Fix gaps #18-20: multi-gateway video skill, selector-first routing, self-review

- ai-video-gen skill: document fal.ai as primary gateway alongside HeyGen,
  add video_selector-first guidance
- animation.yaml: add selector-first rule in assets stage, mandatory
  post-render self-review in compose stage
- CinematicRenderer: add resolveAsset() for staticFile path resolution,
  fixing file:// URI errors in OffthreadVideo and Audio components

.agents/skills/ai-video-gen/SKILL.md

@@ -1,23 +1,33 @@
 ---
 name: ai-video-gen
 description: |
-  Generate AI videos from text prompts using the HeyGen API. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance), (5) Working with HeyGen's /v1/workflows/executions endpoint for video generation.
+  Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax). Supports two gateways: HeyGen API and fal.ai API.
 allowed-tools: mcp__heygen__*
 metadata:
   openclaw:
     requires:
-      env:
+      env_any:
         - HEYGEN_API_KEY
-    primaryEnv: HEYGEN_API_KEY
+        - FAL_KEY
+    primaryEnv: FAL_KEY
 ---
 
-# Video Generation (HeyGen API)
+# Video Generation (Multi-Gateway)
 
-Generate AI videos from text prompts. Supports multiple providers (VEO 3.1, Kling, Sora, Runway, Seedance), configurable aspect ratios, and optional reference images for image-to-video generation.
+Generate AI videos from text prompts. Supports multiple providers via two API gateways:
+
+| Gateway | Env Variable | Providers | Tool |
+|---------|-------------|-----------|------|
+| **fal.ai** | `FAL_KEY` | Kling v3/v2.1, MiniMax, VEO | `kling_video`, `minimax_video`, `veo_video` |
+| **HeyGen** | `HEYGEN_API_KEY` | VEO 3.1, Kling Pro, Sora v2, Runway Gen-4, Seedance | `heygen_video` |
+
+**IMPORTANT:** Always use `video_selector` instead of calling provider tools directly. The selector handles availability checks, cost comparison, and automatic fallback.
 
 ## Authentication
 
-All requests require the `X-Api-Key` header. Set the `HEYGEN_API_KEY` environment variable.
+**fal.ai (recommended primary):** Set `FAL_KEY` environment variable. Get a key at https://fal.ai/dashboard/keys
+
+**HeyGen (secondary):** Set `HEYGEN_API_KEY` environment variable.
 
 ```bash
 curl -X POST "https://api.heygen.com/v1/workflows/executions" \

.claude/skills/ai-video-gen/SKILL.md

@@ -1,23 +1,33 @@
 ---
 name: ai-video-gen
 description: |
-  Generate AI videos from text prompts using the HeyGen API. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance), (5) Working with HeyGen's /v1/workflows/executions endpoint for video generation.
+  Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3) Image-to-video generation with a reference image, (4) Choosing between video generation providers (VEO, Kling, Sora, Runway, Seedance, MiniMax). Supports two gateways: HeyGen API and fal.ai API.
 allowed-tools: mcp__heygen__*
 metadata:
   openclaw:
     requires:
-      env:
+      env_any:
         - HEYGEN_API_KEY
-    primaryEnv: HEYGEN_API_KEY
+        - FAL_KEY
+    primaryEnv: FAL_KEY
 ---
 
-# Video Generation (HeyGen API)
+# Video Generation (Multi-Gateway)
 
-Generate AI videos from text prompts. Supports multiple providers (VEO 3.1, Kling, Sora, Runway, Seedance), configurable aspect ratios, and optional reference images for image-to-video generation.
+Generate AI videos from text prompts. Supports multiple providers via two API gateways:
+
+| Gateway | Env Variable | Providers | Tool |
+|---------|-------------|-----------|------|
+| **fal.ai** | `FAL_KEY` | Kling v3/v2.1, MiniMax, VEO | `kling_video`, `minimax_video`, `veo_video` |
+| **HeyGen** | `HEYGEN_API_KEY` | VEO 3.1, Kling Pro, Sora v2, Runway Gen-4, Seedance | `heygen_video` |
+
+**IMPORTANT:** Always use `video_selector` instead of calling provider tools directly. The selector handles availability checks, cost comparison, and automatic fallback.
 
 ## Authentication
 
-All requests require the `X-Api-Key` header. Set the `HEYGEN_API_KEY` environment variable.
+**fal.ai (recommended primary):** Set `FAL_KEY` environment variable. Get a key at https://fal.ai/dashboard/keys
+
+**HeyGen (secondary):** Set `HEYGEN_API_KEY` environment variable.
 
 ```bash
 curl -X POST "https://api.heygen.com/v1/workflows/executions" \

pipeline_defs/animation.yaml

@@ -197,6 +197,7 @@ stages:
       - Total cost within approved budget from proposal_packet
       - "Layer 3 skills read for EVERY generation tool before writing prompts (check agent_skills field)"
       - "Clip duration maximized (prefer 10s over 5s) to reduce API calls and cost"
+      - "Use selector tools (video_selector, tts_selector, image_selector) — never call provider tools directly"
     success_criteria:
       - Schema-valid asset_manifest artifact
       - All referenced asset files exist on disk
@@ -249,9 +250,11 @@ stages:
       - Motion timing survives the final render
       - Audio sync matches the animatic intent
       - Duration within +/-5% of target
+      - "Post-render self-review MANDATORY: extract keyframes, visually inspect each scene, flag weak frames before presenting to user"
     success_criteria:
       - Schema-valid render_report artifact
       - Output file exists and passes ffprobe validation
+      - self_review_completed is true with per-scene quality notes
 
   - name: publish
     skill: pipelines/animation/publish-director

remotion-composer/src/CinematicRenderer.tsx

@@ -8,9 +8,21 @@ import {
   Sequence,
   interpolate,
   spring,
+  staticFile,
   useCurrentFrame,
   useVideoConfig,
 } from "remotion";
+
+function resolveAsset(src: string): string {
+  if (src.startsWith("http://") || src.startsWith("https://") || src.startsWith("data:")) {
+    return src;
+  }
+  const clean = src.replace(/^file:\/\/\/?/, "");
+  if (clean.startsWith("/") || /^[A-Za-z]:[/\\]/.test(clean)) {
+    return `file:///${clean.replace(/\\/g, "/")}`;
+  }
+  return staticFile(clean);
+}
 import { CinematicRendererProps, CinematicTone, CinematicVideoScene } from "./cinematic/types";
 
 const FPS = 30;
@@ -74,7 +86,7 @@ const SceneVideo: React.FC<{ scene: CinematicVideoScene }> = ({ scene }) => {
     <AbsoluteFill style={{ backgroundColor: "#020407", opacity }}>
       <OffthreadVideo
         muted
-        src={scene.src}
+        src={resolveAsset(scene.src)}
         trimBefore={trimBefore}
         trimAfter={trimAfter}
         style={{
@@ -296,7 +308,7 @@ const Soundtrack: React.FC<{
 
   return (
     <Audio
-      src={src}
+      src={resolveAsset(src)}
       trimBefore={trimBefore}
       trimAfter={trimAfter}
       volume={() => Math.min(fadeIn, fadeOut)}