egregore-labs/egregore / skills/preview-design
preview-design
VerifiedRender a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for `/preview-design`, "preview the design convention", "render this with the new design", or Design Convention round-1 testing.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.7 KB |
| render.shexecutable | script | 2.2 KB |
| samples/document.md | markdown | 2.5 KB |
| samples/handoff.json | config | 3.8 KB |
samples/handoff.json
View on GitHub{
"@context": "https://egregore.xyz/spec/handoff/v1",
"id": "https://egregore.xyz/view/_/sample-design-convention-r1",
"version": "1.0",
"kind": "handoff",
"topic": "Design Convention — Round 1 handoff sample",
"claim": "Running this renders the MERIDIAN handoff surface with every section populated, so you can judge the real design on real structure.",
"ask": "Check the handoff surface: do the deep links resolve, does the briefing read cleanly, and do the decision cards + repo-state table hold up in light and dark?",
"created_at": "2026-06-25T09:00:00Z",
"author": { "display": "Egregore sample", "handle": "egregore" },
"audience": {
"addressed_to": [{ "display": "Reviewer", "handle": "reviewer" }],
"visible_to": "public",
"extendable_by": "anyone"
},
"repo_state": [
{
"repo": "egregore",
"branch": "dev/example/design-convention",
"pr_number": 123,
"base": "develop",
"ahead": 6,
"uncommitted": false
}
],
"body": {
"prose": "## Briefing\n\nThis is a **sample handoff** rendered through the branch's MERIDIAN code. It exists to put the handoff surface under load: prose with `inline code`, a [link](https://example.com/design-convention), a list, and a copyable block.\n\nThe handoff surface is the agent-to-agent + human bridge. The things that must work:\n\n- the **deep links** (open in Claude Code / Claude / ChatGPT)\n- the **decision cards** and **repo-state table**\n- the whole thing reading as the *same family* as the document and platform surfaces\n\n```\nRun this Egregore: design-convention\nSurface: handoff\n```\n",
"sidecar": {
"current_state": "MERIDIAN is wired into the document, handoff, and platform render paths on this branch. The emissary renderer is server-side and not yet design-system-wired — that's the #1 Round-2 task.",
"decisions": [
{
"decision": "Emissary is harness-only for Round 1",
"rationale": "Its renderer (api/main.py) builds inline HTML server-side and isn't wired to the design-system.",
"implications": "Wiring the emissary renderer to MERIDIAN is the #1 Round-2 task."
},
{
"decision": "Preview through the branch-local CLI, never npx",
"rationale": "npx egregore-artifacts pulls the published npm 0.10.2 — the old design.",
"implications": "Testers run skills/preview-design/render.sh, which calls the local cli.js."
}
],
"open_threads": [
"Wire the emissary renderer to the design-system",
"Decide the npm publish cadence for egregore-artifacts once the convention lands"
],
"next_steps": [
"Render each surface with skills/preview-design/render.sh",
"Run the Socratic feedback protocol",
"Aggregate the folder into a prioritized Round-2 backlog"
],
"entry_points": [
{ "kind": "code", "label": "Open in Claude Code", "target": "https://claude.ai/code" },
{ "kind": "chat", "label": "Open in Claude", "target": "https://claude.ai/new" },
{ "kind": "chat", "label": "Open in ChatGPT", "target": "https://chatgpt.com" }
]
}
},
"references": [
{
"type": "url",
"kind": "harness",
"label": "Design Convention harness (all four surfaces)",
"target": "https://example.com/design-convention",
"snippet": "The 4-surface review harness — emissary, document, handoff, platform."
},
{
"type": "file",
"kind": "guide",
"label": "Round-1 feedback protocol",
"target": "memory/feedback/design-convention-r1/GUIDE.md"
}
],
"receiver_instructions": "Review the handoff surface design. Report whether the deep links and any copy payload work, and whether the cards and repo-state table hold up in dark mode."
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |