makaron-cli 0.13.6 → 0.13.8

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.13.6",
+  "version": "0.13.8",
   "description": "Give Claude Code a creative agent. Pass complete creative requests and source media to Makaron Chat.",
   "author": {
     "name": "Versa AI",

package/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.13.6",
+  "version": "0.13.8",
   "description": "Give Codex a creative agent. Pass complete creative requests and source media to Makaron Chat.",
   "author": {
     "name": "Versa AI",

package/README.md

@@ -98,7 +98,12 @@ npx makaron-cli chat --project auto --image photo.jpg --json -b "make it cinemat
 npx makaron-cli chat --project auto --image img1.jpg --image img2.jpg --json -b "combine these"
 ```
 
-`chat` always routes agent, image, and video models automatically. Never pass `--agent-model`, `--image-model`, `--video-model`, or the legacy `--model` flag to `chat`; the CLI rejects them before starting a run. Model flags remain available only on explicit low-level commands such as `edit` and `video create`.
+`chat` routes image and video models automatically, but you may select the Agent LLM with `--agent-model`. Accepted values are exactly `auto`, `gpt-5.6-terra`, `gpt-5.6-sol`, `gpt-5.6-luna`, `grok-4.5`, and `deepseek-v4-pro`; `auto` currently resolves to `gpt-5.6-terra`. This flag changes only the reasoning/tool-calling Agent LLM. The CLI still rejects `--image-model`, `--video-model`, and the legacy `--model` flag before starting a chat run, so image/video model names cannot be mistaken for Agent models.
+
+```bash
+# Explicit lower-cost Agent LLM for a controlled comparison
+npx makaron-cli chat --project auto --agent-model deepseek-v4-pro --json -b "make a 20s badminton video"
+```
 
 Returns immediately:
 ```json
@@ -135,6 +140,20 @@ npx makaron-cli chat --project auto --image selfie.jpg --skill <marketplace-id-o
 
 `--skill` accepts an installed skill name, a marketplace UUID, or a unique marketplace label. If a marketplace skill is matched, the CLI installs or reuses it and sends `[Active skill: <installed-skill-name>]` to Makaron Agent. Ordinary users do not need admin commands, and the CLI intentionally does not expose skill deletion.
 
+### Built-in production skills
+
+Discover the available production workflows before choosing `--skill`:
+
+```bash
+npx makaron-cli skills list --built-in
+npx makaron-cli skills search "talking head captions" --built-in
+npx makaron-cli skills show talking-head --built-in
+npx makaron-cli chat --project auto --video talk.mp4 --skill talking-head -b "make a tight captioned edit"
+```
+
+The default list shows callable/discoverable skills with their purpose and input
+requirements. Add `--all` to include internal adapters and helper skills.
+
 ### With additional images (existing project)
 
 ```bash
@@ -241,7 +260,7 @@ npx makaron-cli chat --project <id> --video party.mp4 --image kid.jpg -b "make t
 npx makaron-cli chat --project <id> --video clip1.mp4 --video clip2.mp4 -b "splice these into one seamless video"
 ```
 
-Video files are uploaded via signed URL. CLI local video uploads support `.mp4`, `.mov`, or `.webm`, max 50MB, max 120s with 1s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode larger videos before upload; the CLI uploads directly to Storage and rejects videos above those limits.
+Video files are uploaded via signed URL. CLI local video uploads support `.mp4`, `.mov`, or `.webm`, max 50MB, max 900s (15 minutes) with 1s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode larger videos before upload; the CLI uploads directly to Storage and rejects videos above those limits.
 The agent understands video content natively — it can analyze scenes, edit, extend, and compose videos. Seedance video-reference editing is still limited to ~15s provider references, so longer uploaded videos should be split/prepared by the agent before model submission; Kling remains the base/direct edit path.
 Use `chat --project <id|auto> --video ...` for any project/timeline video work. Direct `video create` is standalone and does not write timeline entries.
 
