JPeetz/agent-skills / skills/marketing/agent-n-video-pipeline
agent-n-video-pipeline
UnverifiedUse this skill when producing a fully-local "Agent N presents a message" video on the 16GB Apple-Silicon M5 executor: Kokoro mature TTS → LTX-2.3 MLX A2V talking render with native lip sync → karaoke captions → trim → QA → X caption. Replaces the old cloud Herald pipeline (grok-imagine + volcengine) with zero cloud cost. Activates for Herald release videos, Agent N announcements, and newsletter video messages.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 523 B |
| SKILL.md | skill md | 4.4 KB |
| evals/evals.json | config | 2.4 KB |
| scripts/build_final_video_m5.py | script | 5.0 KB |
| scripts/herald_pipeline_m5.shexecutable | script | 5.4 KB |
| scripts/karaoke_burn.py | script | 11.8 KB |
| scripts/kokoro_tts.py | script | 2.2 KB |
evals/evals.json
View on GitHub{
"skill": "agent-n-video-pipeline",
"version": "1.0.0",
"cases": [
{
"id": "e1",
"description": "Should trigger: fully-local Agent N message video",
"input": "Produce the 'Agent N presents a message' video for the Herald release.",
"shouldTrigger": true,
"expect": "Runs herald_pipeline_m5.sh with spec and anchor through all six local stages",
"assertions": [
"Uses one-command script ./herald_pipeline_m5.sh --spec <spec.json> --anchor agentn_anchor_v1.png",
"Kokoro mature TTS (sid 10), LTX-2.3 MLX A2V render leg",
"Karaoke captions word-synced to TRUE script",
"Trims to voice +2.5s, passes QA gate, generates X caption"
]
},
{
"id": "e2",
"description": "Should trigger: announcement / newsletter video message",
"input": "Make an Agent N announcement video about the new release.",
"shouldTrigger": true,
"expect": "Activates the pipeline with segmented mode for >10s messages",
"assertions": [
"Splits by sentence boundaries via queue_segments.py",
"Re-anchors each segment on the identity image",
"Runs stage-by-stage with env gate checks"
]
},
{
"id": "e3",
"description": "Should trigger: troubleshooting local pipeline pitfalls",
"input": "The A2V render failed at the end with 'ffmpeg not found on PATH'.",
"shouldTrigger": true,
"expect": "Applies known pitfall fix: symlink ffmpeg/ffprobe into Comfy venv bin or export PATH",
"assertions": [
"Does not re-climb already-documented pitfalls",
"Verifies ComfyUI headless at http://M5:8188/system_stats"
]
},
{
"id": "n1",
"description": "Not trigger: only writing the X caption, no video",
"input": "Write the X caption that announces the Agent N video.",
"shouldTrigger": false,
"expect": "Writes caption standalone",
"assertions": [
"No render pipeline started"
]
},
{
"id": "n2",
"description": "Not trigger: cloud pipeline preference",
"input": "Use the old cloud Herald pipeline with grok-imagine and volcengine.",
"shouldTrigger": false,
"expect": "Notes the local replacement but does not force local if user explicitly wants cloud",
"assertions": [
"No M5 pipeline forced without user agreement"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |