Expert-level skill for building production-ready AI agents and agentic systems using the Agno framework. Covers agent architecture, multi-agent teams, AgentOS deployment, tool integration, RAG patterns, and production best practices.
Use when the user asks to "write a prompt for DeepSeek", "compose a DeepSeek prompt", wants to send a task to a DeepSeek model, needs to launch a DeepSeek subagent. Also use when explicitly named: DeepSeek. Trigger on any request to draft, refine, or assemble a prompt targeting a DeepSeek-family model — for either…
A data-recovery skill that uses a local small language model and semantic grouping to detect and correct data problems automatically. A data pipeline is a process that moves and transforms data between systems.
Query and analyze data in a Tower-managed Apache Iceberg lakehouse using the Tower CLI's built-in read-only SQL query command (tower catalogs query), and record what you learn about the data with tower catalogs knowledge. Use this skill whenever the user asks a question about their company or business data (revenue…
Ingest data from array file formats into an Icechunk or Arraylake repository as a single Zarr datacube. Use this skill whenever the user mentions archival array or scientific file formats such as netCDF/HDF5/TIFF/GRIB/Zarr; cloud-optimized or ARCO (Analysis-Ready Cloud-Optimized) data; creating, converting or moving…
Generate a structured analytical Jupyter notebook from any dataset path. Produces EDA, statistical tests, visualizations, and optional modeling following notebook best practices.
A local-first memory and knowledge service that an AI client can access through MCP or HTTP. It stores long-term facts and preferences, indexes documents and web pages, and supports retrieval while offline.
Configure and maintain optimal OpenRouter free model failover for OpenClaw. Prioritized cascade of free models ranked by coding capability, with automatic failover on rate limits, downtime, and errors. Load this skill when configuring models, troubleshooting model availability, or refreshing the free model inventory.
A skill for writing and improving prompts for AI image-generation tools such as Gemini, Midjourney, Stable Diffusion, DALL-E, and Leonardo.ai. A prompt is the text that describes the image an AI should create.
Set up an accreta knowledge base over a corpus — pick a preset, write the config and a source declaration, generate the constitution, wire up MCP, and verify the first ingest. Use when someone wants an agent-maintained knowledge base with provenance and drift detection over a codebase, a document collection, or a…
★not rated 2▲
+1
changed 3d agoA100 tokens
originalMIT
Build, debug, and optimize The Agent API / Universal SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing The Agent API code between The Agent model versions. TRIGGER when: code imports google-generativeai/@google/generative-ai; user asks for the The Agent API, Universal…
Use when working with StrataDB / stratadb — an embedded multi-model database (key-value, JSON documents, vectors, events, graphs) with git-style branches and time travel. Covers opening databases from Python or the CLI, choosing a primitive, branch isolation, as-of reads, typed error handling, and built-in inference…
★not rated 2
changed 3d agoA76 tokens
originalApache-2.0
A local knowledge-base search tool that indexes folders and finds matching files or passages using text and meaning. RAG, or retrieval-augmented generation, is the practice of retrieving relevant source material before answering.
A guided workflow for planning and submitting AI-generated videos. It interviews you about the subject, action, setting, camera, sound, style, and restrictions before helping choose a model and platform.
A vision skill that sends images and screenshots to a visual analysis service. It adds image understanding to a model that otherwise works only with text.
A prompt-writing skill for creating, rewriting, classifying, or improving prompts for GPT-Image-2, an image-generation model. It includes style templates, prompting techniques, and guidance on avoiding common prompt problems.
Turn text into embedding vectors with Forge (Voxell's hosted embedding API) for semantic search, RAG retrieval, clustering, dedup, or similarity. Use when the user wants to embed text/documents/queries, build or query a vector index, find similar or duplicate text, or pick an embedding model and dimension. Provides…
★not rated 1 3mo agoA84 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: