原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

design-harness Skill

代码仓库 ↗

作者:tigerless-labs★ 2351 个 skill

安装

What it does

Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.

  • Connects Instruction files the AI reads
  • Account or key Not confirmed yet (README not read yet)
  • Category 设计与网页
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/tigerless-labs-design-harness.svg)](https://mcp.popnx.com/en/skills/tigerless-labs-design-harness)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

Figma Context MCP

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

作者:GLips广泛使用↓ 15.2万/周★ 1.6万5个月前更新

MCP · 连接服务在你的电脑上运行

Next AI Draw.io

draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand

作者:DayuanJiang广泛使用↓ 2.2万/周★ 3.7万 整个仓库的星标3天前更新

MCP · 连接服务在你的电脑上运行

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

作者:pascalorg广泛使用↓ 1037/周★ 2.6万 整个仓库的星标4天前更新

MCP · 连接服务电脑或云端✓ 服务方 · pascal.app

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
design-harness
impeccablediagram-designfrontend-slidesguizang-ppt-skill
作者tigerless-labspbakauscathrynlaveryzarazhangruiop7418
Skill 数1111–
GitHub 星标235111,25067,61132,40729,891
最近代码更新2026年9月1日2026年11月17日2026年11月13日2026年6月24日2026年10月30日
许可证–Apache-2.0MITMITAGPL-3.0

tigerless-labs 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

Claude CodeCodex

依据开发者 README 和 repo 中的文件夹

安装

Is it safe?

  • Who made it

    GitHub account tigerless-labs (organization) is only 5 months old: take extra care

  • Use and upkeep

    ★ 235 stars, few users so far · code last changed 2026年9月1日

  • Any scripts?

    10 scripts that can run on a computer: scripts/build_canvas.py, scripts/check_doc_links.py, scripts/check_style_pack.py, scripts/check_workspace.py and 6 more

  • Uses the internet?

    Could not check every script (some are too large); read them first

  • Changes machine-wide settings?

    No hooks or writes to machine settings found

Checked automatically from the repo files at commit 9aca84e (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

第一步:你用哪个 AI?

选择你用的应用,本页只显示该应用的安装方法

Option 1Upload to claude.ai (web and app)

  1. Download from GitHub

    This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier

    Download from GitHub (whole repo) ↗

    Unzip it, then zip only the plugins/design-harness/skills/design-harness folder again. The ZIP must have a design-harness folder with SKILL.md at the top level, no loose files

  2. Open Skills on claude.ai and upload

    +Create skillUpload a skillpick design-harness.zip

    Open claude.ai/customize/skills ↗

  3. No Upload button? Turn on file creation first

    SettingsCapabilitiesCode execution and file creation

    Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free

Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)

Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)

Checked against official docs 2026年11月12日 · Source: support.claude.com, support.claude.com, code.claude.com

Option 1让 Claude Code 帮你安装

复制这句话,粘贴到 Claude Code 的对话中

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

重新打开 Claude Code,输入 /design-harness,或直接提出相关任务,Claude 会自动选用

Checked against official docs 2026年11月12日 · Source: code.claude.com

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

开发者推荐的方式

正在检查命令 · 通过后才会显示复制按钮

摘自开发者 README,会下载并运行开发者的代码

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.claude/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

  3. 重新打开 Claude Code,输入 /design-harness,或直接提出相关任务,Claude 会自动选用

自己安装的 Skill 可用于 ChatGPT 桌面应用、Codex CLI 和 IDE 中的 Codex 扩展 · 网页版和手机版 ChatGPT 不能使用自己安装的 Skill,只能使用目录中插件自带的 Skill

ChatGPT 桌面应用

ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill

Option 1让 ChatGPT 帮你安装

在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2自己放入文件夹

把 design-harness 文件夹放到 ~/.agents/skills/design-harness

~ 是你的主文件夹($HOME)

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.agents/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

安装之后

  • ChatGPT 桌面应用:打开侧边栏中的 Skills,确认 Skill 已出现
  • 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
  • Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

网页版和手机版 ChatGPT

不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill

想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

Option 1让 Codex 帮你安装

复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称

Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.agents/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

