Turn messages, meeting notes, and documents into sourced decisions, actions, dependencies, and risks
odysseus-dev/odysseus
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 14
- GitHub stars
- 93,630
- GitHub forks
- 1,615
Loading the repository README…
Skills in this repository
Showing 14 of 14 collected skills.
Reconcile source evidence and prepare an accurate external-facing draft without bypassing review
Coordinate availability, confirmations, calendar changes, and participant notifications with read-back verification
Create requested artifacts early, iterate from concrete output, and verify final deliverables
Recover from failed terminal commands using evidence-driven diagnosis and bounded retries
Discover the smallest capable tool set and confirm argument schemas before acting
Make scoped state changes with target confirmation, minimal mutation, and read-back verification
Prioritize support requests, identify owners, route internally, and prepare safe customer drafts
Find, read, and apply authoritative developer documentation during implementation
Build or fix software with a focused red-green-refactor loop
Extract and verify evidence from images, documents, and video without redundant inspection
Research current web information with source-first search and controlled browser fallback
Use when the user asks Claude Code to read or write Odysseus data (todos, email, calendar, memory, documents) or to launch/monitor/stop a Cookbook model-serve task through the scoped Claude Agent API. Requires ODYSSEUS_URL and ODYSSEUS_API_TOKEN.
Use when the user asks Codex to read or write Odysseus data (todos, email, calendar, memory, documents) or to launch/monitor/stop a Cookbook model-serve task through the scoped Codex Agent API. Requires ODYSSEUS_URL and ODYSSEUS_API_TOKEN.
Install with an AI assistant
Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/odysseus-dev/odysseus.