agentsclimarketplace
Sign in

Api integration builder

Skill intelligems-io/intelligems-mcp-skills/skills/api-integration-builder

Use when a user wants to build scripts, dashboards, alerts, or data pipelines with the Intelligems External API and needs source-backed endpoint guidance.From its SKILL.md

Install
npx -y skills add intelligems-io/intelligems-mcp-skills --skill api-integration-builder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.6 KB, 331 tokens by cl100k_base, as published. Nobody here has run it

API Integration Builder

Use this skill when building or reviewing code that calls the Intelligems External API.

First Moves

  1. Load references/external-api.md.
  2. Confirm the integration goal: reporting, monitoring, dashboarding, lifecycle automation, or data export.
  3. Confirm whether the task is read-only. Creating, updating, starting, pausing, or ending experiences requires explicit user approval.
  4. Use INTELLIGEMS_ACCESS_TOKEN or another environment variable. Never hardcode tokens.

Request Pattern

Base URL:

https://api.intelligems.io

Header:

intelligems-access-token: $INTELLIGEMS_ACCESS_TOKEN

Implementation Rules

  • Read the OpenAPI spec when endpoint shape matters.
  • Handle 400, 401, 404, 429, and 500.
  • Respect rate-limit headers: x-ratelimit-limit, x-ratelimit-remaining, and x-ratelimit-reset.
  • Prefer typed clients or schema validation for production integrations.
  • Keep raw API responses out of tracked files unless anonymized.
  • Log request IDs, endpoint names, and high-level status, not tokens or private payloads.
  • Treat export URLs, generated graphs, raw JSON, order-level CSVs, and line-item CSVs as private data.

Output For Code Tasks

When producing code, include:

  1. Environment variables required.
  2. Endpoint list used.
  3. Error handling.
  4. Rate-limit handling.
  5. Validation or test plan.
  6. Safety note for any mutating endpoint.

What ships with it: 1 file

4.7 KB alongside SKILL.md

references/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.