agentleFS
Sign inStart free
davidmosiahdavidmosiah/short-video-agent-kit/llms.txt

short-video-agent-kit

llms.txt3 starsChanged 6 months agoMITView on GitHub

Agent-first short-form AI video generation CLI and MCP server. One unified interface for OpenAI Sora, Google Gemini Veo, xAI Grok, and Seedance/PiAPI. Repository: https://github.com/davidmosiah/short-video-agent-kit NPM: https://www.npmjs.com/package/short-video-agent-kit Docs: https://github.com/davidmosiah/short-video-agent-kit#readme Primary command: npm exec --yes --package=short-video-agent-kit -- short-video-agent-kit doctor MCP command: short-video-mcp Core tools: - short_video_agent_manifest — runtime contract, tool list, supported clients - short_video_connection_status — provider availability, API keys present, dry-run mode - short_video_capabilities — per-provider feature matrix (resolution, duration, audio) - short_video_privacy_audit — what is logged locally vs sent to…

  • Reads credentials

The file

We split this llms.txt into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Call short_video_connection_status to see which providers are available.

    line 30
  2. Distinctive:

    Use short_video_capabilities to pick the right provider for the request (duration, resolution, audio).

    line 31
  3. Distinctive:

    Call short_video_generate with explicit live=true to actually spend credits.

    line 34
  4. Distinctive:

    Not affiliated with or endorsed by OpenAI, Google, xAI, or PiAPI.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# Short Video Agent Kit

Agent-first short-form AI video generation CLI and MCP server. One unified interface for OpenAI Sora, Google Gemini Veo, xAI Grok, and Seedance/PiAPI.

Repository: https://github.com/davidmosiah/short-video-agent-kit
NPM: https://www.npmjs.com/package/short-video-agent-kit
Docs: https://github.com/davidmosiah/short-video-agent-kit#readme
Primary command: npm exec --yes --package=short-video-agent-kit -- short-video-agent-kit doctor
MCP command: short-video-mcp

Core tools:
- short_video_agent_manifest — runtime contract, tool list, supported clients
- short_video_connection_status — provider availability, API keys present, dry-run mode
- short_video_capabilities — per-provider feature matrix (resolution, duration, audio)
- short_video_privacy_audit — what is logged locally vs sent to providers
- short_video_build_payload — turn a natural-language brief into a provider-ready request
- short_video_generate — submit a generation job to the chosen provider
- short_video_list_jobs — list recent generation jobs and their status
- short_video_get_job — fetch a single job (poll until done, get download URL)

Provider env vars (set the ones you have, others are skipped):
- OPENAI_API_KEY — for Sora
- GOOGLE_API_KEY — for Gemini Veo
- XAI_API_KEY — for xAI Grok video
- PIAPI_API_KEY — for Seedance via PiAPI
- SHORT_VIDEO_DRY_RUN=true — default; set to false (or pass live=true) to spend credits
- SHORT_VIDEO_DEFAULT_PROVIDER — sora|veo|grok|seedance, optional

Workflow for agents:
1. Call short_video_connection_status to see which providers are available.
2. Use short_video_capabilities to pick the right provider for the request (duration, resolution, audio).
3. Build the payload with short_video_build_payload (deterministic, no LLM call).
4. Confirm the brief + estimated cost with the user.
5. Call short_video_generate with explicit live=true to actually spend credits.
6. Poll short_video_get_job until the video URL is ready.

Safety:
- API keys stored locally, never returned in tool output.
- Dry-run on by default; paid generation requires live=true or SHORT_VIDEO_DRY_RUN=false.
- Cost estimates surfaced before submission so agents can warn the user.
- Generated videos default to containsSyntheticMedia disclosure when posted downstream.
- Not affiliated with or endorsed by OpenAI, Google, xAI, or PiAPI.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free