mirror of
https://github.com/nexu-io/open-design.git
synced 2026-06-01 03:14:35 +07:00
b5eb8c1647
* feat: general-purpose skills with @-mention composition and user import
Lift skills from "one mode-bound skill per project" to a generic capability
the user can compose per turn:
- Daemon: scan multiple skill roots (user-skills under runtime data, then
the bundled `skills/`); user-imported skills can shadow built-ins by id.
- New `POST /api/skills/import` and `DELETE /api/skills/:id` endpoints,
with CONFLICT/BAD_REQUEST/NOT_FOUND error codes and built-in delete
protection.
- ChatRequest gains `skillIds: string[]`; the chat run concatenates each
picked skill's body (and merges craftRequires) into the system prompt
for that turn only — the project's persistent `skillId` is untouched.
- Web composer: `@` popover now lists skills alongside project files;
picks render as removable chips above the textarea and ride along with
the request as `skillIds`.
- Settings → Library: import form (name/description/triggers/body),
per-card delete for user skills, "user" origin badge.
* chore(web): drop welcome pet teaser + add ds→prompt-template mapping util
- SettingsDialog: remove the inline pet adoption teaser from the welcome
panel so the first-run modal stays focused on configuration.
- New `inferPromptTemplateCategoriesForDs(ds)` helper that maps a design
system's authored metadata to prompt-template gallery categories.
Imported by the design-system gallery wiring on a sibling branch; no
callers in this branch yet.
* feat: split skills/design-templates and add finalize-design API
Phase 0 of the skills/design-templates refactor (specs/current/
skills-and-design-templates.md):
- Move ~104 rendering catalogue entries from skills/ to design-templates/
and keep skills/ for the small set of functional skills that *do work*
on user input (utilities, briefs, packagers).
- Add design-templates/AGENTS.md and skills/AGENTS.md describing the
contract, and a brand-agnostic craft/ surface for opt-in craft rules.
- Daemon: add DESIGN_TEMPLATES_DIR / USER_DESIGN_TEMPLATES_DIR roots and
an /api/design-templates surface mirroring /api/skills. Asset/example
routes still span both registries so existing srcdoc URLs keep
resolving across the rename.
- Web: split LibrarySection into SkillsSection + DesignSystemsSection,
rename the EntryView "Examples" tab to "Templates", and update locales
+ the New-project picker accordingly.
Adds the finalize-design endpoint:
- New apps/daemon/src/finalize-design.ts and packages/contracts/src/api/
finalize.ts — one-shot synthesis of a project's transcript + active
design system + current artifact into <projectDir>/DESIGN.md via the
Anthropic Messages API. Per-project .finalize.lock mirrors the
transcript-export hygiene from PR #493; provider credentials are not
persisted by the daemon.
Other supporting changes:
- README + AGENTS.md updates to document the new directory split and
craft/ surface, plus i18n strings across 13 locales.
- Test refactors and new coverage (finalize-design, runs, sidecar
server, plus refreshed daemon integration tests).
- .gitignore: scope the *.exe ignore to /OpenDesign.exe so legitimate
vendor binaries are no longer hidden.
* fix(merge): move clinical-case-report to design-templates/
Origin/main added the clinical-case-report skill under skills/ before
the skills/design-templates split landed. Its od.mode is prototype, so
per specs/current/skills-and-design-templates.md it is a design template
and belongs alongside the other rendering catalogue entries — not under
the slimmed-down functional skills/ root. Moving it keeps the EntryView
Templates tab consistent with origin/main's intent.
* feat(skills): curated design/creative catalogue + collapsible Settings rows
Seed ~100 curated design/creative skill stubs under skills/ sourced from
awesome-claude-skills (ComposioHQ) and awesome-agent-skills (VoltAgent).
Each stub carries an od.category tag so the new filter pill row in
Settings -> Skills can group them. The seed script
(scripts/seed-curated-design-skills.ts, pnpm seed:curated-design-skills)
is idempotent: it only creates folders that don't already exist, so
hand-edited stubs are never overwritten.
- Daemon: parse and surface od.category on SkillInfo with a strict slug
normaliser; mirror the field on SkillSummary in @open-design/contracts.
Category is purely a UI hint — system-prompt composition is unchanged.
- Web: rewrite SkillsSection from a left-list / right-detail grid into a
vertical stack of collapsible rows mirroring the External MCP panel
(header always visible with name + mode/source/category pills + per-row
enable toggle; SKILL.md preview, file tree and inline edit form expand
on demand). Add a Category filter row above the list. Reorder Settings
nav so Skills + External MCP sit above the Composio/MCP cluster. Update
composer placeholder/hint across 17 locales to advertise '@ files or
skills · / for commands'.
- Docs: extend skills/AGENTS.md with the curated catalogue rules
(idempotency, category vocabulary, no upstream vendoring).
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(skills): teach localized-content + system-prompt tests about the skills/design-templates split
mrcfps blocking review on PR #955: the skills/design-templates split
(b5993385) moved ~110 SKILL.md entries out of `skills/` and into
`design-templates/`, but two repo-level tests still hard-coded the
single-root layout, so CI gates went red on the merged branch:
- `e2e/tests/localized-content.test.ts` only scanned `<repo>/skills`
while the locale `skillCopy` map keeps id-keyed entries spanning
both roots (ExamplesTab/Templates uses one lookup regardless of
origin). Teach the helper to read both `skills/` and
`design-templates/`, deduplicating ids so the union matches the
localized claim.
- `apps/daemon/tests/prompts/system.test.ts` read
`skills/live-artifact/SKILL.md`, which now lives under
`design-templates/live-artifact/`. Update the absolute path so
composeSystemPrompt's coverage of the live-artifact preamble is
exercised again.
Also enroll the curated design/creative catalogue (PR #955, ~91
stubs sourced from awesome-claude-skills / awesome-agent-skills) in
the DE / FR / RU `_SKILL_IDS_WITH_EN_FALLBACK` lists. The stubs are
English-only by design (frontmatter advertises an upstream URL); the
fallback list is exactly the place to acknowledge "we know this id
exists, English copy is fine here" so the localized-content coverage
gate passes without forcing a translation task per locale.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(skills): always quote frontmatter name so importUserSkill round-trips numeric / boolean ids
mrcfps PR #955 review: `buildSkillMarkdown` emitted `name:
${escapeYamlString(name)}` without quotes, so YAML coerced names
like `123`, `true`, `false`, or `null` into non-string scalars on
re-parse. listSkills() then read `data.name` as a number/boolean
and the import flow's follow-up `findSkillById(skills, result.id)`
missed it, falling into `/api/skills/import`'s "imported skill
could not be re-read" 500 path for those ids.
Switch the emitter to a quoted scalar (`name: "..."`) — the
double-escape already in `escapeYamlString` makes the quoted form
safe — and add a round-trip test covering `123`, `true`, `false`,
`null`, and `0` to lock in the contract.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(web): drop staged-skill chips when the matching @<id> token leaves the draft
mrcfps PR #955 review: `submit()` always forwarded every id in
`stagedSkills`, but that state was only mutated on picker click and
chip removal. Hand-deleting an `@<id>` token from the textarea left
the chip staged, so the request still carried `skillIds: [<id>]` and
the daemon composed a skill the prompt no longer referenced.
Sync the chips with the draft inside `handleChange()` by pruning
`stagedSkills` whenever the new value no longer contains the
`@<id>` token (using the same whitespace boundary as
`removeStagedSkill`'s strip regex). Comment explains why this
prune does not run for `staged` file attachments — users frequently
add files via the upload button without leaving an `@<path>` token,
so a symmetric prune there would erase legitimate uploads.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(daemon): stage @-composed skills' side files alongside the active skill
codex PR #955 review: composing a per-turn `@`-picked skill into the
system prompt appended its body (with the `withSkillRootPreamble`
guidance pointing at relative paths under `<cwd>/.od-skills/<folder>/`)
but never staged the actual folder. `startChatRun` only copied
`activeSkillDir`, so when the project's primary skill was different
(or absent) the composed skill's references/, examples/, and scripts/
files lived only at their absolute repo path — agents that honour
the cwd-relative form (or that don't get `--add-dir`, e.g. Codex with
allowlisted gpt-image projects) couldn't reach them.
