vibe-pipeline
Skill185 starsChanged yesterdayMITView on GitHub
Author and run VibeFrame YAML pipelines with vibe run, checkpoints, and budget controls.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- releaseSkill
- sync-checkSkill
- testSkill
- vibe-pipelineSkill
- vibe-sceneSkill
- releaseSkill
- sync-checkSkill
- testSkill
- vibe-sceneSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 1 is distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use this skill when the user wants a reproducible multi-step media workflow, checkpointed execution, or budget-limited provider calls.
- Very specific: line 54
Use scene-build and scene-render when a storyboard project already exists:
- Very specific: line 82
Keep this in sync with packages/cli/src/pipeline/types.ts and packages/cli/src/pipeline/executor.ts.
- Very specific: line 137
Keep step ids short and stable (image, motion, title, render).
- Very specific: line 139
Use $<step-id>.output rather than repeating file paths.
- Very specific: line 140
Add a budget: block for any pipeline that can call image/video providers.
- Very specific: line 141
Use scene-build for storyboard projects and generate-* / edit-* for standalone media chains.
- Very specific: line 144
When converting a shell sequence, map each vibe ...
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- GENERATED by `pnpm agent-sync` from .agents/skills/vibe-pipeline/SKILL.md — DO NOT EDIT. -->Vibe Pipeline
A VibeFrame pipeline is a YAML manifest executed by vibe run. Steps can
reference earlier outputs with $<step-id>.output, and the executor writes a
checkpoint under the output directory so failed runs can resume.
Use this skill when the user wants a reproducible multi-step media workflow, checkpointed execution, or budget-limited provider calls.
Minimal Skeleton
name: promo-video
budget:
costUsd: 8
maxToolErrors: 1
steps:
- id: image
action: generate-image
provider: openai
model: "2"
size: 1536x1024
quality: hd
prompt: "sleek product shot on a quiet studio background"
output: hero.png
- id: video
action: generate-video
provider: seedance
image: $image.output
prompt: "slow cinematic camera push, polished product demo motion"
duration: 5
ratio: "16:9"
output: hero.mp4
- id: titled
action: edit-motion-overlay
input: $video.output
description: "minimal lower-third title, clean sans-serif, subtle grain"
model: gemini
understand: auto
output: titled.mp4Scene Project Skeleton
Use scene-build and scene-render when a storyboard project already exists:
name: storyboard-render
budget:
costUsd: 2
maxToolErrors: 1
steps:
- id: build
action: scene-build
project: my-video
mode: batch
composer: openai
tts: kokoro
skipBackdrop: true
skipRender: true
- id: render
action: scene-render
project: my-video
output: renders/final.mp4
quality: standard
fps: 30
format: mp4Supported Actions
Keep this in sync with packages/cli/src/pipeline/types.ts and
packages/cli/src/pipeline/executor.ts.
- Generate:
generate-image,generate-video,generate-tts,generate-sfx,generate-music,generate-storyboard,generate-motion - Edit:
edit-silence-cut,edit-jump-cut,edit-caption,edit-noise-reduce,edit-fade,edit-translate-srt,edit-text-overlay,edit-motion-overlay,edit-grade,edit-speed-ramp,edit-reframe,edit-interpolate,edit-upscale,edit-image - Audio:
audio-transcribe,audio-isolate,audio-dub,audio-duck - Detect:
detect-scenes,detect-silence,detect-beats - Analyze/review:
analyze-video,analyze-media,review-video - Scene:
scene-build,scene-render
Each step names its main input input and its file output (relative to
the output directory); other parameters follow the matching vibe command
or MCP tool. If unsure, read the executor source. There is no public
vibe run --list-actions command.
vibe run refuses an unknown action before any step runs (exit 2). A run
with a failed step exits 1 with the per-step report in the error's data;
fix the step and rerun with --resume.
A failed step carries errorCode (AUTH_ERROR, API_ERROR, NOT_FOUND, ...)
and, for a provider failure, errorKind (auth, quota, rate-limit, ...):
fix the key for auth, wait for rate-limit, and retry provider/network.
Running
vibe run pipeline.yaml --dry-run
vibe run pipeline.yaml -o pipeline-output
vibe run pipeline.yaml -o pipeline-output --resume
vibe run pipeline.yaml -o pipeline-output --budget-usd 5
vibe run pipeline.yaml -o pipeline-output --jsonUseful flags:
--dry-runvalidates the graph and shows upper-bound cost estimates.- On a real run each step reports
costUsd: its metered provider usage priced from the model catalog, or its upper-bound estimate (flaggedcostEstimated) when nothing was metered.budget.costUsdcounts these, including what failed steps were billed. --resumeskips completed checkpointed steps.--budget-usd,--budget-tokens,--max-errorsoverride or extend the manifest budget.--effort low|medium|high|xhighforwards an LLM effort hint where supported.--jsonreturns structured output for agents.
Checkpoint file: <output-dir>/.pipeline-state.yaml.
Authoring Rules
- Dry-run before executing paid provider steps.
- Keep step ids short and stable (
image,motion,title,render). - Name outputs with the real extension (
.png,.mp4,.mp3,.json). - Use
$<step-id>.outputrather than repeating file paths. - Add a
budget:block for any pipeline that can call image/video providers. - Use
scene-buildfor storyboard projects andgenerate-*/edit-*for standalone media chains.
When converting a shell sequence, map each vibe ... command to one action and
turn downstream input paths into step references.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

