open/ktg-plugin-marketplace
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions

docs(claude-design): update CLAUDE.md with Scope fence + authoring rules

Browse source 
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-05-18 12:37:11 +02:00
commit 2a398b6297
1 changed files with 72 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

103
plugins/claude-design/CLAUDE.md
View file

@ -1,43 +1,88 @@
# claude-design
## Kontekst
## Context
Plugin som skal være ekspert på **Claude Design** (claude.ai/design) — Anthropics surface for å lage interaktive artifacts via prompt.
Skal dekke hele prosessen fra idé til ferdig artifact:
1. Forstå hva brukeren vil lage
2. Velge riktig artifact-type og prompt-strategi
3. Generere effektive prompts for Claude Design
4. Iterere og refine basert på preview
5. Polere og levere
Den endelige sammensetningen — skills, agenter, kommandoer — defineres gjennom Voyage-pipelinen og er IKKE fastlagt på forhånd.
This plugin is an expert on **Claude Design** (`claude.ai/design`) — Anthropic's Labs research preview for generating interactive design artifacts from a prompt. It walks the operator through the full lifecycle: idea → intent-preset selection → audience and destination → DESIGN.md anchor → five-layer prompt drafting → copy-paste delivery → iteration coaching → ship-readiness handoff. It does not generate artifact code itself and it does not drive the browser; it produces the prompt that the operator pastes into Claude Design.
## Status
`0.1.0-pre` — bootstrap. Innholdet bygges via `/trekbrief` → `/trekresearch` → `/trekplan` → `/trekexecute` → `/trekreview`.
`v0.1.0`. Surface:
## Marketplace-kontekst
- One skill: `claude-design-facilitator` (auto-fire + explicit `/claude-design-facilitator` slash command)
- Five foundation references under `skills/claude-design-facilitator/references/`
- Eight per-preset references under `skills/claude-design-facilitator/references/presets/`
- Five test scripts under `tests/` plus a `verify.sh` roll-up
- A `.coverage.md` preset manifest at the plugin root (canonical input for SC2 and the SC3 Authoritative-claims registry)
- `LICENSE` (MIT), `GOVERNANCE.md` (marketplace fork-and-own blurb), `README.md`, `CHANGELOG.md`
Plugin ligger inne i `ktg-plugin-marketplace`. Ingen egen git-repo, ingen egen Forgejo-remote. Alle commits til marketplace-repoet på `git.fromaitochitta.com/open/ktg-plugin-marketplace`.
No commands, no agents, no hooks, no MCP servers at v0.1. The single skill is the entire user-facing surface.
Følg marketplace-konvensjonene fra rot-CLAUDE.md:
## Marketplace context
- Norsk dialog, engelsk kode/dokumentasjon
- Conventional Commits: `type(scope): description` — scope er `claude-design`
- Hooks i Node.js (.mjs), ikke bash
- Null npm-avhengigheter i hooks
- Docs-trippel oppdatert i samme commit ved feature-endringer: plugin `README.md`, plugin `CLAUDE.md`, rot-`README.md`
This plugin lives inside `ktg-plugin-marketplace`. No separate git repository, no separate Forgejo remote. All commits go to the marketplace repository at `https://git.fromaitochitta.com/open/ktg-plugin-marketplace`.
## Arbeidsflyt
Marketplace conventions inherited from the root `CLAUDE.md`:
Pipelinen er sannhet inntil release:
- Conventional Commits — `type(scope): description`; scope is `claude-design`
- Hooks in Node.js (`.mjs`), never bash (this plugin ships no hooks at v0.1)
- Zero npm dependencies in hooks and scripts
- Docs-triple updated in the same commit on every feature change: plugin `README.md` + plugin `CLAUDE.md` + root `README.md`
1. Brief lukker scope og scope-grenser
2. Research samler eksterne kilder (Anthropic cookbook, claude.ai/design-dokumentasjon, community-mønstre)
3. Plan beskriver fil-for-fil hva som skal lages
4. Execute leverer kode/innhold
5. Review er release-gate
## Architecture (v0.1)
Voyage-policy: Opus på alle sub-agenter og orchestrator-faser.
- **`skills/claude-design-facilitator/SKILL.md`** is the auto-fire entry point AND the explicit `/claude-design-facilitator` invocation surface. The skill body documents the eight-phase facilitation flow.
- **`skills/claude-design-facilitator/.triggers.txt`** lists the natural-language phrases the skill auto-fires on. `tests/test-skill-triggers.sh` validates every phrase appears in the SKILL.md description.
- **`skills/claude-design-facilitator/references/`** is the knowledge base. Five foundation references (00–04) plus eight per-preset references under `references/presets/`. Every authoritative claim cites an Anthropic primary source inline.
