Not in the top 1,000 by GitHub stars
Liuxiangjian-ai/official-document-skill
一个面向公文写作的skill，基于数百篇《人民日报》等报刊文章总结而来。根据文种、场景和材料，生成结构规范、表达稳妥、内容具体、去 AI 味的公文。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
cbe5f8cd8aa7 → cbe5f8cd8aa7
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → cbe5f8cd8aa7
No earlier version was observed for comparison.
433GitHub stars
15stars in 7 days
1skill in this repository
0commits in 30 days
Heat
6.1- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
official-document-skill
When your agent uses it
Draft, revise, polish, humanize, and quality-check Chinese official documents and government-style practical writing (公文、党政机关公文、事务文书、申论应用文、人民日报风格政务表达), producing deliverable drafts with correct document type, format, restrained institutional tone, concrete facts, People's Daily-inspired expression discipline, humanizer-style AI-pattern cleanup, and reduced AI-flavored phrasing. Use when the user asks for 通知、通报、报告、请示、批复、函、纪要、决定、通告、议案、倡议书、工作方案、工作计划、工作总结、简报、讲话稿、发言稿、汇报材料、调研报告、宣传稿、公开信、感谢信、信访回复、理论评论、政策解读, or asks to 一键生成/润色/改写/降AI味/减少AI味/人味/自然表达/人民日报风格/检查格式/生成可交付公文.
What it loads into context
Frontmatter
219 tokensAlways available to the agent
SKILL.md
7,534 tokensWhen the skill is activated
Reference documents
3,858 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Workflow
- Output Defaults
- Document-Type Decision
- Formal Format Rules
- People's Daily-Inspired Expression Patterns
- Anti-AI Style Standard
- Humanizer Pass for Official Documents
- Positive Rewrite Rules
- Type-Specific Drafting Templates
- Useful Openings
- Useful Closings
- Heading Methods
- Internal Scoring Rubric
- Final Quality Checklist
- User Input Template
Files
LICENSEasset1,070 bytesREADME.mddoc12,006 bytesSKILL.mdcore33,121 bytesSKILL.mdcore33,121 bytesSKILL.mdcore33,121 bytesSKILL.mdcore33,121 bytesexamplesasset5,453 bytestests.mddoc1,958 bytes
Read SKILL.md
# 公文写作
## Purpose
Generate or revise Chinese official documents that are structurally correct, usable as a deliverable, fact-grounded, restrained in tone, and low in AI-flavored boilerplate. Combine two source bases:
- Formal public-document writing rules: document-type choice, official format, upward/downward/parallel writing, closing formulas, and common format errors.
- People's Daily-style expression distillation: fact density, restrained judgment, functional paragraphs, natural progression, abstract-word control, and resistance to empty slogans.
- Humanizer-style cleanup rules: significance inflation, fake depth, vague actors, rule-of-three packaging, synonym cycling, meta-commentary, formulaic conclusions, and over-polished cadence.
## Core Workflow
1. Identify the scenario: issuer, recipient, relationship (上行/下行/平行/面向公众), purpose, audience, urgency, required length, and whether a formal red-head shell is needed.
2. Choose the document type. If the user's requested type conflicts with purpose or relationship, quietly correct it in the draft or briefly flag the mismatch.Skills included
- official-document-skill
Repository facts
- License
- MIT
- Created
- Jun 7, 2026
- Last pushed
- Jun 12, 2026
- Forks
- 32
- Open issues
- 1
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 3 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 6 network referencesin 1 file: README.md:3
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 6 signals by file
README.md
- Network accessline 3
<p align="center"> <img src="https://img.shields.io/badge/版本-V1.3-blue" /> - Network accessline 4
<img src="https://img.shields.io/badge/版本-V1.3-blue" /> - Network accessline 5
<img src="https://img.shields.io/badge/语言-中文-blue" /> - Network accessline 6
<img src="https://img.shields.io/badge/场景-公文写作-green" /> - Network accessline 7
<img src="https://img.shields.io/badge/文种-20+-red" /> - Network accessline 8
<img src="https://img.shields.io/badge/语料-优秀公文案例-yellow" />
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 6 facts
- Network access in prose of documentationREADME.md:3Low confidence
- Network access in prose of documentationREADME.md:4Low confidence
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:6Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:8Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