  3. 重新打开 Codex 并提出相关任务,Codex 会列出这个 skill

Option 1让 Cursor 帮你安装

复制这句话,粘贴到 Cursor 的对话中

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

在 Cursor 的 Agent 聊天中输入 / 并选择 design-harness

Checked against official docs 2026年11月12日 · Source: cursor.com

For Terminal users

Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。

  1. 打开终端

    Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”

  2. 把 skill 文件夹复制到 ~/.cursor/skills

    这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹

    正在检查命令 · 通过后才会显示复制按钮

  3. 在 Cursor 的 Agent 聊天中输入 / 并选择 design-harness

Option 1Let the AI install it

适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat

Where to install

正在检查命令 · 通过后才会显示复制按钮

正在检查命令 · 通过后才会显示复制按钮

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。

在 GitHub 上查看 ↗

已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹

查看原始 SKILL.md

以下文字来自开发者的 repo,不是 PopNx MCP 的指令

显示前 8,000 个字符 · 在 GitHub 打开完整文件

---
name: design-harness
description: A decision board for evidence-based calls — the human adjudicates, the agent runs the errands. Three layers (sources → ideas → output) in plain markdown, synced on the human's command, projected onto a visual canvas. Use for vendor/tool selection, literature reviews, due diligence, competitive analysis, or any contested call that must stand on traceable evidence — triggers like "file these papers", "put this on the board", "assemble the design", "how do we decide this".
license: MIT
allowed-tools: Bash(python3 ${CLAUDE_SKILL_DIR}/scripts/*)
metadata:
  author: tigerless-labs
  repository: https://github.com/tigerless-labs/design-harness
---

# design-harness — the human adjudicates, the agent runs errands

Markdown is the **single source of truth**; the canvas HTML, every layer index, and the
location registry are projections, rebuildable at any time. Judgment comes only from the
human; you lay out options and evidence and run the errands — never adjudicate in the
human's place.

## Structure

### Workspace layout

```
<workspace>/
├── target.md             the human's acceptance criteria; source of the output form
├── logs.md               append-only change ledger (see "Disciplines · Ledger")
├── index.md              workspace entry point
├── sources/<type>/*.md   ① evidence: one source, one card
├── ideas/*.md            ② judgments (archive/ holds archived cards)
├── output/…              ③ assembly; internal structure set by the chosen output form
└── board/*.md            free surface: one file, one board
```

A host may hold many workspaces under any directory names; the sole registry is
`.design-harness/config.json` at the host root — discovery trusts the registry, never
the directory name.

Every layer also carries an `index.md`, grouped under tag headings (`## TAG: one line on
why they belong together`), unclassified cards flat at the end after a `---` divider and
an *unclassified* marker. Search goes through the indexes; there is no classification
layer.

### Three layers + the free surface

1. **sources/ — evidence.** One source, one card, filed under `sources/<type>/`. The
   agent ingests and grades freely, and invents the type directories itself — no preset
   list; name them after what the source is (papers, github, podcasts, …), adding
   directories as needed. The directory name projects verbatim as the card's badge on
   the canvas.
2. **ideas/ — judgments.** **Judgment comes only from the human**: decision judgments the
   human voices in conversation are transcribed into idea cards automatically, and the
   human can simply ask for a card to be added; the agent transcribes, never invents.
   Two states: live (the file exists) and archived (moved into `ideas/archive/`, never
   deleted). A new idea repeating an old card's judgment merges automatically; a
   conflicting one puts both on the board for the human to pick.
3. **output/ — assembly, the convergent layer.** **First assembly is human-initiated**;
   its form comes from [references/output-forms/](references/output-forms/system-design.md)
   and the human's `target.md`. Ideas diverge, output converges: output changes only on
   the human's word (see "Workflow · Sync").

One free surface besides: **board/** — the human's own boards, one markdown file per
board (comparison matrices, theme grids, any scratch reasoning). **No schema, no
required fields** — this freedom belongs to the human; edit only when asked ("lay these
three sources out as a comparison").

