| name | wizard |
| description | Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself. |
| license | MIT |
| metadata | {"tags":"human-in-loop,operations,provisioning","groups":"human-ops","invocation":"model","source":"https://github.com/mattpocock/skills@84fdeffd12f2ee307994d1eb6feb48173b6e0502:skills/engineering/wizard"} |
Wizard
A wizard is a bash script that walks a human, step by step, through a manual procedure that's tedious to do by hand and tedious to re-explain to an AI every time. It opens each URL, says exactly what to click and copy, captures the values, writes them where they belong (.env, GitHub secrets), confirms at every stage, and shows how many stages are left. It might configure third-party services, run a one-off migration, or move the project from one state to another.
template.sh already handles stage-by-stage progress, confirmation gates, cross-platform URL opening (including WSL), hidden secret entry, idempotent .env upserts, gh secret and gh variable writes, and the closing summary. Your job is only to scope the procedure and author its stages. The library above the STAGES marker is identical in every wizard. That consistency is the point; never hand-edit it.
A wizard is ephemeral by default. Build it for one run, save it to a scratch or scripts/ path, and delete it when the job is done. Commit it only when the user wants a repeatable setup path that should live in the repo.
Process
1. Scope the procedure
Work out every manual step the human must take and every value captured along the way. Read the repo first. Don't ask cold:
- For setup:
.env, .env.example, .env.*, README, docker-compose*, framework config, and .github/workflows/* (every secrets.* / vars.* reference is a value the wizard must produce).
- For a migration or transition: the current state, the target state, and the irreversible actions between them.
Then show the user the ordered list of stages and the values each produces. Ask for confirmation; they may add, drop, or reorder stages.
Done when: every stage is named in order, and for each captured value you know (a) where the human gets it, (b) where it is written (.env, a GitHub secret, both, or nowhere; some stages are pure actions), and (c) whether it is secret (hidden entry) or public.
2. Map each stage's journey
For each stage, write the precise path a human follows: which URL to open, what to do there, where a value is shown, and which variable it fills. For example: "Dashboard → Developers → API keys → Reveal test key → copy". If you don't know the current UI or exact command, say so and ask the user or check the docs. Never invent steps that may not exist.
Done when: every stage traces to concrete instructions a stranger could follow.
3. Author the wizard
Copy template.sh to the target path. Replace the example stage with one stage per step, in dependency order. Use these library helpers: stage, say/step, open_url, ask/ask_secret, write_env, set_secret/set_var, and pause/confirm. Set TOTAL_STAGES to the number of stages you wrote.
Follow the template's rules: open the URL before asking for its value, use ask_secret for anything secret, write_env every persisted value, set_secret only for values CI actually needs, and confirm before any irreversible action. Each stage clears the screen so only the current step is visible. Keep a stage to one focused task so nothing the human needs scrolls away. Don't touch the library above the marker.
4. Verify and hand off
bash -n <script>; run shellcheck if available.
chmod +x <script>.
- Don't run it end-to-end yourself because it opens browsers and blocks on human input. Trace it statically instead. Confirm that every value from step 1 is captured and lands where step 1 specified, and that every
set_secret name exactly matches a secrets.* reference in CI.
- Tell the user how to run it. If it's a repeatable setup path, commit it and link it from the README so the next person runs the script instead of asking an AI.