cli-jaw 0.1.0

package/skills_ref/fal-image-edit/SKILL.md

@@ -0,0 +1,249 @@
+---
+name: fal-image-edit
+description: Edit images using AI on fal.ai. Style transfer, object removal, background changes, and more. Use when the user requests "Edit image", "Remove object", "Change background", "Apply style", or similar image editing tasks.
+metadata:
+  author: fal-ai
+  version: "1.0.0"
+---
+
+# fal.ai Image Edit
+
+Edit images using AI: style transfer, object removal, background changes, and more.
+
+## How It Works
+
+1. User provides image URL and editing instructions
+2. Script selects appropriate model
+3. Sends request to fal.ai API
+4. Returns edited image URL
+
+## Recommended Models
+
+| Model | Best For |
+|-------|----------|
+| `fal-ai/nano-banana-pro` | **Best overall** - T2I and editing |
+| `fal-ai/flux-kontext` | Background change, context-aware editing |
+| `fal-ai/flux/dev/image-to-image` | Style transfer |
+| `fal-ai/bria/fibo-edit` | Object removal |
+| `fal-ai/flux/dev/inpainting` | Masked inpainting |
+
+## Supported Operations
+
+| Operation | Model | Description |
+|-----------|-------|-------------|
+| General Edit | `fal-ai/nano-banana-pro` | Best quality edits |
+| Style Transfer | `fal-ai/flux/dev/image-to-image` | Apply style to image |
+| Object Removal | `fal-ai/bria/fibo-edit` | Remove objects from image |
+| Background Change | `fal-ai/flux-kontext` | Change/replace background |
+| Inpainting | `fal-ai/flux/dev/inpainting` | Fill in masked areas |
+
+## Usage
+
+```bash
+bash /mnt/skills/user/fal-image-edit/scripts/edit-image.sh [options]
+```
+
+**Arguments:**
+- `--image-url` - URL of image to edit (required)
+- `--prompt` - Description of desired edit (required)
+- `--operation` - Edit operation: `style`, `remove`, `background`, `inpaint` (default: `style`)
+- `--mask-url` - URL of mask image (required for inpainting/removal)
+- `--strength` - Edit strength 0.0-1.0 (default: 0.75)
+
+**Examples:**
+
+```bash
+# Style transfer
+bash /mnt/skills/user/fal-image-edit/scripts/edit-image.sh \
+  --image-url "https://example.com/photo.jpg" \
+  --prompt "Convert to anime style" \
+  --operation style
+
+# Remove object
+bash /mnt/skills/user/fal-image-edit/scripts/edit-image.sh \
+  --image-url "https://example.com/photo.jpg" \
+  --prompt "Remove the person on the left" \
+  --operation remove
+
+# Change background
+bash /mnt/skills/user/fal-image-edit/scripts/edit-image.sh \
+  --image-url "https://example.com/portrait.jpg" \
+  --prompt "Place in a tropical beach setting" \
+  --operation background
+
+# Inpainting with mask
+bash /mnt/skills/user/fal-image-edit/scripts/edit-image.sh \
+  --image-url "https://example.com/photo.jpg" \
+  --mask-url "https://example.com/mask.png" \
+  --prompt "Fill with flowers" \
+  --operation inpaint
+```
+
+## MCP Tool Alternative
+
+### General Edit (Recommended)
+```javascript
+mcp__fal-ai__generate({
+  modelId: "fal-ai/nano-banana-pro",
+  input: {
+    image_url: "https://example.com/photo.jpg",
+    prompt: "Make the sky more dramatic with sunset colors"
+  }
+})
+```
+
+### Style Transfer
+```javascript
+mcp__fal-ai__generate({
+  modelId: "fal-ai/flux/dev/image-to-image",
+  input: {
+    image_url: "https://example.com/photo.jpg",
+    prompt: "Convert to anime style",
+    strength: 0.75
+  }
+})
+```
+
+### Object Removal
+```javascript
+mcp__fal-ai__generate({
+  modelId: "bria/fibo-edit",
+  input: {
+    image_url: "https://example.com/photo.jpg",
+    prompt: "Remove the person on the left"
+  }
+})
+```
+
+### Background Change (Kontext)
+```javascript
+mcp__fal-ai__generate({
+  modelId: "fal-ai/flux-kontext",
+  input: {
+    image_url: "https://example.com/portrait.jpg",
+    prompt: "Place the subject in a tropical beach setting"
+  }
+})
+```
+
+### Inpainting
+```javascript
+mcp__fal-ai__generate({
+  modelId: "fal-ai/flux/dev/inpainting",
+  input: {
+    image_url: "https://example.com/photo.jpg",
+    mask_url: "https://example.com/mask.png",
+    prompt: "Fill with flowers"
+  }
+})
+```
+
+## Output
+
+```
+Editing image...