### Card schema and templates

- A card = **frontmatter + title + summary**. No fixed sections; references are inline
  links in the summary.
- `ideas/` cards (including `archive/`): frontmatter **requires `id` and `type`**;
  `tags` and `conflicts` optional (see "Exactly three structured facts"). No status
  field — the file's existence is the live state, sitting under `archive/` is the
  archived state.
- `sources/` cards: frontmatter optional; when present only `tags` is read.
- `board/` documents: **no schema**. The board is **terminal**: it may reference any
  layer, but sources/ideas/output must never reference the board — distill a board's
  conclusions into idea cards.

idea card template:

```markdown
---
id: <kebab-slug, matching the filename>
type: idea
tags: [<at most one; omit the whole line>]
conflicts: [<ids of prior cards this judgment contends with; omit when none>]
---

# <the judgment in one sentence>

<Summary: what the judgment says and why; the evidence and prior cards it stands on as
inline links.>
```

source card template:

```markdown
---
tags: [<at most one; the whole frontmatter may be omitted>]
---

# <source name + one-line characterization>

<Core content + relevance to this project; the original provenance (arXiv/URL/date/
authors) as inline links.>
```

target template:

```markdown
# target — acceptance criteria for the output

## Purpose
(One paragraph: what this workspace decides, for whom, and where the boundaries are.)

## Current requirements
- (One checkable requirement per line.)

## Fulfilment map
- (Requirement → output file mapping, updated with each assembly.)
```

### Exactly three structured facts

1. **References** — inline markdown links in the card body. Forward only: a link points
   at the evidence or prior cards this card stands on, never at supporters. "Who cites
   me" is a projection-derived backlink, never written down. **Acyclic**: mutual
   references mean the two cards should merge, or one edge is a mistakenly written
   backlink — delete it.
2. **Tags** — single level, **at most one per card**, optional. A card that truly
   belongs to two tags is two cards: split it. No tag just means unclassified. Tags may
   be proposed by the human or assigned by the agent.
3. **Conflict** — the optional `conflicts: [<other card's id>]` in the **newer** card's
   frontmatter, declaring a judgment conflict with prior cards (written on the new card
   only, acyclic, same direction as references). The field lives exactly as long as the
   conflict: the human's adjudication removes it — archive the loser and the edge
   vanishes with the card; rewrite in place and the entry is deleted. The indexes'
   pending-conflict annotations derive from this field.

Everything else — backlinks, distances, coordinates, clusters, index groupings — is
derived and never enters the truth.

### Rendering contract — the engine's minimum

Everything projection needs. **This section is the engine; everything else in this file
is methodology**, freely reconfigurable per schema — one engine serves many thin
schemas, a new scenario is a new schema configuration rather than a new engine; the
contract binds files, and the CLI is only the first host.

- Four layer names: `sources/` and `ideas/` become canvas nodes, `output/` and `board/`
  become document panels. Paths containing an `archive/` segment are excluded;
  `index.md` is excluded.
- Files are UTF-8 markdown.
- Frontmatter is optional; when present it must close (`---` … `---`).

Everything else degrades without breaking: no H1 → show the filename stem; no tag → the
*unclassified* group; any source type directory → the name projects verbatim;
unresolvable link → no edge. Silent data loss is a validator error, never waved through:
markdown under an unknown top-level directory, or frontmatter opened but never closed,
is INVALID.

### Canvas — the only projection surface

The canvas is the human's main thinking surface and **only a projection** — it holds no
facts and accepts no writes that bypass markdown. It doubles as the sharing surface:
every card links back to its evidence, so handing someone the board hands them the
reasoning behind the design. There is exactly one canvas — the
unified canvas ([template](canvas/template.html); its interaction contract lives in the
workspace's canvas module doc) — and exactly one builder: the rules (truth-driven,
edges = in-card references, layout derived from references

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
235
开发者
tigerless-labs
许可证
未注明许可证 此 repo 未注明许可证,默认作者保留所有权利;转发或商用前请先询问作者。
最近代码更新
2026年9月1日
repo 中的 SKILL.md 文件(含译本和模板)
1
主题
agent-skills, ai-agents, claude-code, claude-code-plugin, codex, decision-support, evidence-based, knowledge-management, literature-review, markdown, provenance, research-tools