d ago First seen · 55 lines · 96 tokens per session scan A b3f5ac3f1b0d
processing-pdfs is a skill published in the GitHub repository ht426/skillseed (11 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 684 once invoked, about $0.0005 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…