wp-agent-toolkit-design-bridge
Skill1 starsChanged 33 days agoMITView on GitHub
Bridge Figma or screenshot design intent into WordPress repo conventions via WP Agent MCP. Use when the user asks to implement, build, or match a design in WordPress.
In this repository11 other files it gives its agents.
- .cursor/rules/00-project-overview.mdcCursor rule
- .cursor/rules/10-architecture-and-safety.mdcCursor rule
- .cursor/rules/20-indexing-and-audit-contracts.mdcCursor rule
- .cursor/rules/30-mcp-implementation-guidelines.mdcCursor rule
- .cursor/rules/40-wp-introspection-guidelines.mdcCursor rule
- wp-agent-toolkit-bootstrapSkill
- wp-agent-toolkit-cursor-pluginSkill
- wp-agent-toolkit-demoSkill
- wp-agent-toolkit-mcp-serverSkill
- wp-agent-toolkit-orchestratorSkill
- wp-agent-toolkit-wp-helper-pluginSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 3 are distinctive, and 11 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
11
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Call get_design_bridge_readiness (WP Agent MCP) first.
- Very specific: line 21
If readyForBridge: false, explain blockers[] and remediation before capture work.
- Very specific: line 26
Before Figma capture, verify Figma MCP via dynamic tool discovery (GetDynamicTools pattern figma).
- Distinctive: line 27
If missing and user gave a Figma URL: explain how to enable Figma MCP in Cursor Settings → MCP, then offer screenshot fallback (no Figma …
- Distinctive: line 32
Do not spawn parallel subagents for bridge steps in v1.
- Very specific: line 56
Do not ask the user for themeSlug, blogId, or other tool fields.
- Very specific: line 57
If the bridge returns requiresThemeSelection: true, ask the user once in natural language which theme to use (offer themeCandidates), then …
- Very specific: line 61
Call bridge_design_to_implementation with visualIntent (or figmaCapture) and componentHint from the user's request.
- Distinctive: line 63
Use the returned implementation spec:
- Very specific: line 72
Read cited files via read_project_file
- Very specific: line 73
Prefer reuse/extend per componentPlan
- Very specific: line 78
If Playwright MCP available: run verificationChecks
- Very specific: line 91
After one get_design_context call:
- Very specific: line 94
Add components[].label for each component/frame name (include block slugs such as tht/card-hero when visible).
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design Implementation Bridge
When to use
Route here when the user:
- Shares a Figma link or node and wants it implemented in WordPress
- Attaches a screenshot/mock and asks to match the project design system
- Says "implement this frame/section/hero" with design context
Users stay in natural language. Never require tool names in user prompts.
Prerequisites (transparent checks)
- Call
get_design_bridge_readiness(WP Agent MCP) first.- If
readyForBridge: false, explainblockers[]and remediation before capture work. - Surface
companionMcps.figma.setupHintwhen the user provided a Figma URL. - Surface
companionMcps.playwright.setupHintonly for post-implementation verification.
- If
- Figma MCP availability (agent-side only)
- Before Figma capture, verify Figma MCP via dynamic tool discovery (
GetDynamicToolspatternfigma). - If missing and user gave a Figma URL: explain how to enable Figma MCP in Cursor Settings → MCP, then offer screenshot fallback (no Figma MCP required).
- Before Figma capture, verify Figma MCP via dynamic tool discovery (
Workflow (linear, quota-efficient)
- Readiness → capture → one interpret pass → bridge → implement → verify
- Do not spawn parallel subagents for bridge steps in v1.
Capture
| Input | Action |
| Figma URL | One get_design_context call (load figma-design-to-code skill first) |
| Screenshot/image | Interpret image directly; skip Figma MCP |
Interpret (agent, one pass)
Convert capture into semantic visualIntent:
- Layout structure + region roles
- Color roles (
background,text,accent, …) — not raw hex as the primary signal - Typography roles (
heading,body, …) - Spacing rhythm (
tight/normal/loose,sectionPadding) - Component labels/kinds
Raw Figma values may appear under raw hints only. Never send raw-only payloads (bridge returns BRIDGE_INTENT_TOO_RAW).
Theme target
- Pass
componentHintwith a natural-language excerpt from the user's request (component description and optional theme mention, e.g. "card hero in our tht theme"). - Do not ask the user for
themeSlug,blogId, or other tool fields. - If the bridge returns
requiresThemeSelection: true, ask the user once in natural language which theme to use (offerthemeCandidates), then retry with the chosen theme reflected incomponentHint.
Bridge (single MCP call)
Call bridge_design_to_implementation with visualIntent (or figmaCapture) and componentHint from the user's request.
Use the returned implementation spec:
tokenReconciliation→ theme preset CSS varscomponentPlan.audit→ reuse / extend / createimplementationGuidance.avoidRawValues→ never paste Figma literals into theme filesverificationChecks→ Playwright or manual checklist
Implement
- Read cited files via
read_project_file - Prefer reuse/extend per
componentPlan - Apply changes via
apply_patchwhen appropriate
Verify
- If Playwright MCP available: run
verificationChecks - Otherwise: present manual checks from the spec
Anti-patterns
- Pasting Figma hex/spacing/font values directly into SCSS/PHP/theme.json
- Calling
get_theme_profile+audit_componentseparately when bridge can bundle reconciliation - Running
search_project_files, terminalgrep, orrgbefore the bridge when implementing from Figma/screenshot (bridge bundles audit + token reconciliation) - Multiple Figma MCP reads for the same frame
- Parallel Task subagents for token matching (bridge is deterministic in WP Agent)
Figma → visualIntent handoff
After one get_design_context call:
- Set
visualIntent.layout.structurefrom frame layout summary. - Add
components[].labelfor each component/frame name (include block slugs such astht/card-herowhen visible). - Map colors/typography/spacing to roles; keep literals under
*.rawonly. - Or pass the capture object as
figmaCaptureand let the bridge derive a first-pass intent.
Include known block slugs in components[].label — layout text alone often misses indexed block matches.
Example user prompts
Implement this hero section in our WordPress theme+ Figma link[screenshot] Match this layout using our design system for the tht themeTurn this Figma frame into a block pattern(ask for theme if missing)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

