Guide · Agent skill
How to use the blogwatcher agent skill: track blog feeds
Updated · written with AI from the project's own documentation and checked against our catalogue data
The blogwatcher skill lets an AI agent keep a list of blogs and RSS or Atom feeds, check them for new posts, list unread articles and mark them as read. It works by running the blogwatcher command-line tool on your computer, so the agent reports what the feeds actually contain rather than guessing. This guide explains what the skill does, how to install it, how to ask for things in plain language, and what it needs and touches on your machine.
Blog and feed watcherspinabot/brigade · MIT Download the skill Quick start
- 1Install Go. Install the Go toolchain so the go install command can run on your machine.
- 2Install the blogwatcher CLI. Run go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest, then check with blogwatcher --help.
- 3Download and unzip the skill. Download the blogwatcher ZIP from our page and unzip it so SKILL.md sits in a skills folder.
- 4Place the skill folder. Unzip into ~/.claude/skills/ or a project's .claude/skills/, or upload it under Settings → Capabilities → Skills in the Claude apps.
- 5Add your first blog. Ask the agent to track a blog, or run blogwatcher add with a name and feed URL.
- 6Scan and read. Ask the agent to check for new posts, then list articles and mark them read when done.
What is an agent skill and what does blogwatcher do?
An agent skill is a folder containing a SKILL.md file that gives an AI agent instructions for a specific task. When the skill is installed, the agent can read those instructions and use them when your request matches the task.
The blogwatcher skill covers feed monitoring. Once installed, the agent can add blogs, list the blogs you track, scan them for updates, list articles, mark one or all articles as read, and remove blogs. Each of these actions runs the blogwatcher CLI on your computer. Think of it as a personal feed reader that the agent operates for you.
- Add, list and remove the blogs you track
- Scan tracked blogs and RSS or Atom feeds for new articles
- List articles and mark one or all of them as read
Install the blogwatcher CLI with Go
The skill depends on the blogwatcher command-line tool, which is a Go program. Installing the skill alone is not enough: the blogwatcher binary must be available on your machine. The source gives this install command, which requires a Go toolchain:
- You need the Go toolchain installed so that go install works.
- Run blogwatcher --help afterward to confirm the tool is available.
- The skill's metadata lists blogwatcher as a required binary.
go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latestInstall the blogwatcher skill itself
Download the blogwatcher ZIP from our page and unzip it. The folder contains SKILL.md. Then place it where your agent looks for skills:
For Claude Code, unzip it into ~/.claude/skills/ to make it available across your projects, or into a project's .claude/skills/ folder to limit it to that project.
In the Claude apps, you can instead upload the skill under Settings → Capabilities → Skills.
- Personal install: ~/.claude/skills/
- Project install: .claude/skills/ inside your project
- Claude apps: Settings → Capabilities → Skills
Trigger the skill with natural requests
You do not need to type commands yourself. Describe what you want in plain language and mention blogs, feeds or articles. The agent matches your request to the skill and runs the right blogwatcher command.
You can also ask the agent to show the tool's help, which the source suggests as a quick start. Commands map roughly to requests: adding a blog, listing blogs, scanning for updates, listing articles, and marking articles read.
- "Track https://example.com as a blog called Example."
- "Check my blogs for new posts."
- "What new articles do I have?"
- "Mark article 1 as read."
- "Mark everything as read."
- "Stop tracking My Blog."
Command reference
These are the common commands listed in the skill. You can run them directly in a terminal or let the agent run them for you. For flags and options, use the built-in help.
- Add a blog: blogwatcher add "My Blog" https://example.com
- List blogs: blogwatcher blogs
- Scan for updates: blogwatcher scan
- List articles: blogwatcher articles
- Mark an article read: blogwatcher read 1
- Mark all articles read: blogwatcher read-all
- Remove a blog: blogwatcher remove "My Blog"
- Help for any command: blogwatcher <command> --help
$ blogwatcher scan
Scanning 1 blog(s)...
xkcd
Source: RSS | Found: 4 | New: 4
Found 4 new article(s) total!Requirements, network use and safety notes
The skill requires the blogwatcher CLI binary, the Go toolchain if you install through go install, and network access to the blog feeds you track. It runs scripts and uses the network, because scanning fetches feeds from the internet.
Only track feeds you trust, and review what the agent runs if you want to be cautious. The skill's own instructions are limited to the blogwatcher commands listed above.
- Requires: blogwatcher CLI, Go toolchain (for go install), network access to tracked feeds
- Runs scripts: yes. Uses network: yes
- Source license: MIT
Tips for getting better results
Tracking works best with sites that publish an RSS or Atom feed, because the tool depends on feeds to detect updates. If a site has no feed, blogwatcher has nothing to detect. Use a clear name when you add a blog, since you refer to it by that name when removing it.
Scan before you ask for new articles, so the list reflects the latest feed contents. Article numbers, such as the one used in read 1, come from the output of the articles list.
- Use sites that offer an RSS or Atom feed
- Give each blog a clear, memorable name
- Run a scan before listing new articles
What people use it for
- Keeping up with several industry or news blogs and getting a quick summary of new posts
- Tracking technical blogs or release notes that publish RSS or Atom feeds
- Monitoring competitor or industry blogs as a journalist or marketer
- Clearing a backlog of unread articles with a single mark-all-read request
Frequently asked questions
How do I install the blogwatcher skill?
Download the blogwatcher ZIP from our page and unzip it into ~/.claude/skills/ or a project's .claude/skills/ folder. In the Claude apps, you can upload it under Settings → Capabilities → Skills. You also need the blogwatcher CLI, installed with go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest.
What does blogwatcher require?
It requires the blogwatcher CLI binary, the Go toolchain if you install the CLI with go install, and network access to the blog feeds you want to track. It runs scripts and uses the network.
Is blogwatcher free?
The source is licensed under MIT. The source does not state any pricing, so check the project's repository for details on cost and terms.
Can blogwatcher track websites without an RSS feed?
Not reliably. The tool depends on RSS or Atom feeds to detect updates, so sites that offer no feed are a poor fit.
What is the difference between blogwatcher and a normal feed reader?
blogwatcher is a command-line tool that an agent operates for you. You can talk to the agent in plain language to add blogs, scan for updates and mark articles read, instead of using a graphical reader.
Why does my scan show no new articles?
The tool only finds what the feed currently contains. Make sure the blog has an RSS or Atom feed and that your machine has network access. Run blogwatcher <command> --help to check available options.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Choose blogwatcher if you follow many feed-based blogs and want an agent to check, list and mark them for you, and you can install a Go-based CLI. Pick a different tool if the sites you follow have no RSS or Atom feed, or if you cannot install command-line tools on your machine.
Download the skill