@@ -342,7 +361,7 @@ npx makaron-cli video create --script "Shot 1 (15s): <<<image_1>>> and <<<image_
 
 # 3b. Native SeeDance or MiniMax H3 text-to-video (no image required)
 npx makaron-cli video create --script "Shot 1 (5s): A neon one-person studio wakes at dawn" --duration 5 --video-model seedance-fast --aspect 16:9
-npx makaron-cli video create --script "Shot 1 (15s): A premium creative editor comes alive" --duration 15 --video-model minimax-h3 --video-resolution 2k --aspect 16:9
+npx makaron-cli video create --script "Shot 1 (15s): A premium creative editor comes alive" --duration 15 --video-model minimax-h3 --aspect 16:9
 
 # 3c. Edit a video from a local file or public URL
 npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --video-model seedance-fast
@@ -358,7 +377,7 @@ For project/timeline video editing, use:
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to the selected model limit), `--video <file|url>` and `--audio <file|url>` (repeatable where supported), `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--video-model seedance-fast|seedance-mini|seedance|seedance-2.5|kling|grok|google-omni|minimax-h3`, `--video-resolution auto|480p|720p|768p|1080p|2k|4k`. Default model is `seedance-fast`. SeeDance accepts native text-to-video with no image and integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; MiniMax H3 accepts native text-to-video, 4-15s output, and up to 9 image, up to 3 video, and up to 3 audio references through Makaron Agent/chat. H3 defaults to public 2k output; 768p requires provider preview access plus `MINIMAX_H3_ENABLE_768P=true` on the Makaron server. Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio, including up to 6 image references when no video reference is provided. For `--video-model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to the selected model limit), `--video <file|url>` and `--audio <file|url>` (repeatable where supported), `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--video-model seedance-fast|seedance-mini|seedance|seedance-2.5|kling|grok|google-omni|minimax-h3`, `--video-resolution auto|480p|720p|768p|1080p|2k|4k`. Default model is `seedance-fast`. SeeDance accepts native text-to-video with no image and integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; MiniMax H3 accepts native text-to-video, 4-15s output, public 768p/2k resolution, and up to 9 image, up to 3 video, and up to 3 audio references through Makaron Agent/chat. H3 defaults to 768p; request 2k explicitly for maximum/final quality. Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio, including up to 6 image references when no video reference is provided. For `--video-model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
 
 Seedance 2.5: use `--video-model seedance-2.5` for 4-30 second output at 480p/720p. `--image` accepts local files or URLs (up to 30), while repeatable `--video` and `--audio` accept up to 10 each. Use `--video-operation generate|edit|extend`, `--extend-direction forward|backward`, `--output-format mp4|mov`, `--web-search`, `--generated-audio` / `--no-generated-audio`, and `--relaxed-content-filter`. Edit/extend require a video reference. The Evolink route does not currently expose 4K output.
 

package/bin/makaron.mjs

@@ -28,6 +28,14 @@ const NPM_PACKAGE_NAME = 'makaron-cli';
 const UPDATE_CHECK_INTERVAL_MS = 24 * 60 * 60 * 1000;
 const UPDATE_CHECK_TIMEOUT_MS = 400;
 const AGENT_WAIT_TIMEOUT_SECONDS = Math.max(900, Number(process.env.MAKARON_AGENT_WAIT_TIMEOUT_SECONDS || 10_800));
+const CHAT_AGENT_MODELS = [
+  'auto',
+  'gpt-5.6-terra',
+  'gpt-5.6-sol',
+  'gpt-5.6-luna',
+  'grok-4.5',
+  'deepseek-v4-pro',
+];
 
 // Public anon key (safe to embed — only enables auth, not data access)
 const SUPABASE_URL = 'https://sdyrtztrjgmmpnirswxt.supabase.co';
@@ -35,7 +43,7 @@ const SUPABASE_ANON_KEY = 'sb_publishable_FJFN2YYaWaQjABUKLqxQcA_fhxPLFDY';
 
 const MAX_VIDEO_UPLOAD_FILE_SIZE_MB = 50;
 const MAX_VIDEO_UPLOAD_FILE_SIZE = MAX_VIDEO_UPLOAD_FILE_SIZE_MB * 1024 * 1024;
-const MAX_VIDEO_UPLOAD_DURATION = 120;
+const MAX_VIDEO_UPLOAD_DURATION = 900;
 const MAX_VIDEO_UPLOAD_DURATION_TOLERANCE = 1;
 const MAX_VIDEO_PROVIDER_REFERENCE_DURATION = 15;
 const MAX_VIDEO_PROVIDER_REFERENCE_DURATION_TOLERANCE = 0.5;
@@ -59,6 +67,16 @@ function warnLegacyModelFlag(replacement) {
   process.stderr.write(`⚠️  --model is deprecated here; use ${replacement}.\n`);
 }
 
+function validateChatAgentModel(value) {
+  if (!value || !CHAT_AGENT_MODELS.includes(value)) {
+    process.stderr.write(`❌ Unknown Agent LLM: ${value || '(missing value)'}\n`);
+    process.stderr.write(`Choose one of: ${CHAT_AGENT_MODELS.join(', ')}\n`);
+    process.stderr.write('--agent-model selects only the Agent LLM. Put image/video model preferences in the chat prompt, or use the explicit edit/video commands.\n');
+    process.exit(1);
+  }
+  return value;
+}
+
 function getCliVersion() {
   try {
     const pkg = JSON.parse(fs.readFileSync(new URL('../package.json', import.meta.url), 'utf-8'));
@@ -351,13 +369,15 @@ Options:
   --audio <file|url>        Attach a song, beat, or voice reference. MP3/WAV, repeatable.
   --media-manifest <file|-> Import source_url + start + end + description clips before this run.
   --skill <id|label|name>   Use an installed skill or auto-install a matched marketplace skill.
+  --agent-model <id>        Agent LLM only: auto, gpt-5.6-terra, gpt-5.6-sol,
+                            gpt-5.6-luna, grok-4.5, or deepseek-v4-pro.
   --background, -b          Submit and print a runId.
   --json                    Output structured JSON.
   --stream                  Legacy live SSE stream.
   --help, -h                Show this help.
 
-Model routing is automatic in chat. Do not pass --agent-model, --image-model,
---video-model, or the legacy --model flag.
+Agent LLM defaults to auto (currently gpt-5.6-terra). Image/video model routing
+stays automatic in chat; --image-model, --video-model, and --model are rejected.
 
 What you can ask:
   Image edit
@@ -372,6 +392,11 @@ What you can ask:
   Marketplace skill
     makaron chat --project auto --image selfie.jpg --skill "Football Captain" "make this cinematic"
 
+  Built-in production skill
+    makaron skills list --built-in
+    makaron skills show talking-head --built-in
+    makaron chat --project auto --video talk.mp4 --skill talking-head "make a tight captioned edit"
+
   Fix one video moment from a screenshot
     makaron chat --project <id> --image screenshot.png "@4 this frame should be Paris; only fix this moment"
 
@@ -381,6 +406,9 @@ What you can ask:
   Agent-to-agent source-range handoff
     makaron chat --project auto --media-manifest set-01.json -b --json "make a 30s vertical video"
 
+  Compare Agent LLMs with identical inputs
+    makaron chat --project auto --agent-model deepseek-v4-pro -b --json "make a 20s badminton video"
+
   Music
     makaron chat --project <id> "add calm piano background music"
 
@@ -422,6 +450,7 @@ async function streamAgent(baseUrl, headers, projectId, prompt, opts = {}) {
       projectId,
       prompt,
       headless: true,
+      ...(opts.agentModel ? { agentModel: opts.agentModel } : {}),
       ...(opts.uploadedVideoCount ? { uploadedVideoCount: opts.uploadedVideoCount } : {}),
       ...(opts.turnMediaCount ? { turnMediaCount: opts.turnMediaCount } : {}),
     }),
@@ -530,6 +559,7 @@ async function streamAgent(baseUrl, headers, projectId, prompt, opts = {}) {
 
 async function submitRun(baseUrl, headers, projectId, prompt, opts = {}) {
   const body = { projectId, prompt };
+  if (opts.agentModel) body.agentModel = opts.agentModel;
   if (opts.currentSnapshotIndex != null) body.currentSnapshotIndex = opts.currentSnapshotIndex;
   if (opts.isNsfw) body.isNsfw = opts.isNsfw;
   if (opts.audioAttachments?.length) body.audioAttachments = opts.audioAttachments;
@@ -1149,12 +1179,29 @@ async function fetchBuiltInSkills(baseUrl) {
   return (data.skills || []).filter(skill => skill.builtIn);
 }
 
