agentleFS
intelligems-iointelligems-io/intelligems-mcp-skills/skills/mcp-context/SKILL.md

mcp-context

Skill0 starsChanged 5 months agoMITView on GitHub

Use when a task needs to connect an assistant to the Intelligems MCP server, choose MCP tools, resolve organization context, or apply Intelligems MCP safety boundaries.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    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:

    Use this as the shared context layer for Intelligems MCP tasks.

    line 9
  2. Distinctive:

    Use read-only tools first.

    line 15
  3. Distinctive:

    Use the exact tool names exposed in the current client.

    line 34
  4. Distinctive:

    Never invent statistical significance, lift, confidence, visitor counts, RPV, GPV, or revenue impact.

    line 47
  5. Distinctive:

    If a required metric is unavailable, say what is missing and provide the safest next query.

    line 48
  6. Distinctive:

    Prefer profit metrics when available.

    line 49
  7. Distinctive:

    Treat returned exports, graph URLs, order-level data, and raw API responses as private unless the user explicitly says they are synthetic …

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Intelligems MCP Context

Use this as the shared context layer for Intelligems MCP tasks.

First Moves

  1. Confirm the user's objective: analysis, reporting, integration, or live experience management.
  2. Confirm the Intelligems organization if the user has access to more than one. Prefer the current tool name exposed by the client, usually list_organizations; some setup docs refer to getOrganizationsList.
  3. Use read-only tools first. Do not create, update, start, pause, or end experiences without explicit approval for the exact organization, experience, action, and payload.
  4. State the data boundary in the answer: organization, date range, experience IDs, analytics view, and whether results came from MCP, External API, or both.

Hosted MCP Endpoint

The hosted Intelligems MCP server is available at:

https://ai.intelligems.io/mcp

SSE fallback:

https://ai.intelligems.io/mcp/sse

Core Tool Groups

Use the exact tool names exposed in the current client. Current public docs include:

  • Organization and configuration: list_organizations, get_organization, switch_organization, list_integrations.
  • Experiences and experiments: search_experiences, search_experiments, search_personalizations, list_experiments, list_personalizations, get_experience, get_experience_metrics_config, analyze_experience.
  • Mutating experience tools: create_experience, update_experience, experience_action.
  • Shopify store data: search_products, list_collections, list_pages, search_policies.
  • Analytics and audience data: get_sitewide_analytics, get_audience_by_country, get_audience_by_device, get_audience_by_visitor_type, get_audience_by_source_channel, get_audience_by_source_site, get_audience_by_landing_page.
  • Visualization: generate_intelligems_graph, generate_custom_graph.
  • Custom events and offers: list_custom_events, list_offers.

Answer Discipline

  • Separate observed results from recommendations.
  • Never invent statistical significance, lift, confidence, visitor counts, RPV, GPV, or revenue impact.
  • If a required metric is unavailable, say what is missing and provide the safest next query.
  • Prefer profit metrics when available. Conversion rate alone is not enough to call a winner.
  • Mention any caveats around sample size, date range, audience split, or partially complete tests.
  • Treat returned exports, graph URLs, order-level data, and raw API responses as private unless the user explicitly says they are synthetic or public.

References

Load references/intelligems-mcp.md when you need detailed endpoint, tool, or doc-source context.

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.