Working memory protocol for multi-step tasks. Use the scratchpad to record intermediate findings without bloating LLM context.
Langue du texte source : anglais
Menu
SkillsMP a collecté 12 skills depuis misunders2d/ori. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 12 skills collectés sur 12.
Working memory protocol for multi-step tasks. Use the scratchpad to record intermediate findings without bloating LLM context.
Langue du texte source : anglais
How to schedule one-off and recurring agent tasks, route their delivery to specific Slack/Telegram channels, and use plan enforcement reliably. Load this any time the user asks to remind, schedule, automate, or run something on a cron.
Langue du texte source : anglais
How to add, list, or remove API keys and OAuth integrations through the chat. Load this when the user asks to add/set/configure/connect a key, token, credential, or third-party service (Slack, Telegram, OpenRouter, Anthropic, Google, GitHub, ClickUp, …).
Langue du texte source : anglais
Model string conventions for set_agent_model — how to format names for Gemini, Claude, OpenRouter, and other providers. Load this any time the user asks to change, swap, set, switch, route, or test a model — to avoid building the wrong model string.
Langue du texte source : anglais
How to handle privileged tool calls that require explicit admin approval (ACT-XXXXXX tokens, optional TOTP 2FA). Load this when a tool returns an action token or when the user replies 'Approve ACT-...'.
Langue du texte source : anglais
The mandatory step-by-step procedure for self-evolution: how to plan, stage, verify, and commit code changes. Different paths for parent (native) vs child (Docker sandbox). Load this any time you're about to modify code.
Langue du texte source : anglais
Reference for the A2A v1.0 protocol (Agent-to-Agent). Covers agent discovery, communication with friends and arbitrary agents, and DNA exchange via the Ori-Net.
Langue du texte source : anglais
How to spawn disposable child agents in Docker for sandboxed work — iteration, testing, evolution from a clean slate. Children stage and export DNA back; they cannot commit or reboot. Load this when the user asks to test, sandbox, isolate, spawn, or…
Langue du texte source : anglais
Step-by-step procedure for exporting and importing DNA (tools/skills) between Ori agents over native A2A binary content. DNA exchange is a communication event — never commit or reboot during a transfer.
Langue du texte source : anglais
Reference material for the Google Advanced Agentic Development Kit (ADK). Use this when tasked with building new Agents, managing state memory, orchestrating sequential/parallel behaviors, or modifying Python integrations/tools in the root `app/` structure.
Langue du texte source : anglais
Forces the agent to actively research official documentation, GitHub issues, and installed package versions before implementing new features OR debugging failures.
Langue du texte source : anglais
A metacognitive workflow to create or modify skills in a Rootless environment. Use this when adding a new integration, capability, or domain-specific knowledge.
Langue du texte source : anglais