Setup and Verification
SkillAI & modelsInstall, configure, update, or verify mcp-stata across Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and VS Code. Activate when users ask to set up the Stata toolkit or troubleshoot the installation.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Setup and Verification skill
What this skill tells your AI
The instructions your AI receives, as published by brycewang-stanford/auto-empirical-research-skills in skills/64-tmonk-mcp-stata/skills/stata-setup/SKILL.md and read by ahel’s review.
Use the shared installer and verification flow instead of hand-writing per-agent config unless the user explicitly asks for manual steps.
Preferred Install Commands
Project-shared install:
bash plugin/install.sh --scope project
Personal install:
bash plugin/install.sh --scope user
Specific agent:
bash plugin/install.sh --agent codex
Pin a version if a lab wants to:
bash plugin/install.sh --version 2.5.1
Offline/local source:
bash plugin/install.sh --local-source /path/to/mcp-stata
Live verification:
bash plugin/install.sh --verify
What the Installer Does
- Uses the canonical server id
mcp-stata - Writes project-scoped configs where the client supports them
- Falls back to user-scoped config where project scope is not first-class
- Installs Codex skills into the Codex skills directory
- Installs the Gemini extension from
plugin/gemini-extension.json - Registers shared
~/.agents/skills/mcp-statasymlinks for compatible agents - Supports latest-by-default installs and explicit version pinning
Verification Standard
When the user asks whether setup is complete, verify more than “the file exists”:
- Stata discovery and edition
uv/uvxavailability- package availability for
reghdfeandgtools - graph-export readiness
- log-path emission for command output
- startup/profile behavior
If live verification is not possible on the current machine, state exactly what remains unverified.
Troubleshooting
- If Stata is not discovered, tell the user to set
STATA_PATH. - If a user-managed machine blocks temp files, logs, or graph export, use the stata-environment-diagnose skill.
- If project-wide configs are undesirable, re-run with
--scope user.
Signals
- GitHub stars
- 4k
- Forks
- 531
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
stata-setup- Source
- github.com/brycewang-stanford/auto-empirical-research-skills
github.com/brycewang-stanford/auto-empirical-research-skills
More in AI & models
Skill · anthropics
More in AI & modelswayfinder
Skill · mattpocock
More in AI & modelswizard
Skill · mattpocock
More in AI & modelsalgorithmic-art
Skill · anthropics
More in AI & modelscode-review-and-quality
Skill · addyosmani
More in AI & modelsai-first-engineering
Skill · affaan-m
More in AI & models