数据分析

Replicate

试用

Replicate (replicate.com). Use this skill for ANY Replicate request — reading, creating, and updating data. Whenever a task involves Replicate, use this skil...

它能做什么

Replicate (replicate.com). Use this skill for ANY Replicate request — reading, creating, and updating data. Whenever a task involves Replicate, use this skill instead of calling the API directly.

技能文档

Replicate

Operate Replicate through your OOMOL-connected account. This skill calls the replicate connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Replicate. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "replicate" --action ""

2. Run the action with a JSON payload that matches the input schema:

oo connector run "replicate" --action "" --data '' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action is listed below with a one-line description; actions that change state carry a [write] or [destructive] tag. Before constructing --data, fetch the action's live schema with oo connector schema to get its authoritative input fields.

Available actions

  • cancel_prediction — Cancel a running Replicate prediction by prediction ID. [write]
  • create_prediction — Create a Replicate prediction using JSON model input and optional synchronous wait headers. [write]
  • get_account — Retrieve the authenticated Replicate account for the connected API token.
  • get_collection — Retrieve one Replicate collection by slug.
  • get_model — Retrieve one Replicate model by owner and model slug.
  • get_model_version — Retrieve one Replicate model version by owner, model, and version ID.
  • get_prediction — Retrieve the current state and output of a Replicate prediction.
  • list_collections — List public Replicate model collections.
  • list_model_versions — List versions for one Replicate model.
  • list_models — List public Replicate models with optional official sorting parameters.
  • list_predictions — List Replicate predictions for the authenticated account.

Safety

  • Untagged actions are reads (get / list / search) — safe to run directly.
  • Actions tagged [write] change Replicate state — confirm the exact payload and effect with the user before running.
  • Actions tagged [destructive] remove or overwrite data — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: ):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — Replicate is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:

    https://console.oomol.com/app-connections?provider=replicate
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

相关技能

Reply.io (reply.io). Use this skill for ANY Reply.io request — reading, creating, and updating data. Whenever a task involves Reply.io, use this skill instea...

ScraperAPI (scraperapi.com). Use this skill for ANY ScraperAPI request — reading, creating, and updating data. Whenever a task involves ScraperAPI, use this...

1 次安装

Instantly.ai (instantly.ai). Use this skill for ANY Instantly.ai request — reading, creating, and updating data. Whenever a task involves Instantly.ai, use t...

3 次安装

Resend (resend.com). Use this skill for ANY Resend request — reading, creating, and updating data. Whenever a task involves Resend, use this skill instead of calling the API directly.

7 次安装

Retell AI (retellai.com). Use this skill for ANY Retell AI request — searching and reading data. Whenever a task involves Retell AI, use this skill instead o...

3 次安装

Respond.io (respond.io). Use this skill for ANY Respond.io request — reading, creating, updating, and deleting data. Whenever a task involves Respond.io, use this skill instead of calling the API directly.

1 次安装