clawpost
AI-powered social media publishing for LinkedIn and X (Twitter) with algorithm optimization and scheduling.
Best use case
clawpost is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
AI-powered social media publishing for LinkedIn and X (Twitter) with algorithm optimization and scheduling.
Teams using clawpost should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/clawpost-2/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How clawpost Compares
| Feature / Agent | clawpost | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
AI-powered social media publishing for LinkedIn and X (Twitter) with algorithm optimization and scheduling.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Social Media Publisher Skill
ClawPost helps you create, manage, and publish content to LinkedIn and X (Twitter) — with AI-assisted writing, drafts, scheduling, and direct publishing via API.
## Getting Started
If the user doesn't have an account or API key yet, walk them through these steps:
1. **Sign up** at [clawpost.dev](https://clawpost.dev) — sign in with LinkedIn.
2. **Connect platforms** — In the Dashboard, connect LinkedIn and/or X (Twitter) accounts.
3. **Add credits** — Go to Dashboard → Billing and top up credits (minimum $5). Credits are used for AI generation features.
4. **Generate an API key** — Go to Dashboard → Settings → API Keys → Generate New Key. The key starts with `claw_`.
5. **Set the environment variable**:
```bash
export CLAW_API_KEY="claw_your_key_here"
```
## Setup
Required environment variable:
- `CLAW_API_KEY` — your API key (starts with `claw_`). Generate one following the steps above.
Optional:
- `CLAW_API_URL` — defaults to `https://clawpost.dev`. Only set this if using a self-hosted instance.
All endpoints are under `{{CLAW_API_URL}}/api/claw/v1/` (default: `https://clawpost.dev/api/claw/v1/`).
## Authentication
Every request needs the header:
```
Authorization: Bearer {{CLAW_API_KEY}}
```
## Important: Passing JSON in shell commands
When sending JSON data with curl, **always use a heredoc** to avoid shell escaping issues with quotes and special characters:
```bash
curl -s -X POST URL \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"key": "value"}
EOF
```
All examples below use this pattern. Do **not** use `-d '{...}'` with single quotes — it breaks when content contains quotes, newlines, or special characters.
## Response Format
All responses follow this shape:
```json
{
"success": true,
"message": "Human-readable summary",
"data": { ... },
"error": { "code": "ERROR_CODE", "details": "..." }
}
```
Always read the `message` field — it's designed to be relayed directly to the user.
## Endpoints
### Check Status
Verify your API key works and see what's connected.
```bash
curl -s {{CLAW_API_URL}}/api/claw/v1/status \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
### List Connected Platforms
```bash
curl -s {{CLAW_API_URL}}/api/claw/v1/platforms \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
### Check Credits
```bash
curl -s {{CLAW_API_URL}}/api/claw/v1/credits \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
### List Posts
Filter by status (`draft`, `published`, `scheduled`, `failed`) and platform (`linkedin`, `twitter`).
```bash
curl -s "{{CLAW_API_URL}}/api/claw/v1/posts?status=draft&platform=linkedin&limit=10" \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
### X Post History
Retrieve your X (Twitter) post history from the cached profile data. This is a read-only endpoint - no credits are used.
Query parameters:
- `type` - `posts`, `replies`, or `all` (default: `all`)
- `limit` - max results, 1-100 (default: `20`)
- `period` - `7d`, `30d`, `90d`, or `all` (default: `all`)
```bash
curl -s "{{CLAW_API_URL}}/api/claw/v1/history/x?type=posts&period=30d&limit=10" \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
The response includes a `summary` object with aggregated metrics (`totalPosts`, `totalReplies`, `totalLikes`, `totalRetweets`, `totalRepliesReceived`, `totalImpressions`, `topPost`) and a `posts` array with individual tweet details, metrics, media, and reply context.
### Get Single Post
```bash
curl -s {{CLAW_API_URL}}/api/claw/v1/posts/POST_ID \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
Each post includes an `availableActions` array (e.g., `["publish", "schedule", "update", "delete"]`).
