ffmpeg-skill
by kajisho5
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FFMPEG_SKILL_HW | No | Set to 1 to make Apple VideoToolbox hardware encoding the default on this machine for every re-encoding tool except `export.py`'s delivery presets. | |
| FFMPEG_SKILL_TIMEOUT | No | Per-ffmpeg-call timeout in seconds (default 1800; 0 means no limit). Past the limit the process is killed, its partial output removed and the failure reported as `kind: timeout`. | |
| FFMPEG_SKILL_MCP_FULL | No | Set to 1 to list all 42 tools in `tools/list` instead of just the core 12 (default: only the core 12 are advertised; every tool is callable through `tools/call` either way). | |
| FFMPEG_SKILL_ASR_MODEL | No | Sets this machine's default ASR model for `--transcribe` (e.g. `large-v3-turbo`); without it, `base` is used. | |
| FFMPEG_SKILL_ASR_ENGINE | No | Sets this machine's default speech engine for `--transcribe` (with `FFMPEG_SKILL_ASR_MODEL`); without it, the engine is auto-selected. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessUsually handled