-function printBuiltInSkills(skills) {
+function isDiscoverableBuiltInSkill(skill) {
+  return skill.userSelectable !== false || skill.manifestVisible === true;
+}
+
+function builtInSkillSearchText(skill) {
+  return [
+    skill.name,
+    skill.label,
+    skill.description,
+    skill.studioRunRecipe,
+    skill.studioRunProfile,
+    skill.canonicalSkill,
+    ...(Array.isArray(skill.tags) ? skill.tags : []),
+  ].filter(Boolean).join(' ').toLowerCase();
+}
+
+function printBuiltInSkills(skills, opts = {}) {
   if (!skills.length) {
     console.log('No built-in skills found.');
     return;
   }
-  console.log(`Built-in skills: ${skills.length}\n`);
+  const heading = opts.heading || 'Built-in skills';
+  console.log(`${heading}: ${skills.length}\n`);
   for (const skill of skills) {
     const recipe = skill.studioRunRecipe ? `  [Studio Run: ${skill.studioRunRecipe}]` : '';
     const source = skill.sourceMediaRequired ? '  [source media required]' : '';
@@ -1164,6 +1211,30 @@ function printBuiltInSkills(skills) {
     console.log(`  ${skill.name}${recipe}${source}${adapter}`);
     if (skill.description) console.log(`    ${String(skill.description).replace(/\s+/g, ' ').trim()}`);
   }
+  if (opts.hint !== false) {
+    console.log('\nInspect and use a skill:');
+    console.log('  makaron skills show <name> --built-in');
+    console.log('  makaron chat --project auto --skill <name> "your request"');
+  }
+}
+
+function printBuiltInSkill(skill) {
+  const description = String(skill.description || '').replace(/\s+/g, ' ').trim();
+  console.log(`${skill.label || skill.name} (${skill.name})`);
+  if (description) console.log(`\nPurpose:\n  ${description}`);
+  console.log('\nBest input:');
+  console.log(`  ${skill.inputHint || (skill.sourceMediaRequired ? 'Source media is required. Attach it with --video, --image, or --audio as appropriate.' : 'Start from a clear brief; attach source media when the request depends on existing footage or assets.')}`);
+  if (skill.studioRunRecipe || skill.studioRunProfile) {
+    console.log('\nWorkflow:');
+    if (skill.studioRunRecipe) console.log(`  Studio Run recipe: ${skill.studioRunRecipe}`);
+    if (skill.studioRunProfile) console.log(`  Profile: ${skill.studioRunProfile}`);
+  }
+  if (Array.isArray(skill.tags) && skill.tags.length) {
+    console.log(`\nKeywords:\n  ${skill.tags.join(', ')}`);
+  }
+  console.log('\nUse with chat:');
+  const media = skill.sourceMediaRequired ? ' --video <file>' : '';
+  console.log(`  makaron chat --project auto${media} --skill ${skill.name} "describe the result you want"`);
 }
 
 function marketplaceSearchText(skill) {
@@ -1693,6 +1764,8 @@ Commands:
 
   chat --project <id> "message"      Chat (non-blocking, polls for result)
   chat --project <id> --skill <id>   Use a built-in or marketplace skill
+  chat --project <id> --agent-model <id> "message"
+                                     Select only the Agent LLM (strict allowlist)
   chat --project <id> --video <file> Attach video to conversation
   chat --project <id> --audio <file> Attach song/beat/voice reference
   chat --project auto --media-manifest <file> "message"
@@ -1726,7 +1799,8 @@ Examples:
   makaron chat --project <id> "turn this into a short video"
 
 Run makaron <command> --help for command-specific options.
-Chat chooses agent, image, and video models automatically.
+Chat defaults the Agent LLM automatically; --agent-model can select an exact
+Agent LLM. Image and video model routing remains automatic in chat.
 
 Environment:
   MAKARON_API_KEY       API key (mk_live_xxx) — recommended for agents
@@ -1818,20 +1892,25 @@ function printHelp(topic, subtopic) {
   } else if (topic === 'install-skill') {
     console.log('Usage: makaron install-skill [--global] [--agent <agent>] [--yes]');
   } else if (topic === 'skills') {
-    if (subtopic === 'list') console.log('Usage: makaron skills list [--built-in] [--json]');
-    else if (subtopic === 'search') console.log('Usage: makaron skills search <query> [--json]');
-    else if (subtopic === 'show') console.log('Usage: makaron skills show <marketplace-id|label> [--json]');
+    if (subtopic === 'list') console.log('Usage: makaron skills list [--built-in] [--all] [--json]');
+    else if (subtopic === 'search') console.log('Usage: makaron skills search <query> [--built-in] [--all] [--json]');
+    else if (subtopic === 'show') console.log('Usage: makaron skills show <id|label|name> [--built-in] [--json]');
     else if (subtopic === 'install') console.log('Usage: makaron skills install <marketplace-id|label> [--json]');
     else console.log(`Skill commands:
-  skills list --built-in              List all built-in Makaron skills and Studio Run recipes
+  skills list --built-in              List user-facing built-in skills and what they do
+  skills list --built-in --all        Include internal/adapted helper skills
   skills list                         List marketplace skills
   skills search <query>               Search marketplace skills
+  skills search <query> --built-in    Find a built-in skill by task or keyword
   skills show <id|label> --built-in   Show a built-in skill
   skills show <id|label>              Show a marketplace skill
   skills install <id|label>           Install a marketplace skill to your workspace
 
