bearblog
Create and manage blog posts on Bear Blog (bearblog.dev). Supports extended Markdown, custom attributes, and browser-based publishing.
Best use case
bearblog is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create and manage blog posts on Bear Blog (bearblog.dev). Supports extended Markdown, custom attributes, and browser-based publishing.
Teams using bearblog 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/bearblog/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How bearblog Compares
| Feature / Agent | bearblog | 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?
Create and manage blog posts on Bear Blog (bearblog.dev). Supports extended Markdown, custom attributes, and browser-based publishing.
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.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
SKILL.md Source
# Bear Blog Skill
Create, edit, and manage posts on [Bear Blog](https://bearblog.dev) — a minimal, fast blogging platform.
## Authentication
Bear Blog requires browser-based authentication. Log in once via the browser tool, and cookies will persist.
```
browser action:navigate url:https://bearblog.dev/accounts/login/
```
## Creating a Post
### Step 1: Navigate to the post editor
```
browser action:navigate url:https://bearblog.dev/<subdomain>/dashboard/posts/new/
```
### Step 2: Fill the editor
Bear Blog uses a **plain text header format**.
The editor fields are:
- `div#header_content` (contenteditable): attributes (one per line)
- `textarea#body_content`: Markdown body
**Verified:** use `fill`/`type` on those two fields, then click **Publish** (or **Save as draft**). No `evaluate` needed.
**Header format:**
```
title: Your Post Title
link: custom-slug
published_date: 2026-01-05 14:00
tags: tag1, tag2, tag3
make_discoverable: true
is_page: false
class_name: custom-css-class
meta_description: SEO description for the post
meta_image: https://example.com/image.jpg
lang: en
canonical_url: https://original-source.com/post
alias: alternative-url
```
**Body format:** Standard Markdown with extensions (see below).
The separator `___` (three underscores) is used in templates to separate header from body.
### Step 3: Publish
Click the publish button or submit the form with `publish: true`.
## Post Attributes Reference
| Attribute | Description | Example |
|-----------|-------------|---------|
| `title` | Post title (required) | `title: My Post` |
| `link` | Custom URL slug | `link: my-custom-url` |
| `published_date` | Publication date/time | `published_date: 2026-01-05 14:30` |
| `tags` | Comma-separated tags | `tags: tech, ai, coding` |
| `make_discoverable` | Show in discovery feed | `make_discoverable: true` |
| `is_page` | Static page vs blog post | `is_page: false` |
| `class_name` | Custom CSS class (slugified) | `class_name: featured` |
| `meta_description` | SEO meta description | `meta_description: A post about...` |
| `meta_image` | Open Graph image URL | `meta_image: https://...` |
| `lang` | Language code | `lang: fr` |
| `canonical_url` | Canonical URL for SEO | `canonical_url: https://...` |
| `alias` | Alternative URL path | `alias: old-url` |
## Extended Markdown
Bear Blog uses [Mistune](https://github.com/lepture/mistune) with plugins:
### Text Formatting
- `~~strikethrough~~` → ~~strikethrough~~
- `^superscript^` → superscript
- `~subscript~` → subscript
- `==highlighted==` → highlighted (mark)
- `**bold**` and `*italic*` — standard
### Footnotes
```markdown
Here's a sentence with a footnote.[^1]
[^1]: This is the footnote content.
```
### Task Lists
```markdown
- [x] Completed task
- [ ] Incomplete task
```
### Tables
```markdown
| Header 1 | Header 2 |
|----------|----------|
| Cell 1 | Cell 2 |
```
### Code Blocks
````markdown
```python
def hello():
print("Hello, world!")
```
````
Syntax highlighting via Pygments (specify language after ```).
### Math (LaTeX)
- Inline: `$E = mc^2$`
- Block: `$$\int_0^\infty e^{-x^2} dx$$`
### Abbreviations
```markdown
*[HTML]: Hypertext Markup Language
The HTML specification is maintained by the W3C.
```
### Admonitions
```markdown
.. note::
This is a note admonition.
.. warning::
This is a warning.
