一、④段整套同步(用户选候选 A)
- 新增 `references/stage-proto-doc/assets/产品文档模板.html`(16 KB/247 行,从备份拷、转 LF)。
- ④段 SKILL.md 换成备份 15:28 那版,并按模板口径改齐:
· 「产品文档框架」从「四块+一附录」改成**六节** —— 页面结构/功能清单/使用场景/操作流程/
跨页与界面状态/待确认与偏离;与模板同构,⛔ 不从空白页重写结构。
· 编号从 R/S/F 改成 **P 页面/S 场景/F 功能/J 二级功能**,各自唯一、按展示顺序通排。
· 保留旧版有价值的要求:每项功能补齐 做什么/入口在哪/输入边界/异常与恢复;重点功能三处标红;
横向流程图每步写清页面/功能/操作/完成判据。
· 完成标准「七节」→「六节」,自查清单同步换掉「需求」那批条目,补模板与配图两条。
· 路径 `designs/<项目>/` → `docs/pm/<项目>/ui/`(2 处)。
· 补回本机那条「每份产出文档开头都要有一张图」的引用(指向主 skill,段内不复述)。
- 主 skill 同步:四段结构表④行、④段沿革、画图小节(④段画页面结构图 + 用户路径)。
二、open-design 移到技能根(用户选候选 A)
- `git mv product-planning/references/stage-delivery/assets/open-design → open-design/`(4178 文件)。
- `.gitignore` 白名单加 `!/open-design/` —— 否则移出去就不再纳入版本控制。
- 引用改 11 处:路径形态 `assets/open-design/...` → `<技能根>/open-design/...`;
「随段携带的自带件」改称「同根技能」;「路径怎么找」那条改成自带件(段内相对路径)与
同根技能(`<技能根>/<技能名>/`)两类分开写。
- open-design 自己的 ATTRIBUTION.md 两处同步(它现在与 oil-ui-pro 同层)。
- 副作用(有益):命名闸门读数由 2063 降到 225 —— 此前它把 open-design 里 919 个第三方 md
当成规则一起扫了;现在只扫本包 23 个 md。已确认④段的 H1 与 4a/4b/4c 子步仍在检查范围内。
三、验收
- check_naming.py --ws E:/ProgramData/AIProject/contentm_agent = 通过 225 / 失败 0 / 提示 27。
- 活文件里 `assets/open-design` 残留 0;工作区 CRLF 文件 0。
kami-landing
A drop-in skill that turns a brief into a print-grade kami one-pager — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a white paper or studio one-pager, not an app UI.
Read first — the agent contract, schema, and self-check live in
SKILL.md. This README is the human quick-start.
What you get
A single self-contained HTML file with:
- Warm parchment canvas (
#f5f4ed), never#ffffff. - Single chromatic accent — ink-blue (
#1B365D), constrained to ≤ 5% of visible surface. - Serif at weight 500 for hierarchy. No italic anywhere.
- Tight print rhythm — line-heights 1.10–1.55, language-aware letter-spacing.
- Tabular-nums on every numeric stack.
- Solid-hex tag fills (no
rgba(), which print renderers double-paint). - 1px rings + whisper shadows for depth — no hard drop shadows.
- Multilingual by design (EN / zh-CN / ja stacks selectable via
the
languageparameter).
30-second tour
The skill is "agent-driven, no script": there's no compose.ts. The
agent reads SKILL.md, gathers the brief, then writes
out/index.html directly using the tokens and components catalogued
in design-systems/kami/DESIGN.md.
To preview the canonical OpenDesign instance:
open example.html
To start a fresh project:
- Open the skill in your agent (Claude · Cursor · Codex · …).
- Answer two rounds of brief questions (identity + content).
- Write the file. Done.
Files
design-templates/kami-landing/
├── SKILL.md # ← agent contract (read this first)
├── README.md # ← you are here
└── example.html # canonical OpenDesign rendering
Boundaries
- No external JavaScript. The page is paper, not an app.
- No hard drop shadows, no neumorphism, no
backdrop-filter. - No second accent color. No italic. No cool blue-grays.
- One
.tag.brushper page maximum (it's the only sanctioned gradient).
See also
design-systems/kami/DESIGN.md— the full token spec.design-templates/kami-deck/— sibling skill that produces a slide deck in the same kami language.- Upstream:
tw93/kami— original Claude skill (MIT) that the design system adapts.