 Use with chat:
   makaron chat --project auto --skill <id|label> "your request"
+
+Not sure which built-in skill to use? Start with:
+  makaron skills list --built-in
 `);
   } else if (topic === 'materialize') {
     console.log(`Usage: makaron materialize --project <id> (--media <N> | --snapshot <snapshotId> | --design-path <path> | --design-json <file|->) [--wait] [--publish|--no-publish] [--profile fast_720p|source] [--pick url|job_id|status]`);
@@ -1854,7 +1933,7 @@ Use with chat:
     else console.log(`Video commands:
   video script --image <file> [--image <file>] "direction"   Write video script
   video create --script "..." --video-model seedance-fast    Native text-to-video (no image required)
-  video create --script "..." --video-model minimax-h3 --video-resolution 2k    MiniMax H3 native 2K text-to-video
+  video create --script "..." --video-model minimax-h3                          MiniMax H3 text-to-video (default 768P)
   video create --script "..." --image <url> [--duration 10]  Submit video task
   video create --script "..." --video <public-url> [--video-model seedance-fast|seedance-mini|seedance|seedance-2.5|kling|google-omni|minimax-h3]  Edit/reference a video (Grok does not support video refs)
   video status <taskId>                                      Check video status
@@ -1968,6 +2047,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   let jsonOutput = false;
   let activeSkill = undefined;
   let mediaManifestPath = undefined;
+  let agentModel = undefined;
   for (let i = 1; i < args.length; i++) {
     if (args[i] === '--project' && args[i + 1]) projectId = args[++i];
     else if (args[i] === '--image' && args[i + 1]) chatImages.push(args[++i]);
@@ -1983,6 +2063,21 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     else if (args[i].startsWith('--media-manifest=')) mediaManifestPath = args[i].slice('--media-manifest='.length);
     else if (args[i] === '--skill' && args[i + 1]) activeSkill = args[++i];
     else if (args[i].startsWith('--skill=')) activeSkill = args[i].slice('--skill='.length);
+    else if (args[i] === '--agent-model') {
+      if (agentModel !== undefined) {
+        process.stderr.write('❌ Pass --agent-model only once per chat run.\n');
+        process.exit(1);
+      }
+      if (!args[i + 1] || args[i + 1].startsWith('--')) validateChatAgentModel('');
+      agentModel = validateChatAgentModel(args[++i]);
+    }
+    else if (args[i].startsWith('--agent-model=')) {
+      if (agentModel !== undefined) {
+        process.stderr.write('❌ Pass --agent-model only once per chat run.\n');
+        process.exit(1);
+      }
+      agentModel = validateChatAgentModel(args[i].slice('--agent-model='.length));
+    }
     else if (args[i] === '--stream') useStream = true;
     else if (args[i] === '--background' || args[i] === '-b') background = true;
     else if (args[i] === '--json') jsonOutput = true;
@@ -1991,11 +2086,11 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
       process.exit(1);
     }
     else if (
-      ['--agent-model', '--image-model', '--video-model', '--model'].includes(args[i])
-      || ['--agent-model=', '--image-model=', '--video-model=', '--model='].some(prefix => args[i].startsWith(prefix))
+      ['--image-model', '--video-model', '--model'].includes(args[i])
+      || ['--image-model=', '--video-model=', '--model='].some(prefix => args[i].startsWith(prefix))
     ) {
       const flag = args[i].split('=')[0];
-      process.stderr.write(`❌ makaron chat chooses agent, image, and video models automatically. Remove ${flag} and retry.\n`);
+      process.stderr.write(`❌ ${flag} is not valid for makaron chat. Only --agent-model may select the Agent LLM; image/video routing stays automatic. Remove ${flag} and retry.\n`);
       process.exit(1);
     }
     else promptParts.push(args[i]);
@@ -2213,7 +2308,8 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
         uploadedTurnVideoCount += videoSnaps.length;
         uploadedTurnMediaCount += videoSnaps.length;
       } else {
-        process.stderr.write(`⚠️ Failed to add videos: ${await res.text()}\n`);
+        process.stderr.write(`❌ Failed to add videos to the project timeline: ${await res.text()}\n`);
+        process.exit(1);
       }
     }
 
