Menü
Generate Vela slide deck JSON. Self-contained, speed-optimized.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Create presentation decks using the Vela engine. Compact DSL format — never verbose JSON. Also loads, extracts, and edits existing decks.
Run a full "implement + test + verify a batch of change requests to zero bugs" sprint in one session as a thin orchestrator that delegates implementation to sub-agents (routed by task difficulty, isolated in worktrees for parallel work) and gates completion on an independent BLIND validation by the best model. Use when handed a list of changes/issues (a PDF, ticket list, or spec) to implement, test, and prove working end-to-end — stop rule "a blind best-model hunt finds no bugs + a proof artifact (a Markdown sprint report by default; recorded demo optional)". Repo-agnostic; reads a root `.hyper-sprint/config.md` for repo facts; front-loads app/browser readiness so verification never stalls.
Offline in-container render harness for the FULL Vela app (no CDN) plus the committed `vela-drive.js` scripts — headless UI-test battery, scripted screenshot, recorded demo video, and an opt-in AI mode. Use for REPEATABLE, COMMITTED automation where the harness itself is the deliverable — running the UI battery in CI, recording a demo video, a scripted screenshot in a benchmark, or verifying real Vera/AI features against the local `claude` CLI via `vela-drive.js ai`. For AD-HOC / INTERACTIVE work — explore/test the app, poke a state, reproduce a bug, a one-off screenshot, verify a UX change, drive presenter/gallery — use the `playwright-cli-setup` skill instead (a persistent CLI browser driven step by step). This skill still documents the blocked-CDN offline render recipe that both skills share.
Verify Vela rendering/security behavior in a REAL browser (and against the REAL deck sanitizers) inside the remote-execution container. Use when you need to confirm whether a deck/SVG/CSS payload actually executes or fires a network request when rendered — e.g. exfil/XSS hunts, "does this beacon fire", confirming a sanitizer fix, or any claim that needs more than reading source. Also records how to launch the prebuilt Chromium here despite blocked CDNs.
THE DEFAULT tool for ad-hoc / interactive Vela browser work — explore or test the app, screenshot a state, reproduce a bug, poke a selector, drive presenter/gallery flows, verify a UX change, run bench/vela-interaction-bench.sh. Drives a live offline Vela render via Playwright CLI (@playwright/cli), a persistent warm browser you steer one command at a time (open, snapshot, click, press, eval), inspecting state + output between steps. Prefer this over the committed `vela-drive.js` scripts (skill: vela-live-render) — those are for repeatable, committed automation only (CI, benchmark, recorded demo), NOT one-off exploration. Also prefer over writing throwaway Playwright .js files. Covers container setup (blocked CDNs, file:// block, pinned Chromium) and per-agent session isolation for parallel browser tests.
Time-boxed adversarial bug-hunting of a LIVE app driven by MULTI-STEP PLAYWRIGHT BURSTS against a persistent warm browser — not one LLM turn per CLI step. The app is opened ONCE; the agent submits full scripts that run to completion unattended (one structured result per burst); reset to a known initial state between scenarios; inherit the implementer's driver verbs instead of re-predicting selectors. Generic / repo-agnostic: all app specifics come from the repo's own config. Use when hunting bugs in a browser-drivable app under a hard wall-clock budget.
| name | vela-slides |
| version | 3.1.1 |
| updated | "2026-03-21T00:00:00.000Z" |
| description | Generate Vela slide deck JSON. Self-contained, speed-optimized. |
Generate the deck JSON and write it to the requested file path in ONE tool call. Do NOT validate, do NOT read files, do NOT run CLI commands. Just write the JSON.
{"n":"Title","C":{palette},"T":{themes},"S":[slides]}
Palette C: "$A":"#hex" for colors used 2+. Use 2+ accents.
Themes T: "d":dark(b,c,a,p), "a":alt(different b), "l":light. p=CSS padding.
Slides S: t=theme, n=title, d=duration(int), B=blocks. Spacers: bare int.
Blocks: _=type, x=text, s=size, c=color, i=icon, b=bg, w=weight(int), ic=iconColor, ib=iconBg, I=items, g=gap(int), lb=label, v=variant, H=headers, R=rows
heading(x,s:xs-4xl,w,i) · text(x,s,c) · badge(x,c,b,i) · code(x,lb)
icon-row(I=[{icon,title,x,ic,ib}], distinct ic) · tag-group(I=[{x,c,i}],v) · bullets(I)
table(H,R,striped,headerBg,headerColor) · grid(cols,g,I=[{blocks,style}]) · metric(value,lb,s,c,i)
flow(I=[{i,lb,sublabel,gate}],arrowColor,direction,loop,loopLabel) · steps(I=[{title,x}],lineColor) · timeline(I=[{date,title,x}])
icon(name,s,c,b,circle) · callout(x,title,b,border,i) · quote(x,author) · progress(I=[{lb,value,c}]) · spacer(int) · divider
"d"/"a" themes. bgGradient on cover+CTA+section breaks. 1+ "l" slide in 10+ slide decks.ic per item.Write the complete deck JSON to the requested file in a SINGLE Write tool call. No validation, no CLI, no reads. One call, done.