AI & Agent Engineering

102 skills across 8 categories.

Agent frameworks & orchestration (23)

• acp-routerRoute plain-language requests for Pi, Claude Code, Codex, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, irisk: lowFree
• agent-creditBorrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, healthrisk: mediumFree
• agent-customization**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agentrisk: mediumFree
• agent-sessions-layoutAgents workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar risk: lowFree
• agentic-engineeringOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when AI agents performrisk: mediumFree
• alfworld-appliance-navigatorNavigates the agent to a target appliance (microwave, stove, fridge, or sinkbasin) needed for object processing. Use when you are risk: lowFree
• chatgpt-app-builderDEPRECATED: This skill has been replaced by `mcp-app-builder`. Check if `mcp-app-builder` is available in the skills folder. If norisk: lowFree
• claude-codeDelegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative corisk: highFree
• coding-agentDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or risk: mediumFree
• configured-agentThis skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".risk: lowFree
• councilConvene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex probrisk: lowFree
• councilConvene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you nrisk: lowFree
• Create PlanCreate a concise plan. Use when a user explicitly asks for a plan related to a coding task.risk: mediumFree
• create-agentCreate a custom agent (.agent.md) for a specific job.risk: lowFree
• create-hookCreate a hook (.json) to enforce policy or automate agent lifecycle events.risk: lowFree
• eliza-app-developmentUse when building or changing an elizaOS-based application in this repository. Covers eliza app architecture, monorepo layout, locrisk: lowFree
• executing-plansUse when you have a written implementation plan to execute in a separate session with review checkpointsrisk: lowFree
• hook-developmentThis skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "irisk: mediumFree
• llm-app-patternsProduction-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best risk: lowFree
• opencodeDelegate coding tasks to OpenCode CLI agent for feature implementation, refactoring, PR review, and long-running autonomous sessiorisk: lowFree
• subagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionrisk: lowFree
• subagent-driven-developmentUse when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (sperisk: lowFree
• ts-agent-sdkGenerate typed TypeScript SDKs for AI agents to interact with web applications via MCP servers.risk: lowFree

Evaluation & quality (4)

• advanced-evaluationThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mrisk: lowFree
• healthcare-eval-harnessPatient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, crisk: mediumFree
• hugging-face-trackioTrack ML experiments with Trackio using Python logging, alerts, and CLI metric retrieval.risk: lowFree
• target-novelty-scorerScore the novelty of biological targets through literature mining and.risk: mediumFree

Local & model ops (15)

• ai-multimodalProcess and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timerisk: lowFree
• aoti-debugDebug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant loading failurrisk: lowFree
• computer-vision-expertSOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatirisk: lowFree
• cost-aware-llm-pipelineCost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.risk: lowFree
• cv-classificationBest practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.risk: lowFree
• foundation-models-on-deviceApple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshorisk: lowFree
• geminiGemini CLI for one-shot Q&A, summaries, and generation.risk: lowFree
• geminiExecute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex rrisk: lowFree
• gguf-quantizationGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silirisk: lowFree
• gpt5-consultantUse this skill when stuck in circular debugging, when solutions aren't working despite multiple attempts, or when the user expressrisk: lowFree
• huggingface-hubHugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy infererisk: lowFree
• local-llm-expertMaster local LLM inference, model selection, VRAM optimization, and local deployment using Ollama, llama.cpp, vLLM, and LM Studio.risk: lowFree
• migrate-oai-appThis skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.operisk: lowFree
• mlops-engineerBuild comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.risk: mediumFree
• model-usageUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or arisk: lowFree

MCP & tool integration (7)

• blender-mcpControl Blender directly from Hermes via socket connection to the blender-mcp addon. Create 3D objects, materials, animations, andrisk: lowFree
• fastmcpBuild, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API risk: lowFree
• helium-mcpConnect to Helium's MCP server for news research, media bias analysis, balanced perspectives, stock/options data, and semantic memrisk: lowFree
• hugging-face-tool-builderYour purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining, pirisk: lowFree
• mcp-integrationThis skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "serisk: mediumFree
• mcporterUse the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, confrisk: lowFree
• tool-designThis skill should be used when the user asks to "design agent tools", "create tool descriptions", "reduce tool complexity", "implerisk: lowFree

Memory & context (11)

