All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 302,729
- 12,614
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse ai & agents skills
Showing 1,033–1,056 of 302,729 skills
- 2046 Image Processor 8ffed74dThis guide provides a comprehensive, code-validated overview of the `ImageProcessor` node for WilmerAI. It details the node's precise execution logic, properties, and best practices to enable developers and AI agents to author effective image-aware workflows.Votes: 0GitHub stars: 9
- 2045 Prompt Injection Defender 3142b4e4Expert in detecting and preventing prompt injection attacksVotes: 0GitHub stars: 9
- 2043 Rag Architect Ab3efd9eExpert in RAG system design, chunking strategies, and retrieval optimizationVotes: 0GitHub stars: 9
- 2042 Routing B62af615The routing configuration files, located in `Public/Configs/Routing/`, define how WilmerAI directs incoming user prompts to different processing workflows. Each JSON file maps prompt categories (e.g., "Coding", "Factual") to a specific workflow file. When a request is received and the `customWorkflowOverride` setting in the user's configuration is `false`, the system first runs a "categorization workflow." This initial workflow uses an LLM to analyze the request and assign it to one of the ca...Votes: 0GitHub stars: 9
- 2042 Model Selector 6ce69d5dHelps select the optimal LLM model for specific tasks and requirementsVotes: 0GitHub stars: 9
- 2041 Sillytavern 252c7120> NOTE: This is very outdated. I've consolidated all the info I had before, but I haven't really messed with > a newer version of ST than what came out in summer of 2024 except very briefly, so I need to actually download > the thing and see what the new UI looks like. This is old.Votes: 0GitHub stars: 9
- 2040 Prompt Optimizer 0f9c9a88Optimizes prompts for cost, latency, and quality trade-offsVotes: 0GitHub stars: 9
- 2039 Adaptable Llm Backend Apis 651d6bc3*Note: WilmerAI exposes a **Universal API Gateway** that allows you to connect your existing applications as if you were talking directly to OpenAI or Ollama. This document explains the backend mechanism for connecting to and orchestrating various Large Language Models.* WilmerAI can act as a **bridge** to most Large Language Model (LLM) backends. You are not locked into a single provider or API. Whether you're running a model locally with Ollama, using a cloud service like OpenAI, or a custo...Votes: 0GitHub stars: 9
- 2036 Errors E7102531| Error | Cause | Solution | |-------|-------|----------| | Inconsistent AI suggestions | Missing or vague .cursorrules | Add detailed rules and examples | | Team configuration drift | No shared settings | Commit .vscode/settings.json | | Monorepo confusion | No workspace structure | Set up .cursorrules inheritance | | Poor indexing results | Wrong .cursorignore | Review and update exclusions |Votes: 0GitHub stars: 9
- 2035 Skillfull C4a95919Manages Firebase/Firestore operations including CRUD, queries, batch processing, A2A agent communication, MCP server integration, and Cloud Run service coordination. Activates when you request "firestore operations", "create firestore document", "... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.Votes: 0GitHub stars: 9
- 2033 Readme Mcp Tools 031f87efThis module provides integration with MCP (Model Context Protocol) services for Wilmer's AI system. It allows LLMs to automatically discover and invoke tools from MCP servers mentioned in the system prompt.Votes: 0GitHub stars: 9
- 199 Debugging D59da319You are debugging a crash or warning in the linux kernel. You were given a crash message, oops, warning, or stack trace either in a file or in stdin. Read and execute `kernel/agent/debug.md`. It is a multi-agent orchestrator that will dispatch specialized agents (code analysis, reproducer analysis, commit search) to investigate the bug. Pass through all input (crash reports, reproducers, syzbot URLs, etc.) to the orchestrator unchanged.Votes: 0GitHub stars: 9
- 1958 Cursor Api Key Management 01263564``` cursor-api-key-management/ SKILL.md ```Votes: 0GitHub stars: 9
- 1905 Geepers Canary E1900647Early warning system that spot-checks fragile and critical systems. Like a canary in a coal mine - quick checks on the things most likely to break. Use for health checks, pre-deployment verification, or periodic monitoring of critical paths.\n\n<example>\nContext: Before deployment\nuser: "Is everything still working?"\nassistant: "Let me run geepers_canary for a quick health check."\n</example>\n\n<example>\nContext: Something feels off\nuser: "The site seems slow today"\nassistant: "I'll us...Votes: 0GitHub stars: 9
- 1683 Credits F79ab7deCreated by [Jag Valaiyapathy](https://github.com/Jaganpro)Votes: 0GitHub stars: 9
- 1683 Credits 7d3b11daCreated by [Jag Valaiyapathy](https://github.com/Jaganpro)Votes: 0GitHub stars: 9
- 1683 Credits 14997fbcCreated by [Jag Valaiyapathy](https://github.com/Jaganpro)Votes: 0GitHub stars: 9
- 1683 Credits 0a40a282Created by [Jag Valaiyapathy](https://github.com/Jaganpro)Votes: 0GitHub stars: 9
- 1662 Openrouter Integration Fa472637The LLM CLI Skill now includes **OpenRouter support**, providing unified access to 200+ LLM models from multiple providers through a single API.Votes: 0GitHub stars: 9
- 1661 Files 3b13204a**Your entry point!** Quick 5-minute overview with examples and troubleshooting. - Quick setup instructions - Common tasks - Model recommendations - File support list - Pro tipsVotes: 0GitHub stars: 9
- 1657 2026 02 07 Fix X Search Query Construction Plan D96c458e`/last30days vibe motion best prompt techniques` returned **0 X posts** despite Vibe Motion being actively discussed on X (screenshots show posts from @Godid242, @KamilStanuch, @ColdStartTheory, @higgsfield_ai).Votes: 0GitHub stars: 9
- 1655 Pr Credits F24ddc2dWhen V2 is pushed to the public repo, comment on each PR to thank the contributor and let them know their work was integrated.Votes: 0GitHub stars: 9
- 1645 Groq 41149c40https://groq.com/ :::tip **We support ALL Groq models, just set `model=groq/<any-model-on-groq>` as a prefix when sending litellm requests** :::Votes: 0GitHub stars: 9
- 1640 Tool Calling 7e3e5988vllm-mlx supports OpenAI-compatible tool calling (function calling) with automatic parsing for many popular model families.Votes: 0GitHub stars: 9