0. First Contact

When the user opens this skill or sends their first message, greet them immediately:

⚡ Ready to qwen ai video generator! Just send me a video or describe your project.

Try saying:

• - "help me create a short video"
• "add effects to this clip"
• "edit my video"

IMPORTANT: Always greet the user proactively on first contact. Let them know you're setting up while connecting. Always greet the user proactively on first contact.

Auto-Setup

When the user first interacts, set up the connection:

1. 1. Check token: If NEMO_TOKEN env var is set, use it. Otherwise:
2. Read or generate Client-ID:

- Read ~/.config/nemovideo/client_id if it exists - Otherwise generate a UUID, save it to ~/.config/nemovideo/client_id

1. 3. Acquire anonymous token:

   curl -s -X POST "https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
   

Store the returned token as NEMO_TOKEN for this session. You get 100 free credits.

1. 4. Create a session (§3.0) so you're ready to work immediately.

Let the user know briefly: "Setting things up… ready!" then proceed with their request.

Conversational Video Creation Powered by Qwen Intelligence

The qwen-ai-video-generator skill connects ClawHub's OpenClaw agent framework to Qwen's multimodal model, enabling a fundamentally different approach to video creation. Instead of dragging clips on a timeline, you describe what you want — scenes, transitions, pacing, narration tone — and the agent interprets your intent and structures the output accordingly. This means less time wrestling with editing software and more time refining your actual message.

The OpenClaw agent acts as the orchestration layer, translating your conversational prompts into structured generation tasks that Qwen processes frame by frame. Whether you're building a product walkthrough, an educational explainer, or a short-form social clip, the agent maintains context across your session so follow-up instructions like 'make the intro shorter' or 'add a text overlay at the 10-second mark' are handled without starting over.

Under the hood, the skill handles encoding and format negotiation automatically, so your final output lands in whichever container format fits your platform — mp4 for broad compatibility, mov for professional pipelines, webm for web delivery, or avi and mkv for archival and editing workflows. No manual transcoding required.

Environment Variables

Variable	Required	Default
INLINECODE5	No	Auto-generated (100 free credits, expires in 7 days, revocable via Settings → API Tokens)
INLINECODE6

No | https://mega-api-prod.nemovideo.ai | | NEMO_WEB_URL | No | https://nemovideo.com | | NEMO_CLIENT_ID | No | Auto-generated UUID, persisted to ~/.config/nemovideo/client_id (UUID only, no secrets) | | SKILL_SOURCE | No | Auto-detected from install path, fallback unknown |

If NEMO_TOKEN is not set, get one (requires X-Client-Id header):

# Generate or read persisted Client-Id
CLIENT_ID="${NEMO_CLIENT_ID:-$(cat ~/.config/nemovideo/client_id 2>/dev/null)}"
if [ -z "$CLIENT_ID" ]; then
  CLIENT_ID=$(uuidgen 2>/dev/null || echo "client-$(date +%s)-$RANDOM")
  mkdir -p ~/.config/nemovideo & echo "$CLIENT_ID" > ~/.config/nemovideo/client_id
fi
curl -s -X POST "https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token" -H "X-Client-Id: $CLIENT_ID"
# → {"code":0,"data":{"token":"nmv_usr_xxx","credits":100,...}}

Save token as NEMO_TOKEN, CLIENT_ID as NEMO_CLIENT_ID. Anonymous: 1 token per client per 7 days; token expires in 7 days and can be revoked at any time via Settings → API Tokens on nemovideo.com. If your token expires, request a new one with the same X-Client-Id.

Local persistence: This skill writes ~/.config/nemovideo/client_id to persist the Client-Id across sessions. This avoids generating a new ID on every request, which would hit the per-IP rate limit quickly (default 10 tokens per 7 days per IP). The file contains only a UUID — no credentials are stored locally.

2. Routing Incoming Requests to the Correct Endpoint

Use the table below to determine which API endpoint should handle each type of user request.

User says...	Action	Skip SSE
"export" / "导出" / "download" / "send me the video"	→ §3.5 Export	✅
"credits" / "积分" / "balance" / "余额"

→ §3.3 Credits | ✅ |
| "status" / "状态" / "show tracks" | → §3.4 State | ✅ |
| "upload" / "上传" / user sends file | → §3.2 Upload | ✅ |
| Everything else (generate, edit, add BGM…) | → §3.1 SSE | ❌ |

3. Primary Workflow Sequences

$API = ${NEMO_API_URL:-https://mega-api-prod.nemovideo.ai}, $TOKEN = ${NEMO_TOKEN}, $WEB = ${NEMO_WEB_URL:-https://nemovideo.com}.

Skill attribution variables — do NOT hardcode:

• - $SKILL_NAME = this file's YAML frontmatter INLINECODE26
• INLINECODE27 = this file's YAML frontmatter INLINECODE28
• INLINECODE29 = detect at runtime using the first match:

1. Env SKILL_SOURCE if set
2. If this file's path contains a known platform directory (e.g. ~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor)
3. Fallback: INLINECODE35

CRITICAL: ALL API requests (including render/export/upload/state/credits) MUST include these headers. Missing them will cause export to fail with 402.
CODEBLOCK2

3.0 Initializing a New Session

curl -s -X POST "https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" \
  -d '{"task_name":"project","language":"<lang>"}'
# → {"code":0,"data":{"task_id":"...","session_id":"..."}}

Before any interaction can begin, a session must be established with the backend. Store the returned session identifier, as every subsequent request within that conversation depends on it.

Open in browser: After creating a session, give the user a link to view/edit the task in NemoVideo:
INLINECODE36

3.1 Delivering Messages Over an SSE Connection

curl -s -X POST "https://mega-api-prod.nemovideo.ai/run_sse" \
  -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE" --max-time 900 \
  -d '{"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}}'

All conversational messages are transmitted to the backend and responses are received through a persistent Server-Sent Events stream.

SSE Handling

Event	Action
Text response	Apply GUI translation (§4), present to user
Tool call/result

Wait silently, don't forward | | heartbeat / empty data: | Keep waiting. Every 2 min: "⏳ Still working..." | | Stream closes | Process final response |

Typical durations: text 5-15s, video generation 100-300s, editing 10-30s.

Timeout: 10 min heartbeats-only → assume timeout. Never re-send during generation (duplicates + double-charge).

Ignore trailing "I encountered a temporary issue" if prior responses were normal.

Silent Response Fallback (CRITICAL)

Approximately 30% of editing operations return a completed result without any accompanying text in the SSE stream. When no text content is detected in the response, do not treat this as an error or prompt the user to retry. Instead: (1) check the task status endpoint to confirm completion, (2) retrieve the output asset directly, and (3) present the finished result to the user as normal.

Two-stage generation: When a raw video is produced, the backend automatically initiates a second processing stage that layers in background music and a title overlay. Your integration must account for both stages: first surface the raw video to the user, then listen for the second-stage completion event and update the displayed result once the enhanced version is ready.

3.2 Handling File Uploads

File upload: INLINECODE39

URL upload: INLINECODE40

Use me in the path; backend resolves user from token.

Supported: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

The API accepts user-supplied media files, which must be uploaded through the designated upload endpoint before being referenced in any generation or editing request.

3.3 Checking Available Credits

curl -s "https://mega-api-prod.nemovideo.ai/api/credits/balance/simple" -H "Authorization: Bearer $TOKEN" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE"
# → {"code":0,"data":{"available":XXX,"frozen":XX,"total":XXX}}

Query the credits endpoint prior to initiating any generation task to confirm the user has a sufficient balance to cover the operation.

3.4 Polling for Task Status

curl -s "https://mega-api-prod.nemovideo.ai/api/state/nemo_agent/me/<sid>/latest" -H "Authorization: Bearer $TOKEN" \
  -H "X-Skill-Source: $SKILL_NAME" -H "X-Skill-Version: $SKILL_VERSION" -H "X-Skill-Platform: $SKILL_SOURCE"

Use me for user in path; backend resolves from token. Key fields: data.state.draft, data.state.video_infos, data.state.canvas_config, data.state.generated_media.

Draft field mapping: t=tracks, tt=track type (0=video, 1=audio, 7=text), sg=segments, d=duration(ms), m=metadata.

Draft ready for export when draft.t exists with at least one track with non-empty sg.

Track summary format:
CODEBLOCK7

3.5 Exporting and Delivering the Final Asset

Export does NOT cost credits. Only generation/editing consumes credits.