Thread the composed skills' dirs out of `composeDaemonSystemPrompt`
as `extraSkillDirs` and stage each one through the same
`stageActiveSkill` API used for the primary skill. Dedupe by folder
basename so a project whose primary skill is also `@`-composed isn't
copied twice. Each preamble already advertises its own folder, so the
prompt and the staged tree stay aligned without further changes.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(web): respect the Library disable toggle in the project @-mention picker
codex PR #955 review: only `EntryView` received `enabledSkills`
(filtered against `config.disabledSkills`); active projects still
got `skills={skills}` raw, so a skill the user disabled in Settings
kept appearing in the project's `@`-mention popover and could ride
along to the daemon via `skillIds`. That broke the Library toggle
for any project opened on the post-split branch.
Compute a functional-skills-only enabled subset
(`enabledFunctionalSkills`) and pass it into `<ProjectView>` instead.
Templates stay separate — design-templates are filtered through their
own `enabledDesignTemplates` memo for the Templates gallery — so
ProjectView's chat composer still only sees skills, never templates,
matching the pre-split prop surface.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(e2e): mock /api/design-templates for example-use-prompt flow
The Templates tab in EntryView fetches from /api/design-templates after
the skills/design-templates split (specs/current/skills-and-design-templates.md).
The example-use-prompt Playwright scenario only mocked /api/skills, so the
gallery card never appeared and the test timed out waiting on
example-card-warm-utility-example. Serve the same fixture summary on both
endpoints so the templates gallery renders the card the test clicks.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(tools-pack): create design-templates fixture for resources test
The packaging resources copy now bundles the new design-templates tree
alongside skills (see resources.ts BUNDLED_RESOURCE_TREES). The
copyBundledResourceTrees fixture only created skills, design-systems,
craft, etc., so the recursive copy crashed with ENOENT on
design-templates before it could check the prompt-templates assertion.
Add the missing fixture directory so the test exercises the same set
of resource trees the packaged build does.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(skills): clone built-in side files into the shadow on first edit
mrcfps PR #955 review: editing a built-in skill wrote a USER_SKILLS_DIR
shadow folder that contained only a new SKILL.md. The next listSkills()
pass surfaced the shadow as the active dir, but every side-file resolver
(/api/skills/:id/files, /example, /assets/*, the system-prompt preamble,
and the per-turn cwd staging) reads through skill.dir. With nothing but
SKILL.md in the shadow, the bundled assets/, references/, scripts/, and
examples/ disappeared the moment the user hit save — a built-in like
last30days or live-artifact would break immediately after edit instead
of just having its body overridden.
Teach updateUserSkill() to take a `sourceDir` and clone every entry
except SKILL.md / dotfiles into the shadow on the very first edit. The
shadow stays self-contained, so all the resolvers keep working without
fallback bookkeeping. Subsequent edits detect the existing shadow and
skip the clone, so user tweaks under the side tree survive a re-save.
Wire `sourceDir: skill.dir` from server.ts's PUT /api/skills/:id handler
and add two regression tests:
- 'clones built-in side files into the shadow on the first edit' walks
the file tree after save and asserts assets/template.html, references/
notes.md, and scripts/helper.sh all round-trip from the built-in.
- 'preserves user-edited side files on subsequent edits' edits the
staged assets/template.html, re-saves, and confirms the user content
is still there.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(e2e): rename home tab from Examples to Templates
The Examples tab was renamed to Templates in EntryView (b5993385's
skills/design-templates split — entry.tabExamples became entry.tabTemplates
and the tab value moved from 'examples' to 'templates'), but
entry-chrome-flows still asserted the old label and testId. Update both.
