Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gongyijie85/mattpocock-skills-dsh-zh --skill wizard-zhgit clone --depth 1 https://github.com/gongyijie85/mattpocock-skills-dsh-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/wizard-zh)<a href="https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/wizard-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/wizard-zh/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/wizard-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/wizard-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.01162 |
| Opus 5 | $0.00036 | $0.00581 |
| Sonnet 5 | $0.00015 | $0.00232 |
| Haiku 4.5 | $0.00007 | $0.00116 |
Grade A, and why
wizard-zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
向导(Wizard)
wizard(向导) 是一个 bash 脚本,它一步步引导人类完成一个手工做起来繁琐、每次都要向 AI 重新解释一遍更繁琐的手动流程。它打开每个 URL、精确说出要点什么和复制什么、捕获这些值、把它们写到该去的地方(.env、GitHub secrets)、在每一阶段确认,并显示还剩多少阶段。它可能配置第三方服务、运行一次性迁移,或把项目从一种状态迁到另一种。
令人愉悦的 UX 已经由 template.sh 解决了——分阶段的进度、确认关卡、跨平台 URL 打开(包括 WSL)、隐藏的 secret 输入、幂等的 .env 更新(upsert)、gh secret/gh variable 写入,以及收尾总结。你的工作只是界定流程范围并编写它的 stages。 STAGES 标记之上的库部分在每个 wizard 中都是相同的;这种一致性正是要点——永远不要手工改动它。
wizard 默认是临时的——为一次运行而构建,保存到 scratch 或 scripts/ 路径,任务完成就删除。只有当用户想要一个应常驻仓库的可重复 setup 路径时才提交它。
流程
1. 界定流程范围
推演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。先读仓库——不要上来就问:
- 对于 setup:
.env、.env.example、.env.*、README、docker-compose*、框架配置,以及.github/workflows/*(每个secrets.*/vars.*引用都是 wizard 必须产出的一个值)。 - 对于迁移或过渡:当前状态、目标状态,以及它们之间不可逆的动作。
然后把有序的 stages 列表以及每个 stage 产出的值展示给用户并确认——他们可以增删或重排。
完成标准: 每个 stage 都按顺序命名,并且对于每个捕获的值,你都知道(a)人类从哪里得到它,(b)它写到哪里(.env、某个 GitHub secret、两者,或哪里都不写——有些 stage 是纯动作),以及(c)它是 secret(隐藏输入)还是公开的。
2. 绘制每个 stage 的旅程
对每个 stage,写下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、它填充哪个变量——例如 "Dashboard → Developers → API keys → Reveal test key → copy"。在你并不真正知道当前 UI 或确切命令的地方,明说并询问用户或查阅文档——绝不编造可能并不存在的步骤。
完成标准: 每个 stage 都能追溯到陌生人也能照做的具体指令。
3. 编写 wizard
把 template.sh 复制到目标路径。用每个步骤一个 stage 替换示例 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——并把 TOTAL_STAGES 设为你编写的 stage 数量。
守住模板设定的标准:在索要某个值之前先打开它的 URL,任何 secret 都使用 ask_secret,每个要持久化的值都 write_env,set_secret 只用于 CI 真正需要的值,任何不可逆动作之前都 confirm。每个 stage 都会清屏,只显示当前步骤——让一个 stage 只做一件聚焦的事,这样人类需要的内容不会滚出视野。不要碰标记之上的库部分。
4. 验证并交接
bash -n <script>;如果可用,运行shellcheck。chmod +x <script>。- 不要自己端到端运行它——它会打开浏览器并阻塞等待人类输入。改为静态追踪:第 1 步的每个值都被捕获并落在第 1 步所说的地方,每个
set_secret名称都精确匹配 CI 中的一个secrets.*引用。 - 告诉用户如何运行它。如果它是可重复的 setup 路径,提交它并从 README 链接,这样下一个人运行脚本而不是问 AI。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 45 lines · 73 tokens per session scan A ad2b415fc9c0
wizard-zh is a skill published in the GitHub repository gongyijie85/mattpocock-skills-dsh-zh (5 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,162 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.
Other skills, from other repositories
github-ops
GitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stale items, or any GitHub operational task beyond simple git…
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up CI/CD, containerizing an app, or checking production readiness before a release.
enterprise-agent-ops
Operate long-lived agent workloads with observability, security boundaries, and lifecycle management. Use when running long-lived agent workloads that need observability, security boundaries, or lifecycle control.
dsh-web-skin-developer
Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…
dsh-web-pet-developer
Create a pet for the dsh-pet plugin and integrate it into the dsh web GUI — author a v2 pet.json manifest plus an 8-column x 9-row atlas per the Codex/hatch-pet contract (live2d pets, voice packs and status decorations included), drop it into the pet-center user directory or contribute it as a built-in asset under…
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…