OverviewHistoryStatsSecurity
npx skills add ...
Documentation
SKILL.md
npx skills add belt-sh/cli --skill belt
Use the belt CLI — run 250+ AI apps, manage knowledge, search skills, connect MCP servers. Purpose-built CLI interface for agent workflows — typed inputs, schema validation, no raw API calls needed.
npx skills add belt-sh/cli --skill belt
belt is the cloud platform cli for ai agents. single ~4mb binary, no runtime dependencies.
using a purpose-built cli means your agent operates through a constrained, typed interface instead of writing raw curl commands or sdk calls. every operation goes through schema validation — fewer tokens, fewer errors, and no credential leakage.
first check if belt is already installed:
if already installed, skip to authenticate.
package managers (recommended — verified through each registry's trust chain):
manual install (full control — download, verify, then run):
the installer is a short, readable shell script. it detects your os and architecture, downloads the matching binary from dist.inference.sh, verifies the binary's sha-256 checksum against the published manifest, and places it in your path. no elevated permissions required. the installer source is publicly readable — review it before running:
image and video generation:
file fields (type: file in schema) accept local paths directly — the cli auto-uploads them:
check pricing before running:
multi-function apps (e.g. apps with list_voices, list_resources, etc.):
knowledge and skills:
mcp connectors:
machine-readable output:
all list commands support --json for structured output:
belt app sample generates ready-to-edit input json from the app schema./your-file.jpg in samples — just replace with your actual file pathbelt suggest searches apps, skills, and knowledge in one callbelt task cost <task-id> shows actual cost after a runbelt app run --no-wait submits without blocking, belt task get <id> to check later--session new for stateful apps that keep gpu warm between callsor set BELT_NO_HOOKS=1 in your environment.
curl -fsSL https://cli.inference.sh -o /tmp/belt-install.shcat /tmp/belt-install.sh # review the script
sh /tmp/belt-install.sh # run after reviewbelt login
belt mebelt plugin init claude # claude code
belt plugin init codex # openai codex
belt plugin init cursor # cursorbelt suggest "what tool should i use" # unified search across apps, skills, knowledge
belt app store # browse ai apps
belt app store --category video # filter by category
belt app get <namespace/name> # see schema, pricing, functions
belt app sample <namespace/name> # generate sample input json
belt app run <namespace/name> --input input.json # run an app
belt balance # check creditsbelt app get bytedance/seedance-2-0 # check schema — file fields accept local paths
belt app sample bytedance/seedance-2-0 --save input.json
# edit input.json, then:
belt app run bytedance/seedance-2-0 --input input.jsonbelt app run bytedance/seedance-2-0 --input '{"image": "./photo.jpg", "prompt": "make it cinematic"}'belt app pricing <namespace/name> # see cost formula
belt app pricing <namespace/name> --json # machine-readablebelt app get heygen/avatar-video # shows all functions with schemas
belt app sample heygen/avatar-video -f list_resources # sample for a specific function
belt app run heygen/avatar-video -f list_resources --input '{}'belt knowledge list --json # your knowledge entries
belt knowledge search "react patterns" # semantic search
belt skill list # your skills
belt skill store search "video" # find skills in the store
belt skill use <namespace/name> # load a skill on-demandbelt mcp list # browse available connectors
belt mcp connect slack # connect one
belt mcp run slack send_message --input '{"channel": "#general", "text": "hello"}'belt app list --json
belt app store --json
belt task list --json
belt knowledge list --json
belt skill list --json
belt mcp list --json
belt secrets list --json
belt me --json
belt balance --json# .beltsh/config.json
{"hooks_disabled": true}