Competitor Product Monitor logo

Competitor Product Monitor

OrganizationPopular
tinyfish-io
competitor-product-monitor

Monitor competitor product releases and new feature announcements. Use this skill when the user wants to track what competitors are shipping, find the latest product launches in their industry, or generate a competitor release report. Triggers include phrases like "track competitor releases", "what are my competitors launching", "monitor competitor products", "competitor product report", or any request to watch a rival company's product updates.

Overview

Publishertinyfish-io
Repositorytinyfish-cookbook
Skill namecompetitor-product-monitor
Stars
2.2K
Forks
333
Bundled files
Instructions only
LicenseMIT
Links
  • 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 tinyfish-io on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

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/tinyfish-io/tinyfish-cookbook.git /tmp/tinyfish-cookbook
mkdir -p .claude/skills
cp -r /tmp/tinyfish-cookbook/skills/competitor-update .claude/skills/competitor-product-monitor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Competitor Product Monitor 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 Competitor Product Monitor 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 Competitor Product Monitor 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.

Competitor Product Monitor

This skill walks the agent through a structured workflow to identify competitors, fetch their latest product release information using the TinyFish web agent, and generate a clean report for the user.


Pre-flight: TinyFish Check (REQUIRED)

Before doing anything, verify TinyFish is available:

bash
which tinyfish && tinyfish --version || echo "TINYFISH_CLI_NOT_INSTALLED"
tinyfish auth status

If not installed, stop and tell the user:

Install the TinyFish CLI first: npm install -g @tiny-fish/cli Then authenticate: tinyfish auth login

Do NOT proceed until both checks pass.


Workflow

Step 1 — Ask the user for their product and field

Say:

To get started, please tell me:

  1. Your industry or field (e.g. "project management SaaS", "electric vehicles", "cloud storage")
  2. Your product or company name (e.g. "Notion", "Tesla", "Dropbox")

Wait for the user's response before continuing.


Step 2 — Identify competitors

Based on the user's field and product, suggest 3–5 direct competitors. For each competitor, find or infer their primary website URL.

Present them in a clear list, like:

Here are the competitors I found for [product] in [field]:

  1. Asanahttps://asana.com
  2. Monday.comhttps://monday.com
  3. ClickUphttps://clickup.com

Does this look right? Feel free to remove any, or add others (with their website URLs if possible).

Wait for the user to confirm or modify the list before proceeding.

Tips for finding competitor URLs:

  • Use the company's official homepage, not a blog or news page
  • Prefer URLs like https://companyname.com over subdomains
  • If the user provides a competitor name without a URL, infer the most likely homepage

Step 3 — Fetch product release information with TinyFish

For each confirmed competitor, run a separate TinyFish command. Run them in parallel for speed.

Use this command pattern for each competitor:

bash
tinyfish agent run --sync --url "<competitor_url>" \
  "Find the latest product release, new feature announcement, or product update on this website. Look at the blog, changelog, newsroom, or press release pages. Return JSON: {\"company\": str, \"latest_release\": str, \"release_date\": str, \"description\": str, \"source_url\": str}"

Good pages to target (append to the base URL if needed):

  • /blog
  • /changelog
  • /news
  • /newsroom
  • /releases
  • /whats-new

If the base URL does not surface release info, retry with one of the above paths appended.

Parallel execution example (run all at once):

bash
tinyfish agent run --sync --url "https://asana.com/product" \
  "Find the latest product release or feature announcement. Return JSON: {\"company\": str, \"latest_release\": str, \"release_date\": str, \"description\": str, \"source_url\": str}"

tinyfish agent run --sync --url "https://monday.com/blog" \
  "Find the latest product release or feature announcement. Return JSON: {\"company\": str, \"latest_release\": str, \"release_date\": str, \"description\": str, \"source_url\": str}"

tinyfish agent run --sync --url "https://clickup.com/blog" \
  "Find the latest product release or feature announcement. Return JSON: {\"company\": str, \"latest_release\": str, \"release_date\": str, \"description\": str, \"source_url\": str}"

Collect the resultJson field from each COMPLETE event in the TinyFish output.


Step 4 — Generate the competitor release report

Once all TinyFish results are collected, compile and present the report to the user in this format:


Competitor Product Release Report Field: [field] | Your product: [product] | Generated: [date]


[Company Name] Release: [latest_release] Date: [release_date] [description] Source: [source_url]


[Company Name] ...


After the report, ask the user:

Would you like to monitor these competitors periodically for new releases? If yes, let me know how often (e.g. weekly, daily) and how you'd like to be notified (e.g. email, Slack).


Output JSON Schema

Each TinyFish result should conform to:

json
{
  "company": "string — competitor company name",
  "latest_release": "string — name or title of the release/announcement",
  "release_date": "string — date as found on the page, or 'Unknown'",
  "description": "string — 1-3 sentence summary of what was released",
  "source_url": "string — direct URL to the announcement or changelog page"
}

If a field cannot be found, set it to "Not found" rather than omitting it.


Handling Failures

ProblemAction
TinyFish returns no resultRetry with a more specific URL (e.g. append /changelog or /blog)
Page is bot-protectedNote it in the report as "Could not fetch — site may require login"
Release date missingUse "Date not found" and still include the release info
Company has no public changelogSearch their blog or press page instead

Example Full Run

User: I work in the task management space. My product is Todoist.

Agent finds competitors: Asana, Notion, TickTick, Any.do, Microsoft To Do

Agent runs (in parallel):

bash
tinyfish agent run --sync --url "https://asana.com/product" "..."
tinyfish agent run --sync --url "https://notion.so/blog" "..."
tinyfish agent run --sync --url "https://ticktick.com/blog" "..."
tinyfish agent run --sync --url "https://any.do/blog" "..."
tinyfish agent run --sync --url "https://todo.microsoft.com" "..."

Agent presents:

Competitor Product Release Report Field: task management | Your product: Todoist | Generated: 2026-04-06

Asana Release: Asana AI Studio — custom workflow automation Date: March 2026 Asana launched AI Studio, allowing teams to build no-code AI workflows... Source: https://asana.com/product/ai-studio

...


Notes

  • Always run one TinyFish command per competitor — do not combine multiple sites into one goal.
  • Use --sync flag so results are fully returned before generating the report.
  • The report should list competitors in order of most recent release date first, if dates are available.
  • If the user adds a competitor mid-workflow, fetch only that new competitor and append to the existing report.

Frequently asked questions

What does the Competitor Product Monitor AI skill do?

Monitor competitor product releases and new feature announcements. Use this skill when the user wants to track what competitors are shipping, find the latest product launches in their industry, or generate a competitor release report. Triggers include phrases like "track competitor releases", "what are my competitors launching", "monitor competitor products", "competitor product report", or any request to watch a rival company's product updates.

Why use Competitor Product Monitor on TypingMind?

Because you install it once and use it with any model. Competitor Product Monitor 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 Competitor Product Monitor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tinyfish-io/tinyfish-cookbook/tree/main/skills/competitor-update. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Competitor Product Monitor?

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 Competitor Product Monitor?

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

Is the Competitor Product Monitor AI skill free?

Yes. It is published on GitHub by tinyfish-io 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