double6-workbench-builder SKILL.md skillA
double6-workbench-builder from double6-ai/double6-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add double6-ai/double6-skills/double6-workbench-builder@v1.2.0Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- double6-ai/double6-skills
- Path
skills/double6-workbench-builder/SKILL.md- Versions recorded
- 6
- Latest version
- v1.2.0, committed Oct 23, 2026
- First version recorded
- Aug 7, 2026
- Size
- 5,530 bytes
- Repository stars
- 39
- License
- MIT
把普通用户反复要做的真实事情构建成离线优先、严格单文件、个人数据留在当前设备的本地工作台（index.html）。用户提到个人工作台、学习台、备考台、任务面板、内容/社媒运营台、阅读或研究追踪、记录与复盘工具，或想把重复流程做成可保存恢复的页面时应使用。Use when the user asks for a personal workbench, dashboard, tracker, planner, habit/reading/research tracker, content or social-media ops board, study or exam desk, or wants a repeated workflow turned into an offline single-file local web app. 联网、多人协作、账号、支付和发布属于独立外部流程（network, multi-user, accounts, payments and publishing are out of scope）.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Double6 工作台制作器 把澄清后的真实重复工作做成一个可离线打开的 `index.html`。触发后先读 `references/runtime-contract.md`；它是完整运行合同，本文只保留路由和执行入口。 ## 核心流程 1. 从 CLI 返回的 16 个领域中选择主场景和最多两个辅助场景；`evidence_spans` 必须逐字摘自用户原话。 2. 用 `start` 建立 run；只询问会改变对象、核心动作、数据边界或验收结果的问题，普通需求和偏好澄清最多五问，必要授权确认独立计数，并给出推荐答案。 3. 默认用 `propose --from-snapshot` 展示包含 4–15 个核心模块、内置 starter 和可选模块的完整理解稿；用户确认必须绑定当前理解稿 SHA。 4. 确认后用 `build` 只生成一个推荐候选，再运行 `evaluate --preflight`。环境未就绪时先修复环境。 5. 让用户查看候选；视觉确认或拒绝必须绑定当前候选 SHA。需要改 renderer/CSS 时进入 `renderer_revision_required`，不得空跑重建。 6. 用 `evaluate` 完成静态与浏览器验收；只有完整通过才交付。`--skip-browser` 只是预检，不能形成交付。 在 skill 根目录运行 CLI（需要 Python 3.10+，构建只用标准库；浏览器验收另需 Playwright + Chromium）： ```bash python scripts/double6.py start --run <run_dir> --request "<用户原话>" --route-file route.json python scripts/double6.py respond --run <run_dir> --event-file event.json python scripts/double6.py propose --run <run_dir> --from-snapshot python scripts/double6.py build --run <run_dir> python scripts/double6.py evaluate --run <run_dir> --preflight python scripts/double6.py evaluate --run <run_dir> ``` 事件文件与产品文件的最小示例、SHA 字段名（`presented_content_sha256` / `presented_candidate_sha256`）见 `references/host-integration-playbook.md`。 ## 必守边界 …
Read the whole file at its exact version.
How to install
mdr add double6-ai/double6-skills/double6-workbench-builder@sha256:340066e4aae199acThe line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_p3vtqvofesxbmoye)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Aug 7, 2026 and Oct 23, 2026, about one every 15 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.2.0 latest | 2026-10-23 | d66a08f | 5,530 B | A | view · diff |
| v1.2.0 | 2026-10-16 | 5d3cbbc | 4,471 B | A | view · diff |
| v0.42.0 | 2026-10-15 | 786f6c1 | 4,376 B | A | view · diff |
| v0.41.0 | 2026-08-09 | 7dc88b5 | 3,726 B | A | view · diff |
| git:20260807.f9d68fe | 2026-08-07 | f9d68fe | 17,153 B | A | view · diff |
| git:20260807.e2a4938 | 2026-08-07 | e2a4938 | 17,098 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5530 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
double6-ai/double6-skills · 39 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_p3vtqvofesxbmoye GET https://markdownregistry.com/api/v1/resolve?ref=double6-ai/double6-skills/double6-workbench-builder GET https://markdownregistry.com/api/v1/blob/340066e4aae199ac3344523135c411b3a0596bc7f48760a2baa59bc3e663a458
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.