+Model: fal-ai/flux/dev/image-to-image
+Operation: style transfer
+
+Edit complete!
+
+Image URL: https://v3.fal.media/files/abc123/edited.png
+Dimensions: 1024x1024
+```
+
+JSON output:
+```json
+{
+  "images": [
+    {
+      "url": "https://v3.fal.media/files/abc123/edited.png",
+      "width": 1024,
+      "height": 1024
+    }
+  ]
+}
+```
+
+## Present Results to User
+
+```
+Here's your edited image:
+
+![Edited Image](https://v3.fal.media/files/...)
+
+• 1024×1024 | Operation: Style Transfer
+```
+
+## Model Selection Guide
+
+### General Editing (Recommended)
+**Nano Banana Pro** (`fal-ai/nano-banana-pro`)
+- **Best overall** for image editing and T2I
+- High quality, versatile
+- Good for most editing tasks
+
+### Style Transfer
+**FLUX Image-to-Image** (`fal-ai/flux/dev/image-to-image`)
+- Best for: Artistic style changes
+- Strength: 0.3-0.5 for subtle, 0.7-0.9 for dramatic
+
+### Object Removal
+**Bria Fibo Edit** (`fal-ai/bria/fibo-edit`)
+- Best for: Removing objects, people, text
+- Works without masks (AI detects objects from prompt)
+
+### Background Change
+**FLUX Kontext** (`fal-ai/flux-kontext`)
+- Best for: Placing subjects in new environments
+- Preserves subject identity well
+
+### Inpainting
+**FLUX Inpainting** (`fal-ai/flux/dev/inpainting`)
+- Best for: Precise edits with mask control
+- Requires binary mask (white = edit area)
+
+## Mask Tips
+
+For inpainting and some removal tasks:
+- White pixels = areas to edit
+- Black pixels = areas to preserve
+- Use PNG format with transparency or solid colors
+- Feathered edges create smoother transitions
+
+## Troubleshooting
+
+### Edit Too Subtle
+```
+The edit is barely visible.
+
+Increase the strength parameter:
+--strength 0.85
+```
+
+### Edit Too Dramatic
+```
+The edit changed too much of the image.
+
+Decrease the strength parameter:
+--strength 0.3
+```
+
+### Object Not Removed
+```
+The object wasn't fully removed.
+
+Tips:
+1. Be more specific in the prompt
+2. Try using an explicit mask
+3. Use the inpainting model for precise control
+```
+
+### Background Artifacts
+```
+The new background has artifacts around the subject.
