adaptive-decision-interviews
Use when the user wants the agent to conduct a structured interview that elicits and preserves their judgement before a decision artefact is drafted. Do not…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
internal-tooling
Build reusable automation as first-class CLI subcommands instead of throwaway scripts. Use when an agent considers writing a script, automating repeated tasks,…
create-skill
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends your…
flow-nexus-neural
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
prometheus-configuration
Set up Prometheus for comprehensive metric collection, storage, and monitoring of infrastructure and applications. Use when implementing metrics collection,…
ts-agent-sdk
Generate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts verbose JSON-RPC curl commands to clean function calls…
systems-design-review-methodology
Use when the /systems-design-review mode is active. 7-step design review methodology -- understand the design, classify the system, evaluate against codebase,…
agentic-workflows
Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
fuzzing
Run, optimize, and debug OpenVMM fuzzers. Covers cargo-fuzz targets, crash reproduction, lldb debugging, code coverage analysis, entropy optimization, and…
bootstrap
Alias for the /promptkit skill. Use this when the user wants to assemble a task-specific prompt using PromptKit, or says "bootstrap" to start the PromptKit…
promptkit
PromptKit composition engine. Use this skill when the user wants to assemble a task-specific prompt, write a requirements doc, investigate a bug, review code,…
authoring-tips
Index of practical authoring tips and workarounds for Copilot Studio agents. When a request may need best-practice guidance, an authoring technique, or a…
patterns
Index of repeatable implementation patterns for Copilot Studio agents. When a request may need a best-practice architecture or reusable pattern for building an…
coverage-analysis
Project-wide code coverage and CRAP (Change Risk Anti-Patterns) score analysis for .NET projects. Calculates CRAP scores per method and surfaces risk hotspots…
follow-goal
Give the agent a durable objective with a verifiable stopping condition, then keep iterating across turns until that condition is met. Use when the user says…
developing-opencode-meta
Build OpenCode plugins, agents, hooks, and tools. Use when creating, reviewing, or debugging OpenCode extensions. Covers plugin architecture, agent…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
gemini-skill-creator
Generates high-quality, predictable, and efficient .agent/skills/ directories based on user requirements. Use whenever you need to create a new skill or modify…
trajectory-review
Review how an agent reached its result, not only whether the result passed, covering tools called, detours, unverified assumptions and wasted round trips, and…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
template-skill
Replace with description of the skill and when Claude should use it.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
mcp-typescript-sdk-skills
Serves and consumes Skills over MCP (SEP-2640, the `io.modelcontextprotocol/skills` extension) with v2 of the MCP TypeScript SDK: publishes a folder of…
korean-humanize
This is a Korean-specialized skill that precisely removes the "AI feel" from Korean text written by AI (ChatGPT, Claude, Gemini, etc.) and polishes it so it reads like human-written prose. Translationese (through/~in terms of/double passive), excessive English quotations, mechanical parallelism (first, second, third), AI-specific stock phrases (in conclusion/suggesting…