Bash wizard for manual steps
Generates an interactive bash script that walks a person through manual steps such as dashboard setup, API keys and CI secrets, opening each URL and saving values to .env and GitHub secrets. Use when setup or a migration needs steps only a human can take.
wizard- Author
- Matt Pocock
- Source
- mattpocock/skills/skills/engineering/wizard @ abeeaf9
- License
- MIT · Copyright (c) 2026 Matt Pocock
About this skill
What it does
Some setup steps only a person can take: signing up on a dashboard, copying an API key, approving a cutover. Wizard has the agent write an interactive bash script that walks you through them.
The agent scopes the procedure from the repo: .env, .env.example, the README, docker-compose*, framework config and .github/workflows/*, where every secrets.* or vars.* reference is a value to produce. You confirm the ordered stages and what each captures. Each stage gets the exact path through the UI; where the agent does not know the current screens, it asks or checks the docs instead of inventing steps. It checks the result with bash -n, shellcheck if installed, and by reading it, not running it.
The folder ships template.sh. Everything above its STAGES marker is a fixed library the agent does not touch: "Stage 2/5" progress with one stage per screen, URL opening on Linux, macOS and WSL, hidden input for secrets, .env writes that replace existing lines and create the file with mode 0600, saved values offered again on a re-run, gh secret set and gh variable set with a to-do list when gh is missing, y/N gates and a final summary.
When to use it, and when not
Use it for infrastructure, credentials and CI secrets, an unfamiliar third-party dashboard, or a one-off migration.
Skip it for anything the agent can do itself. The script is meant for one run and then deleted; commit it only as a repeatable setup path linked from the README.
How to run it
The install command below puts SKILL.md, template.sh and the licence in place. The agent picks the skill up by its description when a task needs manual steps; to call it yourself:
- Claude Code:
/wizard, or ask for the skill by name. - Codex:
$wizard. - Cursor: type
/in the Agent chat and pickwizard.
Example: /wizard Walk me through getting the payment and email API keys this repo needs, write them to .env and set the CI secrets.
How it differs from similar skills
Env and config audit decides which values belong in environment variables and checks git history for leaks, but does not collect values from you; a wizard does. GitHub Actions CI writes the workflows whose secrets a wizard fills. Release checklist and Incident runbook go through steps with you in the chat; a wizard is a standalone script that runs without the agent. No other catalog skill generates one.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/wizard/SKILL.md https://anymodel.org/en/skills/matt-pocock/wizard/SKILL.md -o ~/.claude/skills/wizard/LICENSE https://anymodel.org/en/skills/matt-pocock/wizard/LICENSE -o ~/.claude/skills/wizard/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/wizard/agents/openai.yaml -o ~/.claude/skills/wizard/template.sh https://anymodel.org/en/skills/matt-pocock/wizard/template.sh
curl -fsSL --create-dirs -o ~/.agents/skills/wizard/SKILL.md https://anymodel.org/en/skills/matt-pocock/wizard/SKILL.md -o ~/.agents/skills/wizard/LICENSE https://anymodel.org/en/skills/matt-pocock/wizard/LICENSE -o ~/.agents/skills/wizard/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/wizard/agents/openai.yaml -o ~/.agents/skills/wizard/template.sh https://anymodel.org/en/skills/matt-pocock/wizard/template.sh
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml','template.sh') { $p = Join-Path "$HOME\.claude\skills\wizard" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/wizard/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml','template.sh') { $p = Join-Path "$HOME\.agents\skills\wizard" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/wizard/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/matt-pocock/wizard/SKILL.md
SKILL.md
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.
The delightful UX is already solved by template.sh: stage-by-stage progress, confirmation gates, cross-platform URL opening (including WSL), hidden secret entry, idempotent .env upserts, gh secret/gh variable writes, and a 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: built for one run, saved to a scratch or scripts/ path, deleted when the job's 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 that gets 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/*(everysecrets.*/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, and confirm: they may add, drop, or reorder.
Done when: every stage is named in order, and for each captured value you know (a) where the human gets it, (b) where it's written (.env, a GitHub secret, both, or nowhere; some stages are pure actions), and (c) whether it's 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, which variable it fills: e.g. "Dashboard → Developers → API keys → Reveal test key → copy". Where you don't actually know the current UI or the 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 the library helpers: stage, say/step, open_url, ask/ask_secret, write_env, set_secret/set_var, pause/confirm. Set TOTAL_STAGES to the number of stages you wrote.
Hold the bar the template sets: open the URL before asking for its value, use ask_secret for anything secret, write_env every persisted value, set_secret only the 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>; runshellcheckif available.chmod +x <script>.- Don't run it end-to-end yourself: it opens browsers and blocks on human input. Trace it statically instead: every value from step 1 is captured and lands where step 1 said, and every
set_secretname exactly matches asecrets.*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.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel