Choose an available model and give it the source text and output instructions for a complete response.
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Pull the main findings and unresolved questions from text you provide.
/oo Anthropic: Use an available Anthropic model [model preference] to summarize this report: [text]. Give the main findings, evidence stated in the text, and unresolved questions. Keep the response under [word limit] words.
Count input tokens for the messages and model you plan to use.
/oo Anthropic: Count input tokens for Anthropic model [model] with these messages [messages] and system instructions [instructions]. Report the input count before making any generation request.
Rewrite supplied text while preserving its facts and commitments.
/oo Anthropic: Use Anthropic model [model ID] to rewrite this customer message in a calm, concise tone: [message]. Preserve names, dates, and commitments; do not add claims.
Identify concrete differences before choosing a plan.
/oo Anthropic: Use Anthropic model [model ID] to compare these two proposals: [proposal A] and [proposal B]. List differences in scope, stated dates, costs, and open questions. Treat anything absent as unspecified.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →Connect an Anthropic API key.
Connect Anthropic →Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
This connection lists model metadata, creates non-streaming messages, and counts message input tokens. Your request defines the source material and desired output.
Generate complete model responses and count request input tokens.
List accessible models and inspect a selected model’s metadata.
List Anthropic models available to the current API key.
Leina 
Wanta 
anthropic.list_models Fetch metadata for one Anthropic model.
anthropic.get_model Create a non-streaming Anthropic message.
anthropic.create_message Count input tokens for an Anthropic message request.
anthropic.count_message_tokens No matching tools.
Provide the document text as input, or use a separate authorized app connection to retrieve it. This Anthropic connection processes the messages you supply rather than independently browsing your workspace.
No. It measures the request input for a selected model. The response length depends on generation and the output limit you set.
No. Message actions return a complete non-streaming response.
Manage which optional storage OOMOL can use. You can change these choices from the footer at any time.