read-document SKILL.md skillA
read-document from knowflow-ai/knowwork is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add knowflow-ai/knowwork/read-document@git:20261114.eacd143Pins git:20261114.eacd143 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- knowflow-ai/knowwork
- Path
runtime-host/plugins/dsh-host/skills/read-document/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261114.eacd143, committed Nov 14, 2026
- Size
- 3,561 bytes
- Repository stars
- 145
- License
- Apache-2.0
读 PDF、Word、PPT、Excel 这类不是纯文本的文件时使用:用户要你看、总结、摘录、查找、核对或比较这些文件里的内容(本机对话的工作文件夹里的、云端对话沙箱里生成或下载的)。纯文本文件(.md、.txt、.csv、.json、代码)直接用 read 读,不用它;云端对话里上传的附件已经给了解析好的文字,按给的路径读;要生成或修改 Office 文件用对应的 office 技能;知识库里的文档用知识库工具。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 读文档:先转成文字再读 `read` 只读得了纯文本。PDF、Word、PPT、Excel 先用辅助脚本转成文字,再按下面的办法读。 > 命令里的 `office/…` 是本技能资源目录(加载技能时给出的 Base directory)下的辅助脚本,运行时按资源目录写成完整路径;其余相对路径都相对当前工作目录。 > **解释器:** 工具列表里有 `load_workspace_dependencies`(本机对话)就先调一次,下面命令里的 `python3` 换成它返回的 `python`。没有这个工具(云端对话的沙箱)就直接用 `python3`。用到的库都已带好,不要 `pip install`,也不要另找系统里的解释器。 > **中间文件:** 转出来的文字放进这次新建的隐藏临时目录:`mktemp -d ./.dsh-read.XXXXXXXX` 会打印出目录名(下文写作 `<临时目录>`),之后的命令都直接写这个名字(每条命令是新的 shell,变量留不下来)。回答完——失败了也一样——只删这个目录(`rm -rf <临时目录>`)。原文件只读、不要改;转出来的文字是给你读的,不交付、不在回答里链接。 ## 转成文字 ```bash python3 office/extract_text.py 文件.pdf <临时目录> ``` 脚本打印结果文件的路径、字数、页数(PDF 才有)和目录(标题,标题太少时是每页开头,都带行号)。几个文件就各跑一次,结果放同一个临时目录。 - PDF:每页前面有一行 `[第 n 页]`; - Word、PPT 转成 Markdown,标题是 `#`,PPT 每张幻灯片前面有 `<!-- Slide number: n -->`;Excel 每个工作表一个 `## 表名`,下面是表格; - `.doc`、`.ppt`、`.xls`、`.wps` 这类旧格式脚本会先转成新格式,不用另外处理。 脚本没成功时看退出码: - `3`:提取不出文字(扫描的 PDF、图片)。不要猜内容:是图片、工具列表里又有 `read_image` 的,用它直接看图;其余的如实告诉用户这份是扫描件或图片、这里读不出文字,要用里面的内容就把它作为附件发到云端对话里(云端对话的附件会自动识别文字); - `4`:转换失败(文件损坏、加了密码)。把脚本给的原因告诉用户。 ## 读 - **不长的(两三万字以内)**:用 `read` 读结果文件全文。 - **长的**:先看脚本打印的目录,用 `read` 的 `offset`、`limit` 按行号读用得上的那几段;找具体的词、数字、条款用 `grep -n` 在结果文件里搜,再读前后几十行。不要从头一段段往下读完整份。 …
Read the whole file at its exact version.
How to install
claude plugin marketplace add https://markdownregistry.com/mp/a/art_6k673dwpsv5dkvqh/3d31e7d5d9e6aaac1a074ef4ff31e8e5bf74296f8c620eeb20374876dbdea832.json
Then /plugin install read-document@markdownregistry-6k673dwpsv5dkvqh in Claude Code. It installs git:20261114.eacd143, the one graded A here, pinned to the commit it was graded at, and leaves it there.
mdr add knowflow-ai/knowwork/read-document@sha256:3d31e7d5d9e6aaacThe line at the top of this page pins the label git:20261114.eacd143, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_6k673dwpsv5dkvqh)
1 badge image fetches in 30 days. What the badge shows.
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it: what changed in knowflow-ai/knowwork/read-document since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.
Got a copy of read-document from somewhere else? Ask it: where did my read-document come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.
Versions
The registry has recorded 1 version of this file, committed on Nov 14, 2026.
Watch this file (sign in, one email per new version)
Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.
Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.
mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml
It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.
Installed this file, say at .claude/skills/read-document/SKILL.md? Drop it here to learn which saved version you have and what changed since. Your browser works out its SHA-256 fingerprint and sends only that; the file itself never leaves your computer.
Or paste its contents
Your agent can run this same check on the agent markdown files you have installed, up to 50 in one ask. Add the registry once:
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry
Then ask it to check the files you have installed. No key and no account.
From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies
In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.
sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies
No sha256sum on your machine? shasum -a 256 prints the same lines.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3561 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
knowflow-ai/knowwork · 145 stars · license Apache-2.0 · pushed 2026-11-14 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6k673dwpsv5dkvqh GET https://markdownregistry.com/api/v1/resolve?ref=knowflow-ai/knowwork/read-document GET https://markdownregistry.com/api/v1/blob/3d31e7d5d9e6aaac1a074ef4ff31e8e5bf74296f8c620eeb20374876dbdea832
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.