← Back to Skills Marketplace
leaproud

Official doc generator

by leaproud · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
113
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install official-doc-generator
Description
专门用于自动生成体制内讨论材料并按照公文格式自动排版的技能。支持会议纪要、发言稿、讨论提纲、工作汇报等多种文档类型,遵循GB/T 9704-2012标准、党政机关公文格式和企业公文规范。使用场景:当用户需要生成体制内正式文档、会议材料、工作报告、发言稿等公文时;当需要按照标准公文格式自动排版时;当需要确保文档符合...
Usage Guidance
This package mostly does what it says — generates and validates GB/T 9704-2012 formatted documents — but take these precautions before using it: - Resolve packaging mismatches: the registry metadata says 'instruction-only' yet many executable Python scripts are included. Treat this as a code package, not just instructions. - Check for missing assets: SKILL.md and scripts reference assets/templates/. Confirm those template files are included locally. If they are missing, inspect the code paths that would fetch templates at runtime and ask where they come from. - Inspect network-update behavior: the enhanced sensitive-word checker documents a '联网更新机制' (periodic online update). Before enabling, open the sensitive_words_check_enhanced.py (or related update code) and verify: which URLs does it contact, is the connection authenticated, and does it upload any content? Prefer to run updates only after review or in an isolated environment. - Run locally in a sandbox first: execute the scripts in an isolated VM or container, with no network access, to confirm local functionality and to see whether the tool runs without trying to fetch remote resources. - Review revision-history behavior: the enhanced generator writes a temporary .docx and records a revision entry. Confirm where revision records are stored (same output dir) and that no unexpected telemetry is sent. - If you will use this on sensitive content or in regulated environments, have a trusted engineer audit the update endpoints and any code that performs HTTP requests before enabling automatic updates. If you want, I can scan the omitted/enhanced scripts (sensitive_words_check_enhanced.py, revision_history.py, and any code that performs network calls) for network endpoints and suspicious operations and summarize the exact URLs and behavior.
Capability Analysis
Type: OpenClaw Skill Name: official-doc-generator Version: 1.0.0 The skill bundle is a comprehensive toolset for generating official Chinese documents (meeting minutes, speeches, reports) according to the GB/T 9704-2012 standard. It includes scripts for document generation using `python-docx`, formatting validation, and local sensitive word checking. While the documentation in `SKILL.md` mentions a network-based update mechanism for sensitive words, the actual implementation in `scripts/sensitive_words_check_enhanced.py` explicitly disables network requests for security reasons, requiring manual imports instead. The code follows safe practices, such as requiring user confirmation for output directories and avoiding hardcoded paths. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
The code files (document generators, format validators, sensitive-word checkers, template manager, revision-history) are coherent with the skill's stated purpose of producing and validating GB/T 9704-2012 style official documents. However, registry/manifest text indicated this is an 'instruction-only' skill while the package contains many runnable Python scripts — a metadata/packaging mismatch. Also SKILL.md and scripts reference assets/templates/ (Jinja2/.docx templates) that are not listed in the provided file manifest, suggesting either missing local templates or that the code may attempt to fetch templates at runtime. Those inconsistencies are unexpected for a doc-generator skill and should be resolved.
Instruction Scope
The SKILL.md and scripts primarily instruct generating documents, asking the user to explicitly supply title, author, and an output directory (the code enforces requiring an explicit output path). That limits undesired file writes. SKILL.md also documents an '联网更新机制' (network update) for the sensitive-word database and an enhanced mode that can 'force-update'. The description does not declare a source URL or remote endpoint for updates, nor does it require explicit credentials — network updates are plausible for this purpose but the absence of an authoritative update source or opt-in flow is an ambiguity to resolve.
Install Mechanism
No install spec or external download is declared; the package contains Python scripts and references standard Python libraries (python-docx, optionally Jinja2). There are no brew/npm/external binary downloads in the metadata. This is low-risk provided users run code locally and inspect it; the main concern is the packaging/metadata mismatch (instruction-only claim vs included scripts) and missing template assets which may lead to runtime network activity if the code attempts to fetch them.
Credentials
The skill does not request environment variables, credentials, or privileged config paths — appropriate for a document generator. The only potentially sensitive capability is the documented feature to 'periodically connect to the network to update the sensitive-words database' and a '--force-update' option in enhanced scripts. That behavior is reasonable for keeping a word list current, but the SKILL.md does not specify the remote source(s), or whether updates are authenticated, nor does it require explicit user consent at runtime. Verify what endpoints the update code contacts and whether any data (documents or partial content) are transmitted during updates.
Persistence & Privilege
The skill does not request 'always: true' and is user-invocable only. It writes documents and revision-history files to user-specified output directories and uses temporary files for hashing; these are normal for document generation. It does not appear to modify other skills or global agent settings. Ensure the revision-history feature and any automatic file creation behavior are acceptable and that files are only written where the user explicitly permits.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install official-doc-generator
  3. After installation, invoke the skill by name or use /official-doc-generator
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Official Document Generator v1.0.0 - Initial release. - Supports automatic generation and formatting of official documents (meeting minutes, speeches, discussion outlines, work reports) per GB/T 9704-2012 and organizational standards. - Built-in template system and standardized formatting (fonts, sizes, headings, indentation, etc.). - Includes compliance and sensitive word checking modules. - Provides Jinja2 template integration and Word (python-docx) output. - User prompts for document info, author signature, format standard, and output directory.
Metadata
Slug official-doc-generator
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Official doc generator?

专门用于自动生成体制内讨论材料并按照公文格式自动排版的技能。支持会议纪要、发言稿、讨论提纲、工作汇报等多种文档类型,遵循GB/T 9704-2012标准、党政机关公文格式和企业公文规范。使用场景:当用户需要生成体制内正式文档、会议材料、工作报告、发言稿等公文时;当需要按照标准公文格式自动排版时;当需要确保文档符合... It is an AI Agent Skill for Claude Code / OpenClaw, with 113 downloads so far.

How do I install Official doc generator?

Run "/install official-doc-generator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Official doc generator free?

Yes, Official doc generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Official doc generator support?

Official doc generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Official doc generator?

It is built and maintained by leaproud (@leaproud); the current version is v1.0.0.

💬 Comments