```
### Table of Contents
```markdown
.. toc::
```
## Dynamic Variables
Use `{{ variable }}` in your content:
### Blog Variables
- `{{ blog_title }}` — Blog title
- `{{ blog_description }}` — Blog meta description
- `{{ blog_created_date }}` — Blog creation date
- `{{ blog_last_modified }}` — Time since last modification
- `{{ blog_last_posted }}` — Time since last post
- `{{ blog_link }}` — Full blog URL
- `{{ tags }}` — Rendered tag list with links
### Post Variables (in post templates)
- `{{ post_title }}` — Current post title
- `{{ post_description }}` — Post meta description
- `{{ post_published_date }}` — Publication date
- `{{ post_last_modified }}` — Time since modification
- `{{ post_link }}` — Full post URL
- `{{ next_post }}` — Link to next post
- `{{ previous_post }}` — Link to previous post
### Post Listing
```markdown
{{ posts }}
{{ posts limit:5 }}
{{ posts tag:"tech" }}
{{ posts tag:"tech,ai" limit:10 order:asc }}
{{ posts description:True image:True content:True }}
```
Parameters:
- `tag:` — filter by tag(s), comma-separated
- `limit:` — max number of posts
- `order:` — `asc` or `desc` (default: desc)
- `description:True` — show meta descriptions
- `image:True` — show meta images
- `content:True` — show full content (only on pages)
### Email Signup (upgraded blogs only)
```markdown
{{ email-signup }}
{{ email_signup }}
```
## Links
### Standard Links
```markdown
[Link text](https://example.com)
[Link with title](https://example.com "Title text")
```
### Open in New Tab
Prefix URL with `tab:`:
```markdown
[External link](tab:https://example.com)
```
### Heading Anchors
Headings automatically get slugified IDs:
```markdown
## My Section Title
```
Links to: `#my-section-title`
## Typography
Automatic replacements:
- `(c)` → ©
- `(C)` → ©
- `(r)` → ®
- `(R)` → ®
- `(tm)` → ™
- `(TM)` → ™
- `(p)` → ℗
- `(P)` → ℗
- `+-` → ±
## Raw HTML
HTML is supported directly in Markdown:
```html
<div class="custom-class" style="text-align: center;">
<p>Centered content with custom styling</p>
</div>
```
**Note:** `<script>`, `<object>`, `<embed>`, `<form>` are stripped for free accounts. Iframes are whitelisted (YouTube, Vimeo, Spotify, etc.).
## Whitelisted Iframe Sources
- youtube.com, youtube-nocookie.com
- vimeo.com
- soundcloud.com
- spotify.com
- codepen.io
- google.com (docs, drive, maps)
- bandcamp.com
- apple.com (music embeds)
- archive.org
- And more...
## Dashboard URLs
Replace `<subdomain>` with your blog subdomain:
- **Blog list:** `https://bearblog.dev/dashboard/`
- **Dashboard:** `https://bearblog.dev/<subdomain>/dashboard/`
- **Posts list:** `https://bearblog.dev/<subdomain>/dashboard/posts/`
- **New post:** `https://bearblog.dev/<subdomain>/dashboard/posts/new/`
- **Edit post:** `https://bearblog.dev/<subdomain>/dashboard/posts/<uid>/`
- **Styles:** `https://bearblog.dev/<subdomain>/dashboard/styles/`
- **Navigation:** `https://bearblog.dev/<subdomain>/dashboard/nav/`
- **Analytics:** `https://bearblog.dev/<subdomain>/dashboard/analytics/`
- **Settings:** `https://bearblog.dev/<subdomain>/dashboard/settings/`
## Example: Complete Post
**Header content:**
```
title: Getting Started with AI Assistants
link: ai-assistants-intro
published_date: 2026-01-05 15:00
meta_description: A beginner's guide to working with AI assistants
tags: ai, tutorial, tech
is_page: false
lang: en
```
**Body content:**
```markdown
AI assistants are changing how we work. Here's what you need to know.
## Why AI Assistants?
They help with:
- [x] Writing and editing
- [x] Research and analysis
- [ ] Making coffee (not yet!)
> "The best tool is the one you actually use." — Someone wise
## Getting Started
Check out [OpenAI](tab:https://openai.com) or [Anthropic](tab:https://anthropic.com) for popular options.
---
*What's your experience with AI? Let me know!*
{{ previous_post }} {{ next_post }}
```
## Tips
1. **Preview before publishing** — Use the preview button to check formatting
2. **Use templates** — Set up a post template in dashboard settings for consistent headers
3. **Schedule posts** — Set `published_date` in the future
4. **Draft mode** — Don't click publish to keep as draft
5. **Custom CSS** — Add `class_name` and style in your blog's CSS
6. **SEO** — Always set `meta_description` and `meta_image`
## Troubleshooting
- **Post not showing?** Check `publish` status and `published_date`
- **Tags not working?** Use comma separation, no quotes
- **Styling issues?** Check `class_name` is slugified (lowercase, hyphens)
- **Date format error?** Use `YYYY-MM-DD HH:MM`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