- **`.coverage.md`** at the plugin root is the SC2 manifest (preset enumeration with evidence-grade labels) and the SC3 Authoritative-claims registry (bullet list of files that must carry Anthropic-domain citations).
- **`tests/`** + **`verify.sh`** enforce the brief Success Criteria: SC1 dogfood-log format, SC2 per-preset coverage, SC3 citation discipline, plus skill description quality and plugin structural integrity.
The skill body never offers to generate artifact code, automate the browser, or store artifact history (per [Non-Goals in README](README.md)). It produces prompts.
## Scope fence
This plugin covers **pre-design and during-design** for `claude.ai/design`: idea → prompt → preview → iterate → ship-readiness.
**Post-design** — critique, accessibility audit, UX copy review, research synthesis, design-system audit, engineering handoff — is out of scope and lives in Anthropic's official `knowledge-work-plugins/design` (`https://claude.com/plugins/design`). This plugin must never duplicate the commands `/critique`, `/accessibility`, `/ux-copy`, `/research-synthesis`, `/design-system`, `/handoff` — with or without a `claude-design:` namespace prefix. `tests/validate-plugin.sh` assertion (h) enforces this scope fence mechanically.
The lifecycle-stage coverage map and the operational handoff between the two plugins are documented in `skills/claude-design-facilitator/references/04-handoff-and-scope.md`.
## Authoring rules
Every contribution to this plugin must respect these rules:
- **Language: English everywhere.** Plugin file content — `README.md`, `CLAUDE.md` (this file), `CHANGELOG.md`, `SKILL.md`, all `references/*.md`, all `tests/*.sh` output messages, every code comment — is English. This is the operator override of the marketplace's default Norwegian-dialogue policy; documented in the v0.1 brief. The `tests/validate-plugin.sh` assertion (j) emits a WARN on Norwegian diacritics in shipped content; review case-by-case (citation slugs occasionally legitimately carry diacritics, but the default is zero hits).
- **No operator-private context in shipped content.** No `kjell`, no `vegvesen`, no copy-paste from `REMEMBER.md` / `TODO.md` / `NEXT-SESSION-PROMPT.local.md` / other local-only files. `tests/validate-plugin.sh` assertion (i) enforces this with a recursive grep that excludes the local files themselves.
- **Evidence-grade label discipline.** Every per-preset reference file carries an inline `Evidence grade:` label on line 4. The three grades are `Anthropic-documented + community-validated`, `Community-only`, and `Experimental`. `.coverage.md` is the canonical registry. SC2 and SC3 read from `.coverage.md` directly — keep it in sync.
- **URL canonicalisation.** All `support.claude.com` references use the form `https://support.claude.com/en/articles/<numeric-id>-<slug>`. Numeric IDs are stable across slug rewrites; slug-only URLs are not. `https://anthropic.com/news/...` and `https://claude.com/blog/...` follow whatever slug Anthropic publishes.
- **No NIH of Anthropic surfaces.** The plugin recommends Anthropic's `knowledge-work-plugins/design` as the downstream tool; it does not duplicate that plugin's functionality.
## Workflow
The Voyage pipeline produces v0.1 and every subsequent feature change:
1. **Brief** closes scope and scope boundaries
2. **Research** gathers external sources — Anthropic primary material (news posts, support articles, blog posts, open-source skills, tutorials, plugins), plus community practitioners with attribution
3. **Plan** specifies file-by-file what gets built
4. **Execute** delivers the code and content
5. **Review** is the release gate (`/trekreview`)
Voyage policy: Opus across all sub-agents and orchestrator phases (per `feedback_voyage_opus_always`).
For incremental content updates that do not warrant a full Voyage iteration (e.g., refreshing a single per-preset reference when Anthropic publishes new guidance), the docs-triple rule still applies: plugin `README.md` + plugin `CLAUDE.md` (this file) + root `README.md` updated in the same commit as the content change.
## Communication patterns
### Linking to local files
When pointing to local files in responses, always use markdown link syntax with a descriptive name:
- Use `[Human-friendly name](file:///absolute/path)` — never bare `file:///...` URLs or autolinks `<file://...>`.
- Always use absolute paths. Never `~/` or relative paths.
- For multiple files, render as a bullet list of named markdown links.
Why: bare `file://` URLs only render the first as clickable across multiple lines. Named markdown links make each entry independently clickable and look cleaner.
Example:
- [Brief](file:///Users/ktg/.../brief.html)
- [Research summary](file:///Users/ktg/.../research/summary.md)