+
+Tips:
+1. Use a cleaner source image
+2. Try FLUX Kontext which handles edges better
+3. Adjust the strength for smoother blending
+```

package/skills_ref/fal-image-edit/scripts/edit-image.sh

@@ -0,0 +1,199 @@
+#!/bin/bash
+
+# fal.ai Image Edit Script
+# Usage: ./edit-image.sh --image-url URL --prompt "..." [--operation OP] [--mask-url URL] [--strength N]
+# Returns: JSON with edited image URL
+
+set -e
+
+FAL_API_ENDPOINT="https://fal.run"
+
+# Default values
+IMAGE_URL=""
+PROMPT=""
+OPERATION="style"
+MASK_URL=""
+STRENGTH=0.75
+
+# Check for --add-fal-key first
+for arg in "$@"; do
+    if [ "$arg" = "--add-fal-key" ]; then
+        shift
+        KEY_VALUE=""
+        if [[ -n "$1" && ! "$1" =~ ^-- ]]; then
+            KEY_VALUE="$1"
+        fi
+        if [ -z "$KEY_VALUE" ]; then
+            echo "Enter your fal.ai API key:" >&2
+            read -r KEY_VALUE
+        fi
+        if [ -n "$KEY_VALUE" ]; then
+            grep -v "^FAL_KEY=" .env > .env.tmp 2>/dev/null || true
+            mv .env.tmp .env 2>/dev/null || true
+            echo "FAL_KEY=$KEY_VALUE" >> .env
+            echo "FAL_KEY saved to .env" >&2
+        fi
+        exit 0
+    fi
+done
+
+# Load .env if exists
+if [ -f ".env" ]; then
+    source .env 2>/dev/null || true
+fi
+
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --image-url)
+            IMAGE_URL="$2"
+            shift 2
+            ;;
+        --prompt)
+            PROMPT="$2"
+            shift 2
+            ;;
+        --operation)
+            OPERATION="$2"
+            shift 2
+            ;;
+        --mask-url)
+            MASK_URL="$2"
+            shift 2
+            ;;
+        --strength)
+            STRENGTH="$2"
+            shift 2
+            ;;
+        --help|-h)
+            echo "fal.ai Image Edit Script" >&2
+            echo "" >&2
+            echo "Usage:" >&2
+            echo "  ./edit-image.sh --image-url URL --prompt \"...\" [options]" >&2
+            echo "" >&2
+            echo "Options:" >&2
+            echo "  --image-url     Image URL to edit (required)" >&2
+            echo "  --prompt        Edit description (required)" >&2
+            echo "  --operation     Operation: style, remove, background, inpaint" >&2
+            echo "  --mask-url      Mask URL (required for inpaint)" >&2
+            echo "  --strength      Edit strength 0-1 (default: 0.75)" >&2
+            echo "  --add-fal-key   Setup FAL_KEY in .env" >&2
+            exit 0
+            ;;
+        *)
+            shift
+            ;;
+    esac
+done
+
+# Validate required inputs
+if [ -z "$FAL_KEY" ]; then
+    echo "Error: FAL_KEY not set" >&2
+    echo "" >&2
+    echo "Run: ./edit-image.sh --add-fal-key" >&2
+    echo "Or:  export FAL_KEY=your_key_here" >&2
+    exit 1
+fi
+
+if [ -z "$IMAGE_URL" ]; then
+    echo "Error: --image-url is required" >&2
+    exit 1
+fi
+
+if [ -z "$PROMPT" ]; then
+    echo "Error: --prompt is required" >&2
+    exit 1
+fi
+
+# Select model based on operation
+case $OPERATION in
+    style)
+        MODEL="fal-ai/flux/dev/image-to-image"
+        ;;
+    remove)
+        MODEL="bria/fibo-edit"
+        ;;
+    background)
+        MODEL="fal-ai/flux-kontext"
+        ;;
+    inpaint)
+        MODEL="fal-ai/flux/dev/inpainting"
+        if [ -z "$MASK_URL" ]; then
+            echo "Error: --mask-url is required for inpainting" >&2
+            exit 1
+        fi
+        ;;
+    *)
+        echo "Unknown operation: $OPERATION" >&2
+        echo "Supported: style, remove, background, inpaint" >&2
+        exit 1
+        ;;
+esac
+
+# Create temp directory
+TEMP_DIR=$(mktemp -d)
+trap 'rm -rf "$TEMP_DIR"' EXIT
+
+echo "Editing image..." >&2
+echo "Model: $MODEL" >&2
+echo "Operation: $OPERATION" >&2
+echo "" >&2
+
+# Build payload based on operation
+case $OPERATION in
+    style)
+        PAYLOAD=$(cat <<EOF
+{
+  "image_url": "$IMAGE_URL",
+  "prompt": "$PROMPT",
+  "strength": $STRENGTH
+}
+EOF
+)
+        ;;
+    remove|background)
+        PAYLOAD=$(cat <<EOF
+{
+  "image_url": "$IMAGE_URL",
+  "prompt": "$PROMPT"
+}