#### Post Object Fields
Every post includes a `postType` field:
- `"original"` — a regular post composed by the user
- `"quote"` — a quote tweet of another post (X only)
- `"reply"` — a reply to another post (X only)
- `"remix"` — an original tweet inspired by another post (X only)
When `postType` is `"quote"`, `"reply"`, or `"remix"`, the post also includes a `reference` object with the original tweet's context:
```json
{
"postType": "quote",
"content": "User's commentary text",
"reference": {
"tweetId": "1234567890",
"text": "The original tweet text that was quoted",
"author": "originalAuthor"
}
}
```
This lets you see exactly what was quoted/replied to alongside the user's own text.
### Create a Draft
```bash
curl -s -X POST {{CLAW_API_URL}}/api/claw/v1/drafts \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"content": "Your post text here", "platform": "linkedin"}
EOF
```
Platform: `"linkedin"` or `"twitter"`. Twitter content must be ≤ 280 characters.
### Update a Draft
```bash
curl -s -X PUT {{CLAW_API_URL}}/api/claw/v1/posts/POST_ID \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"content": "Updated post text"}
EOF
```
### Delete a Draft
```bash
curl -s -X DELETE {{CLAW_API_URL}}/api/claw/v1/posts/POST_ID \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
### Publish a Draft
```bash
curl -s -X POST {{CLAW_API_URL}}/api/claw/v1/posts/POST_ID/publish \
-H "Authorization: Bearer {{CLAW_API_KEY}}"
```
### Direct Publish (No Draft Step)
```bash
curl -s -X POST {{CLAW_API_URL}}/api/claw/v1/publish \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"content": "Publishing this directly!", "platform": "linkedin"}
EOF
```
### Schedule a Draft
```bash
curl -s -X POST {{CLAW_API_URL}}/api/claw/v1/posts/POST_ID/schedule \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"scheduledAt": "2026-06-15T10:00:00Z"}
EOF
```
### Direct Schedule (No Draft Step)
```bash
curl -s -X POST {{CLAW_API_URL}}/api/claw/v1/schedule \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"content": "Scheduled post!", "platform": "linkedin", "scheduledAt": "2026-06-15T10:00:00Z"}
EOF
```
### AI Generate Post
Let AI write a post based on your prompt. Optional: `tone` and `platform`.
```bash
curl -s -X POST {{CLAW_API_URL}}/api/claw/v1/ai/generate \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"prompt": "Write about the importance of code reviews", "platform": "linkedin"}
EOF
```
### AI Refine Post
Improve existing content with instructions.
```bash
curl -s -X POST {{CLAW_API_URL}}/api/claw/v1/ai/refine \
-H "Authorization: Bearer {{CLAW_API_KEY}}" \
-H "Content-Type: application/json" \
-d @- <<'EOF'
{"content": "Original post text...", "instructions": "Make it shorter and punchier", "platform": "linkedin"}
EOF
```
## Workflow Tips
1. **Quick publish**: Use `/publish` to post immediately without creating a draft.
2. **Review flow**: Create a draft with `/drafts`, refine with `/ai/refine`, then publish with `/posts/ID/publish`.
3. **Cross-post**: Make separate calls for LinkedIn and Twitter — each is a separate post.
4. **Check before publishing**: Call `/platforms` to verify the target platform is connected.
5. **Twitter limit**: Tweets must be ≤ 280 characters. The API will reject longer content with a clear message.
## Error Codes
| Code | Meaning |
|------|---------|
| `UNAUTHORIZED` | Invalid or revoked API key |
| `NOT_FOUND` | Post or resource doesn't exist |
| `VALIDATION_ERROR` | Bad input (missing content, too long, invalid date) |
| `CONFLICT` | Can't perform action (e.g., already published) |
| `PLATFORM_NOT_CONNECTED` | Target social platform isn't linked |
| `INSUFFICIENT_CREDITS` | Not enough credits for AI operations |
| `NO_AI_KEY` | No AI API key configured |
| `RATE_LIMITED` | Too many requests (60/min general, 10/min publish) |
| `INTERNAL_ERROR` | Something went wrong server-side |Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述