video-workbench
Skill0 starsChanged 3 months agoMITView on GitHub
Engineer repository-backed media processing workbenches across ingestion, job state, processing, review, export, frontend states, QA evidence, and deployment configuration. Use when building or changing a video or audio workflow application rather than analyzing media content.
In this repository5 other files it gives its agents.
- code-intelligenceSkill
- engineering-deliverySkill
- engineeringSkill
- skill-security-auditSkill
- supabase-operationsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
If codecs, accelerators, cloud storage, or deployment credentials are unavailable, use declared fixtures or mocks and state what remains …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Video Workbench
This TIKAZ Edition is designed, integrated, independently refactored, and continuously maintained by TIKAZ. Treat it as a reusable media-application engineering workflow, not a dependency of video-platform-reader.
Inputs and workflow
Accept a media application repository, the requested user flow or pipeline change, representative media fixtures, deployment target, and acceptance criteria. Read repository instructions and map ingestion, queued/running/failed/completed job states, processing stages, review, export, storage, and retry behavior before editing.
Implement in small slices. Keep frontend state and backend job state consistent, preserve media provenance, and verify at least one representative job plus desktop/mobile states when a UI is involved.
Output contract
Return the changed pipeline or interface, state transition map, representative job evidence, failure and retry behavior, test/build results, deployment notes, and remaining media-format risks.
Validation and fallback
If codecs, accelerators, cloud storage, or deployment credentials are unavailable, use declared fixtures or mocks and state what remains unverified. Do not claim export compatibility without inspecting the resulting artifact.
Example and limits
Use video-workbench to add retryable export jobs to this media app, keep UI and worker states aligned, and verify one representative file end to end.This Skill engineers applications; it does not acquire unauthorized media, bypass DRM, or replace evidence-based content analysis.
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.