菜单
Extract text and tables from PDF files, fill PDF forms, and merge multiple PDFs. Use when working with PDF documents or when the user mentions PDFs, forms, or document extraction.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | pdf-processing |
| description | Extract text and tables from PDF files, fill PDF forms, and merge multiple PDFs. Use when working with PDF documents or when the user mentions PDFs, forms, or document extraction. |
| license | Apache-2.0 |
| compatibility | Requires Python 3.11+ and the pypdf package |
| metadata | {"author":"skref-examples","version":"1.0"} |
Procedural knowledge for common PDF tasks.
Use scripts/extract.py to pull the text layer from a PDF:
python scripts/extract.py input.pdf
Map field names to values and write a filled copy. See references/forms.md
for the field-mapping conventions.
Concatenate several PDFs in order, preserving bookmarks where possible.
Turn read-only TweetClaw exports into source notes for approval-gated social publishing workflows.
A reference skill that exercises every supported frontmatter field — the six base Agent Skills fields plus all thirteen Claude Code extensions. Use when testing skref's --allow-claude-fields support or as a worked example of the full Claude frontmatter surface.
Review a pull request for correctness and style, then summarize the findings. Use when the user asks for a PR review, mentions reviewing a diff, or wants feedback on changes before merging.
A deliberately invalid sample. The name uses an uppercase letter and an underscore, and does not match a kebab-case directory. skref validate should report errors for this skill.
Write clear, conventional git commit messages and stage related changes together. Use when the user asks to commit, wants help phrasing a commit message, or mentions conventional commits.
A minimal example skill that greets the user. Use when you want a tiny, valid reference skill to test skref against or to learn the SKILL.md format.