PMDevSolutions/Aurelius / .claude/skills/build-from-canva
build-from-canva
Verified/build-from-canva — Autonomous Canva-to-Working-App Pipeline
You are the master orchestrator for converting a Canva design into a fully working, tested React application. You receive a Canva URL and guide the entire process through 12 phases, using specialized skills and agents.
Key enforcement rules:
- TDD is mandatory — Phase 3 (TDD) MUST complete before Phase 4 (Build). No exceptions.
- Visual QA uses pixel diff — Phase 5 uses
scripts/visual-diff.jsfor programmatic comparison, not manual eyeballing. - E2E tests are generated — Phase 6 generates and runs Playwright E2E tests appropriate to the app type.
- App-type aware — Chrome extensions, PWAs, and web apps each get tailored test strategies.
- Token inference requires confirmation — Phase 2 extracts tokens via AI vision and MUST get user confirmation before locking.
Input
The user provides: $ARGUMENTS (a Canva design URL)
Parse the Canva URL to extract:
designIdfrom the URL path (e.g.,https://www.canva.com/design/DAGxyz.../...→DAGxyz...)
Configuration
Load .claude/pipeline.config.json at the start. This provides:
- Visual diff thresholds and iteration limits
- TDD enforcement settings
- E2E strategy per app type
- Quality gate thresholds
- Lighthouse score minimums
- Canva-specific settings (export format, scale, inference confidence threshold)
Progress Tracking
Track the run in .claude/plans/pipeline-state.json, in the shape /build-from-figma defines (.claude/skills/build-from-figma/SKILL.md → Progress Tracking), with "pipeline": "canva" and the Canva URL as source. Rewrite it at every phase boundary and after each component and page result; the SessionStart hook reads it to report where an interrupted run stopped.
Phases: 0 token-sync, 1 intake (canva-intake), 2 token-inference (canva-token-inference, needs user confirmation), 3 tdd-scaffold, 4 component-build, 4.5 storybook, 5 visual-diff (against the Canva exports), 5.5 dark-mode, 6 e2e-tests, 7 cross-browser, 8 quality-gate, 8.5 responsive, 9 report.
Phase 0: Token Drift Check (Conditional)
Identical to /build-from-figma. Only runs when tokenSync.autoCheck is true AND a lockfile exists.
./scripts/sync-tokens.sh --json
Phase 1: Intake
Invoke the canva-intake skill.
Input: The Canva URL from $ARGUMENTS
Output: .claude/plans/build-spec.json with "source": "canva"
This phase:
- Exports design screenshots via Canva AI Connector MCP
- Analyzes screenshots with Claude vision for structure, components, text
- Scans the local project for framework, existing components, UI libraries
- Asks the user 3-5 targeted questions (scope, component confirmation, reuse, business logic, integration)
- Writes the build spec
Resume check: If .claude/plans/build-spec.json already exists with "source": "canva", ask the user if they want to reuse it or regenerate.
Phase 2: Token Inference
Invoke the canva-token-inference skill.
Input: build-spec.json with screenshot paths
Output: src/styles/design-tokens.lock.json, tailwind.config.ts, src/styles/tokens.css
This phase:
- Analyzes Canva screenshots with Claude vision to extract colors, typography, spacing, effects
- Assigns confidence scores (high/medium/low) to each token
- Presents tokens to user for confirmation — this is MANDATORY, do not skip
- After user confirms/corrects, writes the lockfile
- Generates Tailwind config and CSS custom properties from lockfile
- Validates completeness
Resume check: If src/styles/design-tokens.lock.json already exists with "source": "canva", ask the user if they want to reuse it or re-infer.
Phase 3: TDD Scaffold
Invoke the tdd-from-figma skill. (This skill reads build-spec.json and works identically regardless of source.)
Input: build-spec.json + design-tokens.lock.json
Output: src/components/**/*.test.tsx files
Identical to /build-from-figma Phase 3.
Phases 4-9: Component Lanes, then Parallel Phases
After Phase 3 confirms RED, resolve the renderer manifest (node scripts/renderer-registry.js resolve <renderer> --json) and run Phases 4-9 exactly as /build-from-figma describes (.claude/skills/build-from-figma/SKILL.md → Phases 4-9): the component-lanes workflow for Phases 4-5 when the Workflow tool is available, then parallel-orchestration for Phases 4.5-9. The Canva differences:
- Workflow args:
"source": "canva", andconverteriscanva-react-converterfor React renderers (manifest.converterotherwise). The pagereferencesare the Canva exports from Phase 1 in.claude/visual-qa/screenshots/canva/, so nothing is captured in the prepare step except the test checksums and the dev server. - parallel-orchestration context: pipeline source
"canva", reference screenshots.claude/visual-qa/screenshots/canva/.
Without the Workflow tool, invoke parallel-orchestration with all of ["component-build", "storybook", "visual-diff", "dark-mode", "e2e-tests", "cross-browser", "quality-gate", "responsive", "report"] (minus manifest.phases.exclude). If orchestration.enabled is false, run the phases sequentially as documented below.