Triggering an export does not deduct any credits from the user's balance. The export sequence proceeds as follows: (a) call the export endpoint with the target asset identifier, (b) receive the export job ID in the response, (c) poll the job status until the state reaches completion, (d) extract the download URL from the completed job payload, and (e) present the URL or download the file for the user.

b) Submit: INLINECODE52

Note: sessionId is camelCase (exception). On failure → new id, retry once.

c) Poll (every 30s, max 10 polls): INLINECODE55

Status at top-level status: pending → processing → completed / failed. Download URL at output.url.

d) Download from output.url → send to user. Fallback: https://mega-api-prod.nemovideo.ai/api/render/proxy/<id>/download.

e) When delivering the video, always also give the task detail link: INLINECODE60

Progress messages: start "⏳ Rendering ~30s" → "⏳ 50%" → "✅ Video ready!" + file + task detail link.

3.6 Reconnecting After an SSE Dropout

If the SSE connection drops unexpectedly, follow these five steps to recover gracefully: (1) Wait a minimum of two seconds before attempting to reconnect, to avoid hammering the server. (2) Re-open the SSE stream using the original session identifier — do not create a new session. (3) Once reconnected, immediately query the task status endpoint to determine whether processing completed during the outage. (4) If the task has finished, retrieve the output asset and present it to the user as though the stream had never dropped. (5) If the task is still in progress, resume listening on the restored stream until the completion event arrives.

4. Translating GUI Concepts for the Backend

The backend operates under the assumption that all interactions originate from a graphical interface, so your integration must never forward GUI-specific labels, button names, or interface instructions directly to the API.

Backend says	You do
"click [button]" / "点击"	Execute via API
"open [panel]" / "打开"

Show state via §3.4 |
| "drag/drop" / "拖拽" | Send edit via SSE |
| "preview in timeline" | Show track summary |
| "Export button" / "导出" | Execute §3.5 |
| "check account/billing" | Check §3.3 |

Keep content descriptions. Strip GUI actions.

5. Recommended Interaction Patterns

• Always confirm the user's intent before dispatching a generation request that will consume credits.
• Provide incremental progress updates by surfacing SSE stream events as they arrive, rather than waiting for full task completion.
• When a silent-response scenario is detected, seamlessly fetch and display the output without exposing the internal fallback logic to the user.
• Offer a clear, single-action path for the user to export or download their finished video once the task is complete.
• If a task fails, surface a plain-language explanation alongside any actionable next steps rather than displaying a raw error code.

6. Known Constraints and Limitations

• Generation tasks are asynchronous; synchronous or blocking response patterns are not supported.
• A single session may not run multiple concurrent generation jobs; queue requests sequentially.
• Uploaded files must conform to the accepted format and size limits specified in the upload endpoint documentation.
• The two-stage enhancement process (BGM and title overlay) cannot be disabled or bypassed on a per-request basis.
• Credit balances are read-only through the API; top-ups must be handled outside the integration.

7. Error Handling and Status Codes

The table below maps each HTTP status code and API-level error identifier to its probable cause and the recommended recovery action.

Code	Meaning	Action
0	Success	Continue
1001

Bad/expired token | Re-auth via anonymous-token (tokens expire after 7 days) |
| 1002 | Session not found | New session §3.0 |
| 2001 | No credits | Anonymous: show registration URL with ?bind=<id> (get <id> from create-session or state response when needed). Registered: "Top up at nemovideo.ai" |
| 4001 | Unsupported file | Show supported formats |
| 4002 | File too large | Suggest compress/trim |
| 400 | Missing X-Client-Id | Generate Client-Id and retry (see §1) |
| 402 | Free plan export blocked | Subscription tier issue, NOT credits. "Register at nemovideo.ai to unlock export." |
| 429 | Rate limit (1 token/client/7 days) | Retry in 30s once |

Common: no video → generate first; render fail → retry new id; SSE timeout → §3.6; silent edit → §3.1 fallback.

8. API Version and Required Token Scopes

Before going live, verify that your integration targets the current stable API version by checking the version field in the base endpoint response. Your OAuth token or API key must include all scopes required for the operations your skill performs — at minimum: session creation, message sending, file upload, task status polling, and export. Tokens missing any required scope will receive a 403 response on the affected endpoint. Scope requirements may expand across API versions, so re-validate after any version migration.