Files
OpenMontage/pipeline_defs/screen-demo.yaml
T
calesthio a3e735cc7a Initial release — OpenMontage: the first open-source agentic video production system
11 production pipelines, 47 tools, 124 agent skills.
Supports cloud APIs (fal.ai, OpenAI, ElevenLabs, Suno, HeyGen, Runway) and
free local providers (diffusers, Piper TTS, WAN 2.1, Hunyuan, CogVideo).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-29 08:25:17 -07:00

198 lines
5.7 KiB
YAML

name: screen-demo
version: "2.0"
description: >
Screen recording pipeline. Takes raw screen capture (app demo, browser walkthrough,
coding tutorial) and produces a polished demo video with callouts, zoom crops,
subtitles, and cleaned audio. EP orchestration adds quality gates for legibility,
audio clarity, and pacing.
category: screen_recording
stability: production
default_checkpoint_policy: guided
orchestration:
mode: executive-producer
skill: pipelines/screen-demo/executive-producer
budget_default_usd: 1.00
max_revisions_per_stage: 3
max_send_backs: 3
max_wall_time_minutes: 10
required_skills:
- pipelines/screen-demo/executive-producer
- pipelines/screen-demo/idea-director
- pipelines/screen-demo/script-director
- pipelines/screen-demo/scene-director
- pipelines/screen-demo/asset-director
- pipelines/screen-demo/edit-director
- pipelines/screen-demo/compose-director
- pipelines/screen-demo/publish-director
- meta/reviewer
- meta/checkpoint-protocol
compatible_playbooks:
- clean-professional
- minimalist-diagram
stages:
- name: idea
skill: pipelines/screen-demo/idea-director
produces:
- brief
tools_available: []
checkpoint_required: true
human_approval_default: true
review_focus:
- Brief accurately describes what the screen recording demonstrates
- Target platform and duration are realistic
- Callout strategy identified (what to highlight)
success_criteria:
- Schema-valid brief artifact
- Brief references the provided screen recording footage
- name: script
skill: pipelines/screen-demo/script-director
required_artifacts_in:
- brief
produces:
- script
required_tools:
- transcriber
optional_tools:
- scene_detect
- audio_enhance
tools_available:
- transcriber
- scene_detect
checkpoint_required: true
human_approval_default: true
review_focus:
- Transcription captures any voiceover accurately
- Key UI actions are annotated with timestamps
- Sections align with logical workflow steps
success_criteria:
- Schema-valid script artifact
- Script sections have timestamps from transcript or manual annotation
- name: scene_plan
skill: pipelines/screen-demo/scene-director
required_artifacts_in:
- script
optional_artifacts_in:
- brief
produces:
- scene_plan
required_tools: []
optional_tools:
- frame_sampler
tools_available:
- frame_sampler
checkpoint_required: true
human_approval_default: true
review_focus:
- Zoom-crop regions identified for key UI moments
- Callout overlay positions don't obscure important UI
- Pacing allows viewer to follow the workflow
success_criteria:
- Schema-valid scene_plan artifact
- Every key workflow step has a corresponding scene
- name: assets
skill: pipelines/screen-demo/asset-director
required_artifacts_in:
- scene_plan
optional_artifacts_in:
- script
produces:
- asset_manifest
required_tools:
- subtitle_gen
optional_tools:
- tts_selector
- image_selector
- diagram_gen
- audio_enhance
tools_available:
- subtitle_gen
- tts_selector
- image_selector
- diagram_gen
- audio_enhance
checkpoint_required: true
human_approval_default: false
review_focus:
- Subtitle file exists and matches speech timing
- Reusable callout overlays (arrows, highlights, masks) are prepared
- Audio cleaned of keyboard noise and background hum
success_criteria:
- Schema-valid asset_manifest artifact
- All referenced asset files exist on disk
- name: edit
skill: pipelines/screen-demo/edit-director
required_artifacts_in:
- scene_plan
- asset_manifest
optional_artifacts_in:
- script
produces:
- edit_decisions
tools_available: []
checkpoint_required: true
human_approval_default: false
review_focus:
- Zoom-crop notes are smooth and minimal (no constant motion)
- Dead time (loading, typing pauses) trimmed or sped up
- Callout timing matches narration
success_criteria:
- Schema-valid edit_decisions artifact
- All cuts reference valid source files and assets
- name: compose
skill: pipelines/screen-demo/compose-director
required_artifacts_in:
- edit_decisions
- asset_manifest
optional_artifacts_in:
- scene_plan
produces:
- render_report
required_tools:
- video_compose
- audio_mixer
optional_tools:
- video_trimmer
- audio_enhance
tools_available:
- video_compose
- audio_mixer
- video_trimmer
- audio_enhance
checkpoint_required: true
human_approval_default: false
review_focus:
- Output video is playable and crisp at target resolution
- UI text remains readable after crops and scaling
- Audio is clear with no keyboard/click noise
success_criteria:
- Schema-valid render_report artifact
- Output file exists and passes ffprobe validation
- name: publish
skill: pipelines/screen-demo/publish-director
required_artifacts_in:
- render_report
optional_artifacts_in:
- brief
produces:
- publish_log
tools_available: []
checkpoint_required: true
human_approval_default: true
review_focus:
- Metadata includes relevant software/tool keywords
- Chapter markers align with workflow steps
- Export package is complete
success_criteria:
- Schema-valid publish_log artifact
- Export directory contains video, metadata, and thumbnail concept