Phase 4: Component Build (Renderer-Driven)
Read renderer from build-spec.json, resolve its manifest, and dispatch the converter it names:
node scripts/renderer-registry.js resolve <renderer> --json
Converter selection:
- If
manifest.language === "react", prefer the source-appropriate React converter. For the Canva pipeline that iscanva-react-converter(it builds React components from Canva screenshots). The shipped React manifests (nextjs, vite) setconverterto the genericfigma-react-converter; for the Canva source, usecanva-react-converterinstead. - Otherwise dispatch
manifest.converterdirectly (e.g.react-native-converterfor expo, and the futurevue-converter/svelte-converter).
The component extension, directory, page-routing convention, and test command come from manifest.component and manifest.commands.test.
Input: build-spec.json, resolved renderer manifest, lockfile, existing test files, Canva screenshots
Output: Component and page files for the renderer's framework (React: src/components/**/*.tsx)
This phase:
- Reads build-spec.json — verifies
sourceis"canva"and readsrenderer - Resolves the manifest and dispatches the converter (see selection rule above)
- References lockfile for all token values (no approximating)
- Uses Canva screenshots for layout/structure decisions
- Generates components (at
manifest.component.dirwithmanifest.component.ext) that satisfy the test files from Phase 3 - Runs
manifest.commands.testafter each component batch to confirm GREEN
Critical rule: If tests fail, fix the component — never modify the test files.
Phase 4.5: Storybook Generation (Non-Blocking)
Identical to /build-from-figma Phase 4.5.
./scripts/generate-stories.sh
Phase 5: Visual Verification (Automated Pixel Diff)
Same process as /build-from-figma Phase 5, but reference screenshots come from Canva exports instead of Figma MCP.
Reference screenshots: Already exported during Phase 1, stored in .claude/visual-qa/screenshots/canva/
For each page:
1. Start: pnpm dev (background) — skip if appType is chrome-extension
2. Wait for server ready
3. Reference screenshots already exist from Phase 1 (canva exports)
→ Stored in .claude/visual-qa/screenshots/canva/
4. FOR iteration IN 1..maxVisualIterations:
a. Chrome DevTools MCP: navigate → resize → take_screenshot
→ Save to .claude/visual-qa/screenshots/chromium/
b. Run pixel diff:
→ node scripts/visual-diff.js --batch \
.claude/visual-qa/screenshots/chromium \
.claude/visual-qa/screenshots/canva \
--output-dir .claude/visual-qa/diffs --json
c. Parse JSON results:
→ IF all mismatchPct <= threshold: PASS → break
→ IF any FAIL and iteration < max:
- Read diff images + region analysis
- Fix component code targeting specific regions
- Run: pnpm vitest run (ensure tests still pass)
- Continue to next iteration
5. Stop dev server
Phases 5.5 through 9
Identical to /build-from-figma. All shared phases work the same regardless of design source:
- Phase 5.5: Dark Mode verification (
check-dark-mode.sh) - Phase 6: E2E test generation (
e2e-test-generatorskill) - Phase 7: Cross-browser screenshots (Firefox, WebKit)
- Phase 8: Quality gate (coverage, types, build, tokens, Lighthouse)
- Phase 8.5: Responsive screenshots (
check-responsive.sh) - Phase 9: Build report (
.claude/visual-qa/build-report.md)
The build report should note Source: Canva and include the token inference confidence summary.
Error Recovery
Retry Protocol
For transient failures (rate limits, timeouts, MCP disconnects), apply exponential backoff from pipeline.config.json > canva.retry:
FOR attempt IN 1..maxAttempts:
TRY operation
ON SUCCESS: continue pipeline
ON FAILURE:
IF error type IN retryableErrors:
delay = min(initialDelayMs * backoffMultiplier^(attempt-1), maxDelayMs)
WAIT delay
LOG: "Retry {attempt}/{maxAttempts} after {delay}ms — {error type}"
CONTINUE
ELSE:
FALL THROUGH to manual recovery below
AFTER maxAttempts exhausted:
LOG: "All {maxAttempts} retries failed for {operation}"
FALL THROUGH to manual recovery
Canva MCP Failures
- Rate limited: Automatic retry with exponential backoff (see protocol above). If all retries fail, pause 60 seconds and retry once more. If still failing, ask user to wait and retry later.
- MCP connection lost: Retry connection 3 times. If it fails, ask user to restart Canva AI Connector and re-run the current phase.
- Export timeout: Retry with backoff. On persistent failure, reduce export scale to 1x and retry. If still failing, ask user to manually export.
Content Failures
- Export fails: Ask user to manually export design pages as PNG from Canva and provide file paths.
- Token inference low confidence: Present all tokens with detailed confidence breakdown. Offer to accept user-provided brand guidelines as override.
- Complex nested groups fail to parse: Flatten aggressively (see canva-react-converter § 3a), log skipped layers, continue.
Environment Failures
- Dev server won't start: Check for port conflicts, missing dependencies. Run
pnpm installif needed. - Tests won't pass after 3 attempts: Mark component as needing manual intervention, continue with remaining.
- Build fails: Check TypeScript errors first, then dependency issues. Report blockers.
- Session interrupted: On resume, read
.claude/plans/pipeline-state.json. Skip completed phases whose artifacts still exist and resume from the first incomplete one.
Completion
When all phases complete, present:
- The build report summary
- Count of pages/components built and verified
- Token inference accuracy (how many tokens were confirmed vs corrected)
- Any items needing manual review
- Next steps (e.g., "run
pnpm devto see the app")
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 192k | Updated | Claude CodeCodex | Verified | Install |