agentleFS
HumanleapHumanleap/bot-store-agent-plugin/skills/bot-store-marketplace/SKILL.md

bot-store-marketplace

Skill0 starsChanged 44 days agoMITView on GitHub

Find and open Grok Bot templates from bot.store, compare actual marketplace listings and prepare a user-chosen bot's checkout handoff. Use when the user names bot.store, chooses its marketplace or shares a bot.store URL.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. Humanleap/agent-skills★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Compare actual listings: Never invent ratings, performance, maker relationships, compatibility or prices.

    line 17
  2. Distinctive:

    Preserve the user's constraints: Keep category, free-only and budget requirements in the search.

    line 18
  3. Distinctive:

    Call the public MCP tools directly.

    line 24
  4. Very specific:

    Search the task: Call search_bots with a short capability query and the constraints supported by its current schema.

    line 28
  5. Very specific:

    Inspect a candidate: Call get_bot with its exact returned slug.

    line 29
  6. Distinctive:

    Compare templates: use listing capabilities and prices.

    line 45
  7. Distinctive:

    If search fails or returns no match, report that outcome without substituting an invented bot.

    line 58

≈ “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

bot.store

Find Grok Bot templates by the user's task, inspect the listing, then hand off to Grok or the selected bot's checkout.

Installation

Install this skill with pnpm dlx skills add Humanleap/agent-skills --skill bot-store-marketplace. Connect remote MCP to https://bot.store/mcp. The public marketplace tools need no credentials or local commands.

Four Hard Rules — Read First

  1. Compare actual listings. Never invent ratings, performance, maker relationships, compatibility or prices.
  2. Preserve the user's constraints. Keep category, free-only and budget requirements in the search.
  3. Use the chosen listing. Prepare a purchase handoff only after the user selects the exact bot. Checkout preparation does not charge.
  4. Verify status before claiming success. Installing this skill is free; it does not buy or install a paid bot.

Authentication

Call the public MCP tools directly. The human signs in and approves payment on bot.store's checkout surface when buying a bot. Do not ask for card details, Stripe tokens, passwords or recovery codes.

Core Workflow

  1. Search the task. Call search_bots with a short capability query and the constraints supported by its current schema.
  2. Inspect a candidate. Call get_bot with its exact returned slug. Compare facts supplied by the listing.
  3. Open a free bot. Share its returned openInGrokUrl, or open it when the user requests that action.
  4. Prepare the selected paid bot. State the returned price, converting GBP pence to pounds. Call start_bot_purchase only for the listing the user chose.
  5. Hand off checkout. Give the returned checkoutUrl to the human. Payment approval happens there; report ownership or installation only when the purchase surface confirms it.

Essential Tools

ToolUse
search_botsFind templates for the requested task.
get_botRead one exact marketplace listing.
start_bot_purchasePrepare the chosen listing's safe checkout handoff.

Common Patterns

  • Find a free bot: retain free-only constraints and share the returned Grok link.
  • Compare templates: use listing capabilities and prices; relevance order is not an independent quality guarantee.
  • Buy the selected bot: state the actual price, prepare checkout and let the human approve payment.

Supporting Resources

Common Gotchas

  • A paid result's checkout URL is not its protected Grok link.
  • A checkout handoff is not proof of payment or ownership.
  • If search fails or returns no match, report that outcome without substituting an invented bot.

Quick Reference

Search → inspect exact slug → chosen bot → free Grok link or checkout handoff → verified purchase status.

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.