Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Wizard

ASecurity

Create an interactive Bash wizard for setup steps that only a human can complete.

3 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentsshellbashgitapi

Works with

cliapi

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 9/30/2026

$npx -y skills add marcellocurto/skills --skill wizard --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Wizard?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Wizard
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/marcellocurto-wizard/badge)](https://www.skillsdirectory.com/skills/marcellocurto-wizard)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: wizard
description: Create an interactive Bash wizard for setup steps that only a human can complete.
---

# Wizard

A **wizard** is a Bash script that guides a human through a manual procedure. It opens each URL, explains what to click and copy, captures values, writes them to the intended destinations, and shows progress. It might configure third-party services, run a one-off migration, or move the project from one state to another.

[template.sh](template.sh) provides 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. Scope the procedure and author its stages without hand-editing the shared library above the `STAGES` marker.

A wizard is ephemeral by default: save it to a scratch path for the requested run. When the user wants a repeatable setup path in the repository, retain it under the project's script conventions and document how to run it. Repeatability does not authorize a commit; commit only when the user has authorized that action.

## Process

### 1. Scope the procedure

Identify the steps and values needed for the requested setup, migration, or transition. Read relevant repository context before asking for information:

- For setup: relevant environment examples, README instructions, service and framework configuration, and CI workflows. Use `secrets.*` / `vars.*` references to identify consumers of the requested setup's values; unrelated references do not expand the wizard's scope. Reuse existing configuration where appropriate instead of collecting credentials again. Inspect secret-bearing files only as needed, without exposing their values.
- For a migration or transition: the current state, the target state, and the irreversible actions between them.

Reuse the procedure and authorization already established in the conversation. When the procedure is specified, prepare and validate the concrete script before seeking any missing approval for consequential execution. A stage outline can be a progress update; it does not require another approval round. Ask only about unresolved choices that materially affect the procedure, target, or captured values, and continue preparing independent stages while those choices remain open. Authoring the script does not authorize executing its external writes or irreversible actions.

**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.

Open the URL before asking for its value. Use `ask_secret` for secrets; never embed captured secrets in the script or print them. Persist each value only to its scoped destination: `write_env` for local environment files and `set_secret`/`set_var` for the relevant GitHub configuration. Do not copy a value to additional destinations merely because helpers exist.

Before each irreversible operation, show its target and consequence and require `confirm` to succeed before executing it. A declined confirmation must skip or abort the action; the banner's readiness pause is not a substitute. Keep these execution gates even when the user has authorized preparing the script.

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: it opens browsers and blocks on human input. Trace it statically instead: required values are captured or reused, each write reaches its intended destination, CI secret and variable names match the relevant consumers, and irreversible operations cannot run after a declined confirmation.
- Deliver the script with run instructions and identify consequential stages that require human confirmation. If execution still needs authorization, request it against this concrete artifact and its exact targets. Completion means the requested script is ready for the human to run; do not claim the setup or migration has executed.

Attribution

marcellocurtomarcellocurto
View sourceSee grades on GitHubMore from marcellocurto →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →