← 返回 Skills 市场
upstage-document-parse
作者
upstage-deployment
· GitHub ↗
· v1.0.4
2563
总下载
3
收藏
5
当前安装
5
版本数
在 OpenClaw 中安装
/install upstage-document-parse
功能描述
Parse documents (PDF, images, DOCX, PPTX, XLSX, HWP) using Upstage Document Parse API. Extracts text, tables, figures, and layout elements with bounding boxe...
安全使用建议
This skill will upload any document you ask it to parse to Upstage's API using your UPSTAGE_API_KEY. Before installing or using it, verify Upstage's privacy/retention policy (SKILL.md notes results are stored for 30 days and download URLs expire quickly) and avoid uploading highly sensitive material unless you accept that third party processing. Keep your API key secret, consider using a scoped/short‑lived key if possible, and revoke/rotate the key if you stop using the skill. If you want stricter controls, do not enable autonomous invocation or restrict the skill's use to interactive sessions only.
功能分析
Type: OpenClaw Skill
Name: upstage-document-parse
Version: 1.0.4
The OpenClaw skill 'upstage-document-parse' is designed to parse documents using the Upstage Document Parse API. The `SKILL.md` clearly outlines its purpose, supported formats, and usage examples, all focused on interacting with the legitimate `api.upstage.ai` endpoint. It requires the `curl` binary and an `UPSTAGE_API_KEY` environment variable, which are standard for API interactions. The instructions for the AI agent are straightforward and do not contain any prompt injection attempts, unauthorized data exfiltration, or malicious command execution beyond its stated function of sending user-specified documents to the Upstage API for processing.
能力评估
Purpose & Capability
Name/description, required binary (curl), and required environment variable (UPSTAGE_API_KEY) align with a document-parsing integration that calls an external HTTP API. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to read local document files (e.g., ~/Documents/report.pdf) and POST them to Upstage endpoints — this is consistent with parsing functionality but does involve uploading user files to a third party. Instructions do not direct the agent to read unrelated system files or secrets beyond the declared API key.
Install Mechanism
Instruction-only skill with no install spec and no code files. This minimizes disk-write risk; required runtime tool is curl (reasonable and declared).
Credentials
Only one environment variable (UPSTAGE_API_KEY) is required and is the expected credential for the described API. The SKILL.md does show an optional local openclaw config location for storing the same key, which is consistent with setup.
Persistence & Privilege
always:false (default) and autonomous invocation is allowed (platform default). The skill does not request permanent system presence, nor does it modify other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install upstage-document-parse - 安装完成后，直接呼叫该 Skill 的名称或使用
/upstage-document-parse触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.4
- Updated installation instructions to use clawhub instead of openclaw.
- No functional or API changes; documentation only.
v1.0.3
- SKILL.md formatting improved for metadata and installation instructions.
- Installation step updated from "clawhub install upstage-document-parse" to "openclaw install upstage-document-parse".
- Minor formatting consistency fixes throughout documentation; no functional changes to the API or usage.
v1.0.2
**Summary:** Removed legacy shell script interfaces and updated documentation for new API-based usage and broader file support.
- Removed all legacy scripts (`parse.sh`, `parse-async.sh`, `parse-list.sh`, `parse-status.sh`)—script-based workflow no longer included.
- Documentation rewritten to reflect the new Upstage Document Parse API, with usage examples for curl and Python instead of shell scripts.
- Expanded supported document types: now handles DOCX, PPTX, XLSX, HWP, in addition to PDFs and images.
- Async API and sync API usage now described using direct HTTP (curl) and Python examples.
- Skill intended for direct API or SDK use; script usage and command-line flags are no longer documented.
v1.0.1
- Added installation instructions for the skill using clawhub.
- Expanded API key setup section with clear steps and alternative configuration methods.
- Included usage examples showing how to ask the agent to parse documents directly.
- Clarified that the API key can be set via environment variable.
- General documentation improvements and reorganization for clarity and ease of use.
v1.0.0
Initial release.
- Parse PDFs and images via Upstage Document Parsing API to extract text, tables, figures, and structured content.
- Supports multiple output formats: JSON, Markdown, HTML, and plain text.
- Command-line scripts for synchronous and asynchronous document processing, including status checks and batch support.
- Optional flags for OCR control, coordinate extraction, base64 encoding of tables/figures, and custom output paths.
- Requires UPSTAGE_API_KEY for authentication.
- Supports various document element types (paragraphs, tables, figures, charts, headers, etc.).
- Async API for large documents with batching and job management features.
元数据
常见问题
upstage-document-parse 是什么？
Parse documents (PDF, images, DOCX, PPTX, XLSX, HWP) using Upstage Document Parse API. Extracts text, tables, figures, and layout elements with bounding boxe... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2563 次。
如何安装 upstage-document-parse？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install upstage-document-parse」即可一键安装，无需额外配置。
upstage-document-parse 是免费的吗？
是的，upstage-document-parse 完全免费（开源免费），可自由下载、安装和使用。
upstage-document-parse 支持哪些平台？
upstage-document-parse 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 upstage-document-parse？
由 upstage-deployment（@upstage-deployment）开发并维护，当前版本 v1.0.4。
推荐 Skills