Loading...
Loading...
Found 12 Skills
Step-by-step guide for adding support for a new LLM in Dust. Use when adding a new model, or updating a previous one.
Provides comprehensive guidance for Stable Diffusion AI image generation including model usage, prompt engineering, parameters, and image generation. Use when the user asks about Stable Diffusion, needs to generate AI images, configure models, or work with Stable Diffusion.
Model configuration editor for ~/.pi/agent/models.json with multi-protocol curl testing support.
Manages AI SDK model configurations - updates packages, identifies missing models, adds new models with research, and updates documentation
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
Switch or repair the model configuration of an OpenClaw instance (e.g. Kimi k2p6 → k3): change the default model, add model definitions, and fix model-config failures — 401 "Invalid token", "No available channel / model not found", thinking-level rejections ("Thinking level X is not supported"), and config edits that don't take effect. Use whenever the user wants to switch/upgrade/rollback the OpenClaw model (切换模型/换模型/ 升级模型), or says the OpenClaw/龙虾 bot's model is misconfigured (模型配的错了), or the bot falls back / errors on LLM calls.
Configure LM Studio as embedding provider for GrepAI. Use this skill for local embeddings with a GUI interface.
Mandatory protocol for dispatching any built-in and custom agent in this project via the task tool. Use this skill EVERY TIME you are about to call the task tool with a custom agent_type. This skill ensures the agent's intended model (declared in its YAML frontmatter) is respected rather than overridden by a default. Also encodes prompting best practices for subagent context and quality. ALWAYS invoke before any task tool call that targets a custom agent — even if the agent name seems obvious.
Manage SAP AI Core lifecycle resources: scenarios, executables, configurations, and deployments. WHEN: user wants to list or inspect scenarios or executables, create or list configurations, create or list or stop or delete or patch deployments, get deployment logs, or remove duplicate LLM deployments. DO NOT USE FOR: listing foundation models or getting inference examples — use `genai-hub-foundation-models`; managing resource groups, secrets, or GitOps resources — use `aicore-admin-resources`.
Analyze video content using visual/video large models. This tool is triggered when the user uses phrases like "analyze video", "video understanding", "look at this video", or "analyze video".
Register a custom or variant model (e.g. an OpenRouter ":nitro" / ":floor" / ":exacto" slug) in the Pi Agent so it can be set as the global default. Use when Pi silently falls back to a different model (e.g. moonshotai/kimi-k2.6) after setting defaultModel, or when a model slug isn't in Pi's bundled list. Triggers on "Pi reset my model", "Pi won't use this model", "add a model to Pi", "Pi default keeps reverting".
Resolves which model a subagent runs on from three tiers (cheap, standard, strong), listed in the user's ~/.agents/model-tiers.md and matched to what the current harness offers. Use when a skill says to spawn a subagent on a tier, when choosing models for reviewers or verifiers, or when the user asks to set up or change model tiers.