@@ -2222,6 +2318,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   if (useStream) {
     // Legacy SSE mode
     const { results } = await streamAgent(baseUrl, headers, projectId, finalPrompt, {
+      agentModel,
       uploadedVideoCount: uploadedTurnVideoCount,
       turnMediaCount: uploadedTurnMediaCount,
     });
@@ -2234,6 +2331,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
   } else {
     // Default: fire-and-forget + poll
     const { runId } = await submitRun(baseUrl, headers, projectId, finalPrompt, {
+      agentModel,
       audioAttachments,
       uploadedVideoCount: uploadedTurnVideoCount,
       turnMediaCount: uploadedTurnMediaCount,
@@ -2439,22 +2537,41 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
 
   if (sub === 'list') {
     const builtIn = args.includes('--built-in');
-    const skills = builtIn ? await fetchBuiltInSkills(baseUrl) : await fetchMarketplaceSkills(baseUrl);
+    const allBuiltIn = args.includes('--all');
+    const fetchedSkills = builtIn ? await fetchBuiltInSkills(baseUrl) : await fetchMarketplaceSkills(baseUrl);
+    const skills = builtIn && !allBuiltIn
+      ? fetchedSkills.filter(isDiscoverableBuiltInSkill)
+      : fetchedSkills;
     if (jsonOutput) console.log(JSON.stringify({ skills }, null, 2));
-    else if (builtIn) printBuiltInSkills(skills);
+    else if (builtIn) printBuiltInSkills(skills, {
+      heading: allBuiltIn ? 'All built-in skills' : 'Built-in skills available to use',
+    });
     else printMarketplaceSkills(skills);
   } else if (sub === 'search') {
-    const query = args.filter((arg, index) => index > 1 && arg !== '--json').join(' ').trim();
-    if (!query) { console.error('Usage: makaron skills search <query> [--json]'); process.exit(1); }
+    const builtIn = args.includes('--built-in');
+    const allBuiltIn = args.includes('--all');
+    const query = args.filter((arg, index) => index > 1 && !['--json', '--built-in', '--all'].includes(arg)).join(' ').trim();
+    if (!query) { console.error('Usage: makaron skills search <query> [--built-in] [--all] [--json]'); process.exit(1); }
     const lowerQuery = query.toLowerCase();
     const slugQuery = slugifySkill(query);
-    const skills = (await fetchMarketplaceSkills(baseUrl))
-      .filter(skill => {
-        const rawMatch = marketplaceSkillTokens(skill).some(token => token.includes(lowerQuery));
-        const slugMatch = slugQuery ? marketplaceSearchText(skill).includes(slugQuery) : false;
-        return rawMatch || slugMatch;
-      });
+    const builtInQueryTokens = slugQuery.split('-').filter(Boolean);
+    const skills = builtIn
+      ? (await fetchBuiltInSkills(baseUrl))
+        .filter(skill => allBuiltIn || isDiscoverableBuiltInSkill(skill))
+        .filter(skill => {
+          const searchText = builtInSkillSearchText(skill);
+          const slugText = slugifySkill(searchText);
+          return searchText.includes(lowerQuery)
+            || (builtInQueryTokens.length > 0 && builtInQueryTokens.every(token => slugText.includes(token)));
+        })
+      : (await fetchMarketplaceSkills(baseUrl))
+        .filter(skill => {
+          const rawMatch = marketplaceSkillTokens(skill).some(token => token.includes(lowerQuery));
+          const slugMatch = slugQuery ? marketplaceSearchText(skill).includes(slugQuery) : false;
+          return rawMatch || slugMatch;
+        });
     if (jsonOutput) console.log(JSON.stringify({ skills }, null, 2));
+    else if (builtIn) printBuiltInSkills(skills, { heading: `Built-in skill matches for "${query}"` });
     else printMarketplaceSkills(skills);
   } else if (sub === 'show') {
     const identifier = args[2];
@@ -2466,7 +2583,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
       : findMarketplaceSkill(skills, identifier);
     if (!skill) { console.error(`Skill not found: ${identifier}`); process.exit(1); }
     if (jsonOutput) console.log(JSON.stringify(skill, null, 2));
-    else if (builtIn) printBuiltInSkills([skill]);
+    else if (builtIn) printBuiltInSkill(skill);
     else printMarketplaceSkill(skill);
   } else if (sub === 'install') {
     const identifier = args[2];
@@ -2480,9 +2597,11 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     else console.log(data.skillName);
   } else {
     console.log(`Skill commands:
-  skills list --built-in              List all built-in Makaron skills and Studio Run recipes
+  skills list --built-in              List user-facing built-in skills and what they do
+  skills list --built-in --all        Include internal/adapted helper skills
   skills list                         List marketplace skills
   skills search <query>               Search marketplace skills
+  skills search <query> --built-in    Find a built-in skill by task or keyword
   skills show <id|label> --built-in   Show a built-in skill
   skills show <id|label>              Show a marketplace skill
   skills install <id|label>           Install a marketplace skill to your workspace
@@ -2776,7 +2895,7 @@ if (!command || command === '--help' || command === '-h' || command === 'help')
     console.log(`Video commands:
   video script --image <file> [--image <file>] "direction"   Write video script
   video create --script "..." --video-model seedance-fast    Native text-to-video (no image required)
-  video create --script "..." --video-model minimax-h3 --video-resolution 2k    MiniMax H3 native 2K text-to-video
+  video create --script "..." --video-model minimax-h3                          MiniMax H3 text-to-video (default 768P)
   video create --script "..." --image <url> [--duration 10]  Submit video task
   video create --script "..." --video <public-url> [--video-model seedance-fast|seedance-mini|seedance|seedance-2.5|kling|google-omni|minimax-h3]  Edit/reference a video (Grok does not support video refs)
   video status <taskId>                                      Check video status

