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

生成一个交互式 bash 向导,引导人类完成只有他们能执行的步骤。适用于配置基础设施、设置凭证或 CI 密钥、操作不熟悉的第三方面板、或执行一次性迁移或切换。不要让代理替自己执行本应由人类完成的步骤。

429 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsshellbashdockergitapi

Works with

api

Security Analysis

A100/100

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

Scanned 9/29/2026

$npx -y skills add devcxl/mattpocock-skills-zh --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/devcxl-wizard/badge)](https://www.skillsdirectory.com/skills/devcxl-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: 生成一个交互式 bash 向导,引导人类完成只有他们能执行的步骤。适用于配置基础设施、设置凭证或 CI 密钥、操作不熟悉的第三方面板、或执行一次性迁移或切换。不要让代理替自己执行本应由人类完成的步骤。
---

# 向导

**向导(Wizard)** 是一个 bash 脚本,逐步引导人类完成手动流程——这些流程手动做很繁琐,每次重新向 AI 解释也很麻烦。它会打开每个 URL,精确说明要点击什么和复制什么,捕获值,将其写入正确的位置(`.env`、GitHub secrets),在每个阶段确认,并显示剩余阶段数。它可能配置第三方服务、运行一次性迁移、或把项目从一个状态迁移到另一个状态。

便捷的 UX 已经由 [template.sh](template.sh) 解决——分阶段显示进度、确认关卡、跨平台 URL 打开(含 WSL)、隐藏密文输入、幂等的 `.env` 写入、`gh secret`/`gh variable` 写入,以及一个结束汇总。**你的工作只是界定流程范围并编写其阶段。** 每个向导中 `STAGES` 标记上方的库代码都是相同的——这种一致性正是关键所在,永远不要手动编辑它。

向导默认是临时的——为一次运行而创建,保存在 scratch 或 `scripts/` 路径下,任务完成后删除。仅当用户希望创建一个可重复的设置路径(应留在仓库中)时才提交它。

## 流程

### 1. 界定流程范围

找出人类必须执行的每一个手动步骤以及沿途捕获的每一个值。先阅读仓库——不要凭空提问:

- 对于设置:`.env`、`.env.example`、`.env.*`、`README`、`docker-compose*`、框架配置,以及 `.github/workflows/*`(每个 `secrets.*` / `vars.*` 引用都是向导必须产生的值)。
- 对于迁移或切换:当前状态、目标状态,以及两者之间的不可逆操作。

然后向用户展示有序的阶段列表以及每个阶段产生的值,并确认——他们可能会添加、删除或重新排序。

**完成条件:** 每个阶段都按顺序命名,并且对于每个捕获的值,你知道 (a) 人类从哪里获取它,(b) 它写入哪里(`.env`、GitHub secret、两者皆写,或都不写——有些阶段只是纯操作),以及 (c) 它是秘密(隐藏输入)还是公开的。

### 2. 绘制每个阶段的路径

为每个阶段编写人类遵循的精确路径:打开哪个 URL,在那里做什么,值在哪里显示,填充哪个变量——例如"Dashboard → Developers → API keys → Reveal test key → copy"。如果你不确定当前 UI 或确切命令,请说明并询问用户或查阅文档——永远不要编造可能不存在的步骤。

**完成条件:** 每个阶段都能追溯到具体的指令,让一个陌生人也能照着做。

### 3. 编写向导

将 `template.sh` 复制到目标路径。将示例阶段替换为每个步骤一个 `stage`,按依赖顺序排列。使用库辅助函数——`stage`、`say`/`step`、`open_url`、`ask`/`ask_secret`、`write_env`、`set_secret`/`set_var`、`pause`/`confirm`——并设置 `TOTAL_STAGES` 为你编写的阶段数。

保持模板设定的标准:在要求值之前先打开 URL,对任何秘密内容使用 `ask_secret`,每个持久化的值都使用 `write_env`,仅对 CI 实际需要的值使用 `set_secret`,在任何不可逆操作前使用 `confirm`。每个 `stage` 都会清屏,使当前步骤成为唯一可见内容——让一个阶段只做一件事,这样人类需要的东西就不会滚出视野。不要触碰标记上方的库代码。

### 4. 验证并移交

- `bash -n <script>`;如果可用则运行 `shellcheck`。
- `chmod +x <script>`。
- 不要自己端到端运行——它会打开浏览器并阻塞等待人类输入。改为静态跟踪:步骤 1 中的每个值都被捕获并写入步骤 1 指定的位置,并且每个 `set_secret` 名称精确匹配 CI 中的 `secrets.*` 引用。
- 告诉用户如何运行它。如果这是一个可重复的设置路径,提交它并在 README 中链接,这样下一个人就能直接运行脚本,而不是求助 AI。

Attribution

devcxldevcxl
View sourceSee grades on GitHubMore from devcxl →
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', ...

698461 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 →