Skip to Content

Agent Skills Setup

Before you begin

The skills need two things to do real work:

  1. A CompetLab project with competitors being monitored. The skills read your monitoring data, so you need an account and at least one project set up. New here? Create a free account  and set up your first project first. A trial works.
  2. The CompetLab MCP server configured with your API key. This is how every skill reaches your data. If you haven’t set it up, follow the Connect guide first — it’s the hard prerequisite. Without it, a skill either falls back to web-research-only or tells you it can’t run.

Authentication lives entirely in the MCP configuration. There’s no separate skill-level API key to set.

Install

Pick whichever path fits your setup — all three install the 13 skills. One caveat: the CMO-report orchestrator also reads a set of shared companion docs, and only the manual copy reliably places those (the skills CLI omits them — see its tab).

In a recent version of Claude Code, add the marketplace and install the plugin:

/plugin marketplace add competlab/competlab-ci-skills /plugin install competlab-ci-skills@competlab-ci-skills

The install string is plugin@marketplace — both happen to be named competlab-ci-skills. This is the cleanest path: it keeps the skills updatable through the marketplace.

The plugin ships the companion docs in its cache, where the CMO-report orchestrator finds them via a fallback. For the guaranteed layout — the docs placed at your skills root — the Manual copy tab is the surest path.

Confirm the MCP connection

The skills are only as useful as the MCP connection behind them. Before running one, confirm your agent can reach CompetLab — ask it to list your projects, or check that the mcp__competlab__* tools are available. If the connection isn’t there, the skills will say so rather than invent data. (Details in the Connect guide.)

Optional: a GitHub token for ecosystem scans

Two of the research skills — competlab-ai-ecosystem and competlab-agent-adoption — query public GitHub data. GitHub rate-limits unauthenticated requests to 60 per hour, which a broad scan can exhaust. Set a GH_TOKEN environment variable with a GitHub token to lift that limit. It’s optional and only affects those two skills; everything else runs without it.

Run your first skill

Skills trigger on plain-language requests — each one advertises the phrasings it responds to, so you don’t memorize commands. A few examples:

Give me a weekly briefing for my Acme project. Write a battlecard for Rival Inc. Deep dive on competitor rival.com. Build a CMO report for Acme.

Your agent recognizes the intent, loads the matching skill, pulls the data through the MCP server, and writes the deliverable. For a single-competitor skill like the battlecard or the dossier, name the competitor; for the orchestrator, name the project.

Next steps

  • Skill reference → — all 13 skills, what each needs, and the phrasings that trigger them.
  • MCP Connect → — set up or double-check the MCP server the skills depend on.
Last updated on