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "makaron-cli",
-  "version": "0.13.6",
+  "version": "0.13.8",
   "description": "Talk to Makaron Agent from the terminal — create projects, edit images, generate videos",
   "type": "module",
   "scripts": {

package/skills/makaron/SKILL.md

@@ -85,7 +85,11 @@ npx makaron-cli chat --project auto --image photo.jpg --json -b "make it cinemat
 npx makaron-cli chat --project auto --image img1.jpg --image img2.jpg --json -b "combine these"
 ```
 
-`chat` always routes agent, image, and video models automatically. Never pass `--agent-model`, `--image-model`, `--video-model`, or the legacy `--model` flag to `chat`; the CLI rejects them before starting a run. Model flags remain available only on explicit low-level commands such as `edit` and `video create`.
+`chat` routes image and video models automatically. Use `--agent-model` only when the user explicitly asks to select or compare the reasoning/tool-calling Agent LLM. Accepted values are exactly `auto`, `gpt-5.6-terra`, `gpt-5.6-sol`, `gpt-5.6-luna`, `grok-4.5`, and `deepseek-v4-pro`; `auto` currently resolves to `gpt-5.6-terra`. Never put an image or video model ID in `--agent-model`. The CLI rejects unknown Agent IDs plus `--image-model`, `--video-model`, and legacy `--model` before starting a chat run.
+
+```bash
+npx makaron-cli chat --project auto --agent-model deepseek-v4-pro --json -b "make a 20s badminton video"
+```
 
 Returns immediately:
 ```json
@@ -105,6 +109,33 @@ Returns immediately:
 | Beat-sync video from audio | `npx makaron-cli chat --project auto --audio beat.mp3 "use Seedance Mini at 480p to make a beat-synced video"` |
 | Create motion design | `npx makaron-cli chat --project <id> "make an animated Instagram story with this image"` |
 
+### Built-in production skills
+
+When the request names a production format or the correct workflow is unclear,
+discover the current built-in skills before starting. Do not guess a skill slug
+from memory: the server list is the source of truth.
+
+```bash
+# Short list of callable/discoverable production skills and their purpose
+npx makaron-cli skills list --built-in
+
+# Search by task, format, or keyword
+npx makaron-cli skills search "talking head captions" --built-in
+
+# Inspect input requirements, workflow, keywords, and exact invocation
+npx makaron-cli skills show talking-head --built-in
+
+# Use the exact slug returned by list/show
+npx makaron-cli chat --project auto --video talk.mp4 \
+  --skill talking-head -b "remove false starts, add synced captions and useful B-roll"
+```
+
+Use `--all` only when debugging adapters or looking for an internal helper Skill.
+For ordinary creative work, choose from the default built-in list. A named
+destination takes priority over a generic source workflow: for example,
+explicit TikTok/Douyin work uses `tiktok-video`; ordinary speech-led cleanup
+uses `talking-head`; broader mixed-footage editing uses `source-video-studio`.
+
 ### Marketplace skills
 
 Use marketplace skills when the user asks for a named Makaron effect, template, or skill such as "Football Captain", "足球队长", "World Cup MVP", or a marketplace UUID.
@@ -180,7 +211,7 @@ npx makaron-cli chat --project <id> --video clip1.mp4 --video clip2.mp4 -b "comb
 npx makaron-cli chat --project auto --video https://example.com/dance.mp4 -b "extend this to 15 seconds"
 ```
 
-Supported formats: MP4, MOV, WebM. CLI local video uploads support max 50MB, max 120s with 1s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode larger videos before upload; the CLI uploads directly to Storage and rejects videos above those limits. Videos are uploaded to the project timeline. The Agent can analyze scenes, edit content, compose multiple clips, extend duration, and add effects — all via natural language. Seedance video-reference editing is still limited to ~15s provider references, so longer uploaded videos should be split/prepared by the agent before model submission; Kling remains the base/direct edit path.
+Supported formats: MP4, MOV, WebM. CLI local video uploads support max 50MB, max 900s (15 minutes) with 1s metadata tolerance, and <=1080p / 2,086,876 frame pixels. The frontend can transcode larger videos before upload; the CLI uploads directly to Storage and rejects videos above those limits. Videos are uploaded to the project timeline. The Agent can analyze scenes, edit content, compose multiple clips, extend duration, and add effects — all via natural language. Seedance reference-video limits remain provider-specific, so longer uploaded videos should be split/prepared by the agent before model submission; Kling remains the base/direct edit path.
 
 Use `chat --project <id|auto> --video ...` for any project/timeline video work. Direct video commands are standalone raw-tool calls.
 
@@ -280,7 +311,7 @@ npx makaron-cli video create --script "Shot 1 (15s): <<<image_1>>> and <<<image_
 
 # 3b. Native SeeDance or MiniMax H3 text-to-video (no image required)
 npx makaron-cli video create --script "Shot 1 (5s): A neon one-person studio wakes at dawn" --duration 5 --video-model seedance-fast --aspect 16:9
-npx makaron-cli video create --script "Shot 1 (15s): A premium creative editor comes alive" --duration 15 --video-model minimax-h3 --video-resolution 2k --aspect 16:9
+npx makaron-cli video create --script "Shot 1 (15s): A premium creative editor comes alive" --duration 15 --video-model minimax-h3 --aspect 16:9
 
 # 3c. Edit a video from a local file or public URL
 npx makaron-cli video create --script "make it funny" --video input.mp4 --duration 5 --video-model seedance-fast
@@ -296,7 +327,7 @@ npx makaron-cli video status <taskId>
 npx makaron-cli chat --project <id|auto> --video input.mp4 -b "make it funny"
 ```
 
-Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to the selected model limit), `--video <file|url>` and `--audio <file|url>` (repeatable where supported), `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--video-model seedance-fast|seedance-mini|seedance|seedance-2.5|kling|grok|google-omni|minimax-h3`, `--video-resolution auto|480p|720p|768p|1080p|2k|4k`. Default model is `seedance-fast`. SeeDance accepts native text-to-video with no image and integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; MiniMax H3 accepts native text-to-video, 4-15s output, and up to 9 image, up to 3 video, and up to 3 audio references through Makaron Agent/chat. H3 defaults to public 2k output; 768p requires provider preview access plus `MINIMAX_H3_ENABLE_768P=true` on the Makaron server. Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio, including up to 6 image references when no video reference is provided. For `--video-model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
+Options for `video create`: `--script "..."`, `--script-file <path>`, `--image <url>` (repeatable, up to the selected model limit), `--video <file|url>` and `--audio <file|url>` (repeatable where supported), `--duration <seconds>`, `--aspect 9:16|16:9|1:1`, `--video-model seedance-fast|seedance-mini|seedance|seedance-2.5|kling|grok|google-omni|minimax-h3`, `--video-resolution auto|480p|720p|768p|1080p|2k|4k`. Default model is `seedance-fast`. SeeDance accepts native text-to-video with no image and integer output duration 4-15s (default 5s); `seedance-mini` supports 480p/720p and is best for cheaper drafts/multi-size tests; MiniMax H3 accepts native text-to-video, 4-15s output, public 768p/2k resolution, and up to 9 image, up to 3 video, and up to 3 audio references through Makaron Agent/chat. H3 defaults to 768p; request 2k explicitly for maximum/final quality. Kling supports 5-15s; Grok 1.5 supports 1-15s single-image-to-video only; Gemini Omni supports 3-10s fast 720p image/video generation and editing with native generated audio, including up to 6 image references when no video reference is provided. For `--video-model grok`, forced `--aspect` is ignored to avoid xAI stretching the source image; pad/create the image at the target shape first or use another model.
 
 Seedance 2.5 uses `--video-model seedance-2.5` and supports 4-30s at 480p/720p, up to 30 images + 10 videos + 10 audios, repeatable local/URL references, `--video-operation generate|edit|extend`, `--extend-direction`, `--output-format mp4|mov`, and `--web-search`. The Evolink route does not currently expose 4K output.