+EOF
+)
+        ;;
+    inpaint)
+        PAYLOAD=$(cat <<EOF
+{
+  "image_url": "$IMAGE_URL",
+  "mask_url": "$MASK_URL",
+  "prompt": "$PROMPT"
+}
+EOF
+)
+        ;;
+esac
+
+# Make API request
+RESPONSE=$(curl -s -X POST "$FAL_API_ENDPOINT/$MODEL" \
+    -H "Authorization: Key $FAL_KEY" \
+    -H "Content-Type: application/json" \
+    -d "$PAYLOAD")
+
+# Check for errors
+if echo "$RESPONSE" | grep -q '"error"'; then
+    ERROR_MSG=$(echo "$RESPONSE" | grep -o '"message":"[^"]*"' | head -1 | cut -d'"' -f4)
+    if [ -z "$ERROR_MSG" ]; then
+        ERROR_MSG=$(echo "$RESPONSE" | grep -o '"error":"[^"]*"' | cut -d'"' -f4)
+    fi
+    echo "Error: $ERROR_MSG" >&2
+    exit 1
+fi
+
+echo "Edit complete!" >&2
+echo "" >&2
+
+# Extract image URL
+OUTPUT_URL=$(echo "$RESPONSE" | grep -o '"url":"[^"]*"' | head -1 | cut -d'"' -f4)
+echo "Image URL: $OUTPUT_URL" >&2
+
+# Output JSON for programmatic use
+echo "$RESPONSE"

package/skills_ref/figma-implement-design/SKILL.md

@@ -0,0 +1,264 @@
+---
+name: "figma-implement-design"
+description: "Translate Figma nodes into production-ready code with 1:1 visual fidelity using the Figma MCP workflow (design context, screenshots, assets, and project-convention translation). Trigger when the user provides Figma URLs or node IDs, or asks to implement designs or components that must match Figma specs. Requires a working Figma MCP server connection."
+---
+
+
+# Implement Design
+
+## Overview
+
+This skill provides a structured workflow for translating Figma designs into production-ready code with pixel-perfect accuracy. It ensures consistent integration with the Figma MCP server, proper use of design tokens, and 1:1 visual parity with designs.
+
+## Prerequisites
+
+- Figma MCP server must be connected and accessible
+- User must provide a Figma URL in the format: `https://figma.com/design/:fileKey/:fileName?node-id=1-2`
+  - `:fileKey` is the file key
+  - `1-2` is the node ID (the specific component or frame to implement)
+- **OR** when using `figma-desktop` MCP: User can select a node directly in the Figma desktop app (no URL required)
+- Project should have an established design system or component library (preferred)
+
+## Required Workflow
+
+**Follow these steps in order. Do not skip steps.**
+
+### Step 0: Set up Figma MCP (if not already configured)
+
+If any MCP call fails because Figma MCP is not connected, pause and set it up:
+
+1. Add the Figma MCP:
+   - `codex mcp add figma --url https://mcp.figma.com/mcp`
+2. Enable remote MCP client:
+   - Set `[features].rmcp_client = true` in `config.toml` **or** run `codex --enable rmcp_client`
+3. Log in with OAuth:
+   - `codex mcp login figma`
+
+After successful login, the user will have to restart codex. You should finish your answer and tell them so when they try again they can continue with Step 1.
+
+### Step 1: Get Node ID
+
+#### Option A: Parse from Figma URL
+
+When the user provides a Figma URL, extract the file key and node ID to pass as arguments to MCP tools.
+
+**URL format:** `https://figma.com/design/:fileKey/:fileName?node-id=1-2`
+
+**Extract:**
+
+- **File key:** `:fileKey` (the segment after `/design/`)
+- **Node ID:** `1-2` (the value of the `node-id` query parameter)
+
+**Note:** When using the local desktop MCP (`figma-desktop`), `fileKey` is not passed as a parameter to tool calls. The server automatically uses the currently open file, so only `nodeId` is needed.
+
+**Example:**
+
+- URL: `https://figma.com/design/kL9xQn2VwM8pYrTb4ZcHjF/DesignSystem?node-id=42-15`
+- File key: `kL9xQn2VwM8pYrTb4ZcHjF`
+- Node ID: `42-15`
+
+#### Option B: Use Current Selection from Figma Desktop App (figma-desktop MCP only)
+
+When using the `figma-desktop` MCP and the user has NOT provided a URL, the tools automatically use the currently selected node from the open Figma file in the desktop app.
+
+**Note:** Selection-based prompting only works with the `figma-desktop` MCP server. The remote server requires a link to a frame or layer to extract context. The user must have the Figma desktop app open with a node selected.
