Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Zsxq Smart Publish

ASecurity

Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.

92 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentspythongobashapi

Works with

cliapi

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add aAAaqwq/AGI-Super-Team --skill zsxq-smart-publish --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Zsxq Smart Publish?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Zsxq Smart Publish
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aaaaqwq-zsxq-smart-publish-agi-super-team/badge)](https://www.skillsdirectory.com/skills/aaaaqwq-zsxq-smart-publish-agi-super-team)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: zsxq-smart-publish
description: "Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球."
author: Daniel Li
---

# 知识星球智能发布

Publish content to 知识星球 via API or browser automation.

## Authentication

Requires a valid `zsxq_access_token` cookie. Get it by:

1. Open `https://wx.zsxq.com` in browser
2. Login via WeChat QR scan
3. Open DevTools → Application → Cookies → find `zsxq_access_token`
4. Set env var: `export ZSXQ_ACCESS_TOKEN="your_token"`
   Or store in config file (see `references/config.md`)

Token expires. Re-scan QR when API returns 401.

## Content Types

| Type | topic_type | API field | Char limit | Description |
|------|-----------|-----------|------------|-------------|
| 话题 (Talk) | `talk` | `type` | 50,000 chars | General post, text+images+files |
| 问答 (Q&A) | `q&a` | `type` | 50,000 chars | Question format, star-owner can answer |
| 作业 (Task) | `task` | `type` | 50,000 chars | Homework/assignment with deadline |
| 长文章 (Article) | — | separate endpoint | 100,000 chars | Web-only, rich editor, Markdown support |

**长文章 is web-only**: Publish via browser (`scripts/publish_article.py`), not the topics API.

## Quick Start

### 1. Publish a Talk Post

```bash
python3 scripts/publish.py --type talk \
  --group-id GROUP_ID \
  --text "Hello from AI agent!" \
  --tags "AI,自动化" \
  --image /path/to/image.png
```

### 2. Publish a Q&A

```bash
python3 scripts/publish.py --type qa \
  --group-id GROUP_ID \
  --text "如何使用API批量发帖?" \
  --tags "API,教程"
```

### 3. Publish a Task

```bash
python3 scripts/publish.py --type task \
  --group-id GROUP_ID \
  --text "完成本周阅读任务\n\n阅读《AI未来》第3-5章" \
  --deadline "2026-03-25 23:59"
```

### 4. Publish Long Article (browser required)

```bash
python3 scripts/publish_article.py \
  --group-url "https://wx.zsxq.com/group/GROUP_ID" \
  --title "AI Agent开发指南" \
  --text-file article.md \
  --image /path/to/cover.png
```

### 5. Upload Files/Images

```bash
python3 scripts/upload.py \
  --group-id GROUP_ID \
  --file /path/to/report.pdf \
  --text "本周研报"
```

## Publishing SOP

### Pre-publish Checklist

1. Check `ZSXQ_ACCESS_TOKEN` is valid: `python3 scripts/publish.py --check-auth`
2. Confirm `GROUP_ID` (get from URL: `wx.zsxq.com/group/{GROUP_ID}`)
3. Prepare content within character limits
4. Add relevant tags (max 3 tags per post)
5. Attach images if needed (JPG/PNG, recommended ≤ 5MB each, max 9 images)

### Post-publish

1. Verify post appears in group
2. Set as digest/精华 if needed (star-owner only, via API or browser)
3. Add to appropriate topic category

## API Reference

Base URL: `https://api.zsxq.com`

### Create Topic (Talk/Q&A/Task)

```
POST /v2/groups/{group_id}/topics
Content-Type: application/json
Cookie: zsxq_access_token={token}

{
  "req_data": {
    "topic": {
      "type": "talk|q&a|task",
      "title": "optional title",
      "text": "post content (supports limited Markdown)",
      "image_count": 1,
      "images": [{"file_size": 12345, "width": 800, "height": 600}],
      "file": {"file_key": "xxx"} // for file attachments
    },
    "task": {  // only for type=task
      "owner_user_id": 0,
      "dead_line": "2026-03-25 23:59"
    }
  }
}
```

### Upload Image

```
POST /v2/files/{group_id}/images
Content-Type: multipart/form-data
Cookie: zsxq_access_token={token}

file: (binary)
```

Returns: `{"resp_data": {"upload_key": "xxx", "width": 800, "height": 600}}`

### Upload File

```
POST /v2/files/{group_id}/files
Content-Type: multipart/form-data
Cookie: zsxq_access_token={token}

file: (binary)
```

Returns: `{"resp_data": {"file": {"file_key": "xxx", "name": "file.pdf"}}}`

### Get Topics List

```
GET /v1.10/groups/{group_id}/topics?scope=all&count=20
Cookie: zsxq_access_token={token}
```

`scope` options: `all|digests|questions|tasks`

### Set as Digest (精华)

```
POST /v2/topics/{topic_id}/digest
Cookie: zsxq_access_token={token}
```

### Get Group List (user's groups)

```
GET /v2/groups
Cookie: zsxq_access_token={token}
```

## Content Formatting

### Supported Markdown

- `**bold**`, `*italic*`
- `# heading` (long articles only)
- `` `code` ``, code blocks with ```
- Ordered/unordered lists
- Links: `[text](url)` (long articles only)
- Tables (long articles only)

### NOT Supported

- Image embedding via Markdown (use API upload)
- HTML tags
- Math formulas
- Mermaid diagrams

### Image Specs

- Formats: JPG, PNG, GIF
- Recommended size: ≤ 5MB per image
- Max images per post: 9
- Long articles: insert via editor, no limit on count

### File Specs

- Max file size: 200MB
- Supported: PDF, DOCX, XLSX, PPTX, ZIP, MP3, MP4
- Audio: MP3 recommended, max 30min

## Browser Publishing (for Long Articles)

Long articles cannot be created via API. Use `scripts/publish_article.py`:

1. Navigates to group page
2. Clicks "长文章" button
3. Fills title and content
4. Uploads cover image
5. Publishes

Requires Playwright: `pip install playwright && playwright install chromium`

## Templates

See `assets/` for content templates:
- `assets/talk-template.md` — Standard talk post
- `assets/qa-template.md` — Question format
- `assets/task-template.md` — Homework/assignment
- `assets/article-template.md` — Long article structure

## Error Handling

| HTTP Code | Meaning | Action |
|-----------|---------|--------|
| 401 | Token expired | Re-login, get new token |
| 403 | No permission | Check if user is group member/owner |
| 429 | Rate limited | Wait, retry after cooldown |
| 500 | Server error | Retry with exponential backoff |

## Reference

- Full API details: `references/api.md`
- Config guide: `references/config.md`

Attribution

aAAaqwqaAAaqwq
View sourceMore from aAAaqwq →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →