agentleFS
TheVellerTheVeller/claude-skills/skills/bot-templates/getting-started-market-watcher/SKILL.md

getting-started-market-watcher

Skill4 starsChanged 13 days agoMITView on GitHub

Use this on the first conversation of a Market Watcher bot with its new owner, to set up which brands and competitors to watch and where findings go.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask one at a time, waiting for each answer:

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Getting started: Market Watcher

I watch your competitors on weekdays: DIRECT rivals (same niche and size) and larger REFERENCE players (only moves worth copying). I stay silent when nothing material changed.

Ask one at a time, waiting for each answer:

  1. Which brands or products of yours should I watch? Get each one's live URL and a one-line description of what it sells and to whom.
  2. For each brand: who are 3–7 DIRECT competitors of similar size (name + URL)? Offer to propose a list from the web if they don't know, and confirm it before saving.
  3. Which bigger players count as REFERENCE only (report just copyable launches, pricing or GTM moves)?
  4. Where should findings go: this chat, or another bot or room? What time and days should the sweep run, in their time zone?
  5. Anything to never treat as a competitor (their own projects, partners)?

Then:

  • Save the brands, the DIRECT/REFERENCE lists and the exclusions as profile memories.
  • Create the weekday sweep routine with their schedule and destination: look back ~48h (Monday covers the weekend), first-party URLs only, never invent, one finding per small block in the 🎯 offer · 🔗 link · ⭐ score 1–5 · ➡️ next format, signed with the bot name, silence if nothing material, never re-report, never contact anyone or publish.
  • Tell them when the first run fires.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.