* fix(skills+web): preserve template body in API mode and dir-based skill delete
Two follow-ups from PR #955 review:
1. ProjectView only received `enabledFunctionalSkills`, but
`composedSystemPrompt()` still resolved `project.skillId` through that
prop and `fetchSkill()`. Projects created from the new
`/api/design-templates` surface keep a template id in `project.skillId`,
so opening one in API mode dropped the template body from the system
prompt and the upstream request ran without the project's primary
template instructions. Now ProjectView takes a separate
`designTemplates` prop (the unfiltered template list, so a
later-disabled template still loads for projects already created from
it) and `composedSystemPrompt()` plus the metadata / `isDeck` lookups
fall back to that list, with `fetchDesignTemplate()` as the body-fetch
fallback to `fetchSkill()`. The chat composer's `@`-picker keeps
receiving only the enabled functional skills.
2. `DELETE /api/skills/:id` used `deleteUserSkill(USER_SKILLS_DIR, skill.id)`
which re-slugified the frontmatter id and removed
`<userSkillsDir>/<slug>/`. That matched the import shape but missed the
install shape — `installFromTarget` writes the folder at
`sanitizeRepoName(url)` (GitHub) or `path.basename(realpath)` (local
symlink), neither of which is guaranteed to equal the slugified
frontmatter `name`. A duplicate `app.delete('/api/skills/:id', ...)`
handler at the install routes never fired because Express resolved the
earlier registration first, leaving the install/uninstall path without
working teardown. The handler now removes `skill.dir` (the absolute
path listSkills already discovered) under a USER_SKILLS_DIR safety
check, using `lstat` + `unlinkSync` so symlinked local installs unlink
cleanly without recursing into the user's source tree. The dead
duplicate handler is removed; `deleteUserSkill` is dropped from the
server.ts import set (still exported and unit-tested in skills.ts).
Regression coverage in `apps/daemon/tests/skills-delete-route.test.ts`
pins both shapes plus the symlink-preserves-source case.
* test(daemon): point hyperframes system-prompt test at design-templates
The merge with main brought in a hyperframes system-prompt test that
reads `skills/hyperframes/SKILL.md`, but this branch's split moved
`hyperframes` into `design-templates/` (same migration as `live-artifact`
already handled above in this file). CI was failing with ENOENT on the
old path.
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
12 KiB
12 KiB
| name | description | triggers | od | |||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| replit-deck | Single-file horizontal-swipe HTML deck in the style of Replit Slides's landing-page template gallery. Eight distinct themes (helix, holm, vance, bevel, world-dark, world-mint, atlas, bluehouse) — each a complete visual system (palette + type + accent) captured from replit.com/slides. Pick one theme, do not mix. For pitch decks, board reports, brand memos, campaign reveals — when the user explicitly wants "Replit Slides style". |
|
|
Replit Deck Skill
Produce a single-file horizontal-swipe HTML deck in one of eight Replit-Slides themes. Every theme is a complete visual system — do not mix tokens across themes.
Resource map
replit-deck/
├── SKILL.md ← you're reading this
├── assets/
│ └── template.html ← seed: 8 themes via [data-theme=*], proven iframe-nav script (READ FIRST)
├── references/
│ ├── themes.md ← 8 themes: when-to-pick / do / don't / primary layouts
│ ├── layouts.md ← 10 paste-ready slide layouts, cross-theme
│ ├── components.md ← shared primitives (eyebrow, kpi-row, image-grid, meta-bar)
│ └── checklist.md ← P0/P1/P2 self-review + theme lock-in gate
└── examples/ ← four reference decks across the most contrasting themes
├── example-helix.html (SaaS board update · light minimal)
├── example-holm.html (legal fintech memo · cream editorial serif)
├── example-atlas.html (quarterly history chapter · black + vermilion)
└── example-bluehouse.html (real estate ROI · navy + gradient cards)
Workflow
Step 0 — Pre-flight (mandatory reads)
- Read
assets/template.htmlend-to-end. The[data-theme]blocks carry the tokens; the<script>at the bottom solves five iframe nav bugs — do not rewrite it. - Read
references/themes.md→ pick one theme that matches the user's brief. If the user already picked a theme viaod.inputs.theme, use that. - Read
references/layouts.md→ you'll copy<section>blocks from here. - Read
references/checklist.md→ P0 must pass before emit.