• agent-memory"Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'norisk: lowFree
• compound-learningsTransform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from serisk: lowFree
• context-management-context-restoreUse when working with context management context restorerisk: lowFree
• continuous-learningAutomatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.risk: lowFree
• continuous-learning-v2Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves therisk: lowFree
• mem0-cliMem0 CLI — the command-line interface for mem0 memory operations. TRIGGER when: user mentions "mem0 cli", "mem0 command line", "@risk: lowFree
• memoryTwo-layer memory system with Dream-managed knowledge files.risk: lowFree
• reasoningbank-intelligence"Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use whrisk: mediumFree
• session-logsSearch and analyze your own session logs (older/parent conversations) using jq.risk: lowFree
• strategic-compactSuggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compactrisk: lowFree
• writer-memoryAgentic memory system for writers – track characters, relationships, scenes, and themesrisk: lowFree

Model training & fine-tuning (10)

• axolotlExpert guidance for fine-tuning LLMs with Axolotl – YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal supportrisk: lowFree
• distillStrip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean. Use when the user risk: lowFree
• fine-tuning-with-trlFine-tune LLMs using reinforcement learning with TRL – SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for rewarisk: lowFree
• grpo-rl-trainingExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model trainingrisk: lowFree
• hugging-face-trackioTrack and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analrisk: lowFree
• ml-engineerBuild production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering,risk: mediumFree
• peft-fine-tuningParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limitrisk: lowFree
• pytorch-fsdpExpert guidance for Fully Sharded Data Parallel training with PyTorch FSDP – parameter sharding, mixed precision, CPU offloading, risk: lowFree
• pytorch-patternsPyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model archirisk: lowFree
• unslothExpert guidance for fast fine-tuning with Unsloth – 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimizationrisk: lowFree

RAG & retrieval (5)

• embedding-strategiesSelect and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chrisk: lowFree
• Hybrid Search ImplementationCombine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neitrisk: lowFree
• search-firstResearch-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Systematizes the "risk: lowFree
• search-firstResearch-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researrisk: lowFree
• tavilyTavily web search, content extraction, and research tools.risk: lowFree

Skill & prompt authoring (27)

• add-expertAdd a new expert to the Remotion experts pagerisk: lowFree
• ask-questions-if-underspecifiedClarify requirements before implementing. Use when serious doubts arise.risk: lowFree
• command-developmentThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define commarisk: highFree
• create-instructionsCreate an instructions file (.instructions.md) for a project rule or convention.risk: lowFree
• create-promptCreate a reusable prompt file (.prompt.md) for a common task.risk: lowFree
• create-skill-fileGuides Claude in creating well-structured SKILL.md files following best practices. Provides clear guidelines for naming, structurerisk: mediumFree
• everything-claude-code-conventionsDevelopment conventions and patterns for everything-claude-code. JavaScript project with conventional commits.risk: lowFree
• example-skillThis skill should be used when the user asks to "demonstrate skills", "show skill format", "create a skill template", or discussesrisk: lowFree
• getting-started-with-abilitiesDescribes how to use abilities. Read before any conversation.risk: lowFree
• good-skillThis is a properly formatted skill.risk: lowFree
• guidelines-advisorSmart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specificatirisk: mediumFree
• llm-prompt-optimizerUse when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinationrisk: lowFree
• minimal-skillA minimal skill with no resourcesrisk: lowFree
• prompt-improverThis skill enriches vague prompts with targeted research and clarification before execution. Should be used when a prompt is deterrisk: lowFree
• prompt-lookupActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use risk: lowFree
• rules-distillScan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule filesrisk: lowFree
• Skill ShareA skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skillrisk: lowFree
• Skill WriterGuide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skillrisk: lowFree
• skill-builder"Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organizationrisk: mediumFree
• skill-creatorThe definitive skill-authoring meta-skill: what skills are, core principles (concise, right degrees of freedom), skill anatomy, prrisk: lowPremium
• skill-creatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill)risk: lowFree
• skill-creatorCreate, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, trisk: mediumFree
• skill-developmentThis skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill derisk: lowFree
• skill-installerInstall Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable srisk: mediumFree
• skill-lookupSearch, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, risk: lowFree
• update-skillsCreate or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "risk: lowFree
• writing-skillsUse when creating new skills, editing existing skills, or verifying skills work before deploymentrisk: mediumFree