+
+### Step 2: Fetch Design Context
+
+Run `get_design_context` with the extracted file key and node ID.
+
+```
+get_design_context(fileKey=":fileKey", nodeId="1-2")
+```
+
+This provides the structured data including:
+
+- Layout properties (Auto Layout, constraints, sizing)
+- Typography specifications
+- Color values and design tokens
+- Component structure and variants
+- Spacing and padding values
+
+**If the response is too large or truncated:**
+
+1. Run `get_metadata(fileKey=":fileKey", nodeId="1-2")` to get the high-level node map
+2. Identify the specific child nodes needed from the metadata
+3. Fetch individual child nodes with `get_design_context(fileKey=":fileKey", nodeId=":childNodeId")`
+
+### Step 3: Capture Visual Reference
+
+Run `get_screenshot` with the same file key and node ID for a visual reference.
+
+```
+get_screenshot(fileKey=":fileKey", nodeId="1-2")
+```
+
+This screenshot serves as the source of truth for visual validation. Keep it accessible throughout implementation.
+
+### Step 4: Download Required Assets
+
+Download any assets (images, icons, SVGs) returned by the Figma MCP server.
+
+**IMPORTANT:** Follow these asset rules:
+
+- If the Figma MCP server returns a `localhost` source for an image or SVG, use that source directly
+- DO NOT import or add new icon packages - all assets should come from the Figma payload
+- DO NOT use or create placeholders if a `localhost` source is provided
+- Assets are served through the Figma MCP server's built-in assets endpoint
+
+### Step 5: Translate to Project Conventions
+
+Translate the Figma output into this project's framework, styles, and conventions.
+
+**Key principles:**
+
+- Treat the Figma MCP output (typically React + Tailwind) as a representation of design and behavior, not as final code style
+- Replace Tailwind utility classes with the project's preferred utilities or design system tokens
+- Reuse existing components (buttons, inputs, typography, icon wrappers) instead of duplicating functionality
+- Use the project's color system, typography scale, and spacing tokens consistently
+- Respect existing routing, state management, and data-fetch patterns
+
+### Step 6: Achieve 1:1 Visual Parity
+
+Strive for pixel-perfect visual parity with the Figma design.
+
+**Guidelines:**
+
+- Prioritize Figma fidelity to match designs exactly
+- Avoid hardcoded values - use design tokens from Figma where available
+- When conflicts arise between design system tokens and Figma specs, prefer design system tokens but adjust spacing or sizes minimally to match visuals
+- Follow WCAG requirements for accessibility
+- Add component documentation as needed
+
+### Step 7: Validate Against Figma
+
+Before marking complete, validate the final UI against the Figma screenshot.
+
+**Validation checklist:**
+
+- [ ] Layout matches (spacing, alignment, sizing)
+- [ ] Typography matches (font, size, weight, line height)
+- [ ] Colors match exactly
+- [ ] Interactive states work as designed (hover, active, disabled)
+- [ ] Responsive behavior follows Figma constraints
+- [ ] Assets render correctly
+- [ ] Accessibility standards met
+
+## Implementation Rules
+
+### Component Organization
+
+- Place UI components in the project's designated design system directory
+- Follow the project's component naming conventions
+- Avoid inline styles unless truly necessary for dynamic values
+
+### Design System Integration
+
+- ALWAYS use components from the project's design system when possible
+- Map Figma design tokens to project design tokens
+- When a matching component exists, extend it rather than creating a new one
+- Document any new components added to the design system
+
+### Code Quality
+
+- Avoid hardcoded values - extract to constants or design tokens
+- Keep components composable and reusable
+- Add TypeScript types for component props
+- Include JSDoc comments for exported components
+
+## Examples
+
+### Example 1: Implementing a Button Component
+
+User says: "Implement this Figma button component: https://figma.com/design/kL9xQn2VwM8pYrTb4ZcHjF/DesignSystem?node-id=42-15"
+
+**Actions:**
+
+1. Parse URL to extract fileKey=`kL9xQn2VwM8pYrTb4ZcHjF` and nodeId=`42-15`
+2. Run `get_design_context(fileKey="kL9xQn2VwM8pYrTb4ZcHjF", nodeId="42-15")`
+3. Run `get_screenshot(fileKey="kL9xQn2VwM8pYrTb4ZcHjF", nodeId="42-15")` for visual reference
+4. Download any button icons from the assets endpoint
+5. Check if project has existing button component
+6. If yes, extend it with new variant; if no, create new component using project conventions
+7. Map Figma colors to project design tokens (e.g., `primary-500`, `primary-hover`)
+8. Validate against screenshot for padding, border radius, typography
+
+**Result:** Button component matching Figma design, integrated with project design system.