Step 1 — Commit to one theme
Write out loud (in the TodoWrite or plan section) which theme and why. Once picked, every slide uses that theme's tokens only. No swapping mid-deck. The <body data-theme="helix"> attribute is the single source of truth.
| Theme | Pick when |
|---|---|
helix |
SaaS board update, product metrics, neutral modern |
holm |
Legal memo, investor pre-read, serious / institutional |
vance |
Art portfolio, design catalog, photographer / sculptor |
bevel |
Fashion campaign, lookbook, Y2K / editorial attitude |
world-dark |
Policy report, finance analysis, premium dark |
world-mint |
Lighter companion of world-dark — ESG, wellness finance, sustainability |
atlas |
Long-form narrative, chapter deck, museum / archive aesthetic |
bluehouse |
Consumer product, real estate, lifestyle, colorful cards |
Step 2 — Plan slide rhythm before writing HTML
Default 6 slides. Write the rhythm BEFORE any HTML, for example (helix, 6 slides):
01 cover hero + title + subtitle
02 kpi-row-6 6 metrics with ▲/▼ deltas
03 split-insight left stat + right paragraph
04 chapter-plate section divider
05 three-up three parallel columns
06 closing one bold number or CTA
Show this to the user. Redirecting at this stage is cheap.
Step 3 — Copy seed, bind theme
- Copy
assets/template.htmlto project root asindex.html. - Set
<body data-theme="<chosen>">. - Replace
<title>. - Delete the placeholder slides in the body (the seed ships with 3 demo slides). Keep the chrome (counter / progress / hint).
Step 4 — Paste layouts, fill real copy
For each planned slide, copy the matching <section> from references/layouts.md. Replace every [REPLACE] with specific copy — never leave placeholders, never use lorem. If a slide feels empty, pick a different layout.
Tag each slide with data-screen-label="01 Cover", "02 Metrics", etc., in presentation order.
Step 5 — Self-check
Run references/checklist.md silently before emit: the P0 theme-lock gate plus the five-dimension 1–5 critique (Philosophy / Hierarchy / Execution / Specificity / Restraint). Any dimension ≤ 3 → re-do before emit.
The P0 theme-lock grep is non-negotiable:
grep -E 'data-theme|style="--' index.html | head
If any style="--accent:..." or theme override appears on individual slides, revert. One theme per deck.
Step 6 — Emit artifact
<artifact identifier="deck-<slug>" type="text/html" title="<Deck title>">
<!doctype html>
<html>...</html>
</artifact>
One sentence before the artifact. Stop after </artifact>.
Hard rules
- One theme per deck.
data-themeset on<body>— never override per-slide. - Numbers are real or absent. No invented metrics. Use
—or a grey block as an honest placeholder. - Display face follows theme. helix/world-dark/world-mint/bluehouse use the sans Display; holm/vance/atlas use the serif Display; bevel uses the Y2K display. Do not swap. (Authoritative source: the
--font-displaytoken of each theme inassets/template.html— if this list ever disagrees with the template, the template wins.) - Accent appears 1–2× per slide max. Never a gradient-spam.
- Never rewrite the nav script. Five iframe bugs it solves are not obvious.
- Keep it one HTML file. Inline all CSS. No external fonts — the system stack in each theme is deliberate.
data-screen-labelon every slide.- No Replit logo / brand lockup. These are template styles, not a Replit-brand deck.
