github avatar

Onboard Context Matic

A guided walkthrough that introduces you to the context-matic MCP server, which solves the problem of LLMs working from outdated or wrong SDK training data by providing live, version-aware API documentation. The tour shows you all four tools (fetch_api, ask, model_search, endpoint_search), lets you pick an API to explore, then demonstrates live lookups in your project's language. It's interactive and conversational, stopping at each step for your input. Use this the first time you set up context-matic or when you want to understand what APIs are available and how the server actually works. For end-to-end integration work, use integrate-context-matic instead.

skills.sh installs
1K
GitHub stars
41K
last updated
Aug 21, 2026

Install

$ npx -y skills add github/awesome-copilot --skill onboard-context-matic --agent claude-code

Installs into .claude/skills of the current project.

Files

Onboarding: ContextMatic MCP

This skill delivers a guided, interactive tour of the context-matic MCP server. Follow every phase in order. Stop after each interaction point and wait for the user's reply before continuing.

Agent conduct rules — follow throughout the entire skill:

  • Never narrate the skill structure. Do not say phase names, step numbers, or anything that sounds like you are reading instructions (e.g., "In Phase 1 I will…", "Step 1a:", "As per the skill…"). Deliver the tour as a natural conversation.
  • Announce every tool call before making it. One short sentence is enough — tell the user what you are about to look up and why, then call the tool. Example: "Let me pull up the list of available APIs for your project language." This keeps the user informed and prevents silent, unexplained pauses.

Phase 0 — Opening statement and tool walkthrough

Begin with a brief, plain-language explanation of what the server does. Say it in your own words based on the following facts:

Sponsors

Details

Repository
github.com/github/awesome-copilot
Categories
Backend & APIs, Git & Pull Requests, AI & Agent Building
First seen
Apr 16, 2026

More from github/awesome-copilot

All 318
1orchestra-research avatarchromaorchestra-research/ai-research-skillsOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function AP1Kskills.sh installs
2github avatarphoenix-cligithub/awesome-copilotDebug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review e1Kskills.sh installs
3hkuds avatarcli-anything-obsidianhkuds/cli-anythingCommand-line interface for Obsidian — Knowledge management and note-taking via Obsidian Local REST API. Designed for AI agents and power users who need to manag1Kskills.sh installs
4tencentcloudbase avatarai-model-nodejstencentcloudbase/skillsUse this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express, Koa, NestJS, serverless APIs, scheduled jobs, LLM1Kskills.sh installs
5laravel avatartailwindcss-developmentlaravel/boostAlways invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids992skills.sh installs
6tencentcloudbase avatarcloudrun-developmenttencentcloudbase/skillsCloudBase Run backend development rules (Function mode/Container mode). Use this skill when deploying backend services that require long connections, multi-lang988skills.sh installs