+
+### Example 2: Building a Dashboard Layout
+
+User says: "Build this dashboard: https://figma.com/design/pR8mNv5KqXzGwY2JtCfL4D/Dashboard?node-id=10-5"
+
+**Actions:**
+
+1. Parse URL to extract fileKey=`pR8mNv5KqXzGwY2JtCfL4D` and nodeId=`10-5`
+2. Run `get_metadata(fileKey="pR8mNv5KqXzGwY2JtCfL4D", nodeId="10-5")` to understand the page structure
+3. Identify main sections from metadata (header, sidebar, content area, cards) and their child node IDs
+4. Run `get_design_context(fileKey="pR8mNv5KqXzGwY2JtCfL4D", nodeId=":childNodeId")` for each major section
+5. Run `get_screenshot(fileKey="pR8mNv5KqXzGwY2JtCfL4D", nodeId="10-5")` for the full page
+6. Download all assets (logos, icons, charts)
+7. Build layout using project's layout primitives
+8. Implement each section using existing components where possible
+9. Validate responsive behavior against Figma constraints
+
+**Result:** Complete dashboard matching Figma design with responsive layout.
+
+## Best Practices
+
+### Always Start with Context
+
+Never implement based on assumptions. Always fetch `get_design_context` and `get_screenshot` first.
+
+### Incremental Validation
+
+Validate frequently during implementation, not just at the end. This catches issues early.
+
+### Document Deviations
+
+If you must deviate from the Figma design (e.g., for accessibility or technical constraints), document why in code comments.
+
+### Reuse Over Recreation
+
+Always check for existing components before creating new ones. Consistency across the codebase is more important than exact Figma replication.
+
+### Design System First
+
+When in doubt, prefer the project's design system patterns over literal Figma translation.
+
+## Common Issues and Solutions
+
+### Issue: Figma output is truncated
+
+**Cause:** The design is too complex or has too many nested layers to return in a single response.
+**Solution:** Use `get_metadata` to get the node structure, then fetch specific nodes individually with `get_design_context`.
+
+### Issue: Design doesn't match after implementation
+
+**Cause:** Visual discrepancies between the implemented code and the original Figma design.
+**Solution:** Compare side-by-side with the screenshot from Step 3. Check spacing, colors, and typography values in the design context data.
+
+### Issue: Assets not loading
+
+**Cause:** The Figma MCP server's assets endpoint is not accessible or the URLs are being modified.
+**Solution:** Verify the Figma MCP server's assets endpoint is accessible. The server serves assets at `localhost` URLs. Use these directly without modification.
+
+### Issue: Design token values differ from Figma
+
+**Cause:** The project's design system tokens have different values than those specified in the Figma design.
+**Solution:** When project tokens differ from Figma values, prefer project tokens for consistency but adjust spacing/sizing to maintain visual fidelity.
+
+## Understanding Design Implementation
+
+The Figma implementation workflow establishes a reliable process for translating designs to code:
+
+**For designers:** Confidence that implementations will match their designs with pixel-perfect accuracy.
+**For developers:** A structured approach that eliminates guesswork and reduces back-and-forth revisions.
+**For teams:** Consistent, high-quality implementations that maintain design system integrity.
+
+By following this workflow, you ensure that every Figma design is implemented with the same level of care and attention to detail.
+
+## Additional Resources
+
+- [Figma MCP Server Documentation](https://developers.figma.com/docs/figma-mcp-server/)
+- [Figma MCP Server Tools and Prompts](https://developers.figma.com/docs/figma-mcp-server/tools-and-prompts/)
+- [Figma Variables and Design Tokens](https://help.figma.com/hc/en-us/articles/15339657135383-Guide-to-variables-in-Figma)