Blogwatcher

Community

HezaoHezao

blogwatcher

Monitor blogs and RSS/Atom feeds via blogwatcher-cli.

Overview

Publisher	HezaoHezao
Repository	`poirot`
Skill name	`blogwatcher`
Stars	252
Forks	26
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by HezaoHezao on GitHub. Read the source before you install it.

Installation

Install the Blogwatcher AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/HezaoHezao/poirot/tree/master/poirot/backend/agents/skill/builtin_skills/research/blogwatcher
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/HezaoHezao/poirot/tree/master/poirot/backend/agents/skill/builtin_skills/research/blogwatcher

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/HezaoHezao/poirot.git /tmp/poirot
mkdir -p .claude/skills
cp -r /tmp/poirot/poirot/backend/agents/skill/builtin_skills/research/blogwatcher .claude/skills/blogwatcher

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Blogwatcher in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Blogwatcher on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Blogwatcher is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Blogwatcher

Track blog and RSS/Atom feed updates with the blogwatcher-cli tool. Supports automatic feed discovery, HTML scraping fallback, OPML import, and read/unread article management.

Prerequisites

blogwatcher-cli must be installed. Pick one method:

bash
# Go install
go install github.com/JulienTant/blogwatcher-cli/cmd/blogwatcher-cli@latest

# Binary (Linux amd64)
curl -sL https://github.com/JulienTant/blogwatcher-cli/releases/latest/download/blogwatcher-cli_linux_amd64.tar.gz | tar xz -C /usr/local/bin blogwatcher-cli

# Docker
docker run --rm -v blogwatcher-cli:/data ghcr.io/julientant/blogwatcher-cli scan

All releases: https://github.com/JulienTant/blogwatcher-cli/releases

Verify installation:

bash
blogwatcher-cli --version

When to Use

User wants to monitor blog updates
User wants to track RSS/Atom feeds
User wants to import OPML subscriptions
User wants a digest of new articles from tracked blogs

Common Commands

bash
# Add a blog to track
blogwatcher-cli add https://example.com/blog

# Add with explicit feed URL
blogwatcher-cli add https://example.com/blog --feed https://example.com/feed.xml

# Scan for new articles
blogwatcher-cli scan

# List tracked blogs
blogwatcher-cli list

# List unread articles
blogwatcher-cli articles --unread

# Mark article as read
blogwatcher-cli read <article-id>

# Import OPML
blogwatcher-cli import subscriptions.opml

# Export OPML
blogwatcher-cli export > subscriptions.opml

Workflow

Setup (first time)

bash
# Install blogwatcher-cli (see Prerequisites)
# Add blogs to track
blogwatcher-cli add https://blog1.com
blogwatcher-cli add https://blog2.com

# Or import existing OPML
blogwatcher-cli import my-subscriptions.opml

Daily check

bash
# Scan for new articles
blogwatcher-cli scan

# Show unread
blogwatcher-cli articles --unread

# Read an article (marks as read)
blogwatcher-cli read <article-id>

Automated monitoring

Set up a cron job to scan periodically:

bash
# Scan every morning at 8am
echo "0 8 * * * blogwatcher-cli scan" | crontab -

Docker with persistent storage

The database lives at ~/.blogwatcher-cli/blogwatcher-cli.db by default. In Docker, use a volume to persist:

bash
# Named volume
docker run --rm -v blogwatcher-cli:/data -e BLOGWATCHER_DB=/data/blogwatcher-cli.db ghcr.io/julientant/blogwatcher-cli scan

# Host bind mount
docker run --rm -v /path/on/host:/data -e BLOGWATCHER_DB=/data/blogwatcher-cli.db ghcr.io/julientant/blogwatcher-cli scan

Pitfalls

blogwatcher-cli not installed: this skill requires the external tool. Install first (see Prerequisites).
Feed discovery fails: some sites don't expose <link rel="alternate"> tags. Use --feed to specify the feed URL explicitly.
Rate limiting: scanning many feeds rapidly may get you blocked. The tool handles this, but don't run scan too frequently.
Database location: if using Docker, always set BLOGWATCHER_DB to a volume-mounted path, or data is lost on container exit.
OPML encoding: ensure OPML files are UTF-8 encoded for proper import.

Frequently asked questions

What does the Blogwatcher AI skill do?

Monitor blogs and RSS/Atom feeds via blogwatcher-cli.

Why use Blogwatcher on TypingMind?

Because you install it once and use it with any model. Blogwatcher is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Blogwatcher in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HezaoHezao/poirot/tree/master/poirot/backend/agents/skill/builtin_skills/research/blogwatcher. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Blogwatcher?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Blogwatcher?

As many as you like. As long as a model supports skills, you can use Blogwatcher with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Blogwatcher AI skill free?

Yes. It is published on GitHub by HezaoHezao under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Modal

NousResearch

OrganizationPopular

Serverless GPU cloud for ML jobs and model APIs.

Huggingface Hub

HuggingFace hf CLI: search/download/upload models, datasets.

Pinecone

Managed vector DB for production RAG and search.

Qdrant

Vector search engine for production RAG systems.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Blogwatcher

Prerequisites

When to Use

Common Commands

Workflow

Setup (first time)

Daily check

Automated monitoring

Docker with persistent storage

Pitfalls

Frequently asked questions

Related AI Skills

Set up your own AI workspace now