Menu
Set up the ContextA8C MCP server for accessing Automattic internal resources (Slack, Linear, P2s, GitHub Enterprise, etc.)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | setup-context-a8c |
| description | Set up the ContextA8C MCP server for accessing Automattic internal resources (Slack, Linear, P2s, GitHub Enterprise, etc.) |
| user-invocable | true |
| allowed-tools | Bash, Read |
Set up the ContextA8C MCP server for the current user.
IMPORTANT: The claude CLI binary may exist on the system regardless of which client the user is actually running. Do NOT use which claude to detect the client. Always ask the user first.
Ask the user which AI client they are currently using. Present these options:
Do NOT proceed until the user confirms their client. The setup steps differ per client and applying the wrong one will silently fail (e.g., claude mcp add registers for Claude Code only, not Claude Desktop).
npx --version
If npx is not found, tell the user to install Node.js (v18+) and stop.
Run the setup script:
bash .claude/skills/setup-context-a8c/setup-for-claude-code.sh
Guide the user through these manual steps (the agent cannot do this for them):
Tell the user to add this JSON config to their client's MCP settings file:
.cursor/mcp.json.vscode/mcp.json{
"mcpServers": {
"context-a8c": {
"command": "npx",
"args": ["-y", "@automattic/mcp-context-a8c"]
}
}
}
Tell the user to connect their Automattic accounts in a browser:
Wait for the user to confirm they have connected their accounts.
Tell the user to fully quit and relaunch their AI tool (not just start a new session) for the MCP server to load.
Launch the WooCommerce app on a simulator already authenticated into a given store (site credentials, application password, or WPCom), skipping the manual login UI. Meant to be referenced by other skills/workflows that need a logged-in session fast, but also directly runnable.
Debug a failing test or build error in WooCommerce iOS
Evaluate WooAIAssistant against a structured scenario suite with hard invariants + LLM-as-judge rubric scoring. Runs live against the demo store + gpt-5.1 via the woo-mobile-ai backend wrapper, writes a JSONL run record, compares against stored baselines, and surfaces regressions. Always delegated to a subagent so the main context only sees the markdown report.
Build the app, launch on simulator, and verify feature behavior via mobile-mcp interaction. Use after making changes to visually confirm they work from a user's perspective.
Create a pull request following WooCommerce iOS conventions
Discover and boot an iOS simulator. Use before any command that needs a simulator UDID.