When to pick replit-deck vs. peer skills
| Skill | Pick when |
|---|---|
simple-deck |
Plain, single-theme deck bound to the project's DESIGN.md tokens. When the deck should match the host brand, not assert its own. (designSystemRequired: true.) |
magazine-web-ppt |
Editorial "magazine × e-ink" aesthetic (WebGL fluid background, serif titles, chapter plates). When the brief asks for a keynote / launch / sharing-style deck and calls out Monocle / WIRED / Kinfolk / Domus. |
replit-deck |
The brief explicitly asks for Replit-Slides gallery aesthetic, or needs one of the 8 token-frozen visual identities (SaaS board, editorial memo, gallery catalog, Y2K campaign, policy report, museum chapter, consumer cards). No dependency on DESIGN.md. |
If the user just says "make me a deck" without further guidance, default to simple-deck — it respects their design system. Pick replit-deck only when the brief is explicit about the aesthetic or names a theme.
Scope & provenance
- Eight themes = the full replit.com/slides landing-page gallery at the time of snapshot. Not a curated subset — every theme card currently published on replit.com/slides is represented here (helix, holm, vance, bevel, world-dark, world-mint, atlas, bluehouse). If Replit ships a ninth template, it is not automatically reflected in this skill.
- Snapshot date: 2026-04-29. All hex values were sampled from the actual replit.com/slides PNGs on that date with ImageMagick — no guessed colors, no memory substitutions. See
references/themes.md→ Contributing a new theme for the exact sampling procedure. - Maintenance: one-time snapshot, not tracked. Replit Slides is a live product and may drift. This skill does not auto-sync. If you notice Replit has updated colors or added a theme and want it reflected here, open an issue on
nexu-io/open-designtitledreplit-deck: re-sync to replit.com/slides (YYYY-MM-DD)and attach the updated screenshots. There is no designated owner monitoring the upstream. - No Replit branding. These are gallery-style templates, not a Replit-brand deck. The checklist (P0) forbids inserting a Replit logo or wordmark.
Browser / runtime support
- Target: modern evergreen desktop browsers (Chrome 110+ / Safari 16+ / Firefox 115+) and modern mobile Safari / Chrome.
- Features used: CSS scroll-snap (horizontal),
color-mix(), CSS custom properties,text-wrap: balance. All ≥ 93% Baseline. - Not supported: IE 11, Safari < 15, any browser without
color-mix()(would need a fallback--accent-softif you want to support older Safari; out of scope for this skill). - Mobile: horizontal scroll-snap works on iOS Safari 16+ and Android Chrome. Keyboard nav is desktop-only by design.
- Nav script behavior: reused verbatim from
skills/simple-deck— survives iframe embedding (the daemon preview surface), dual listener races, focus loss, and position persistence across reloads. Do not rewrite it.
Verification
The skill auto-registers with the daemon on filesystem scan (no manual wiring). Confirmed against a running daemon on localhost:7456 after adding this skill:
$ curl -s localhost:7456/api/skills \
| node -e "const d=JSON.parse(require('fs').readFileSync(0,'utf-8')); \
console.log(JSON.stringify(d.skills.find(s=>s.id==='replit-deck'), null, 2));"
{
"id": "replit-deck",
"name": "replit-deck",
"description": "Single-file horizontal-swipe HTML deck in the style of Replit Slides's\nlanding-page template gallery. Eight distinct themes …",
"triggers": [
"replit deck",
"replit slides",
"replit 风格 ppt",
"replit style deck",
"helix deck",
"holm memo",
"atlas chapter",
"bluehouse",
"bevel campaign"
],
"mode": "deck",
"platform": null,
"scenario": "product",
"previewType": "html",
"designSystemRequired": false,
"defaultFor": [],
"upstream": null,
"featured": null,
"fidelity": null,
"speakerNotes": null,
"animations": null,
"examplePrompt": "Single-file horizontal-swipe HTML deck in the style of Replit Slides's landing-page template gallery.",
"hasBody": true
}
All four example decks (examples/example-{helix,holm,atlas,bluehouse}.html) open directly in a browser. Keyboard nav (← / → / Space / Home / End) and horizontal scroll-snap work in Chrome 129 and Safari 18.