llm-application-dev-prompt-optimize
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-06 00:14
Agents & models
25,709 results
prompt-engineering
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies,…
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts,…
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use…
skill-creator
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 Claude's…
voice-agents
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis,…
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work…
scrivener-sync
When the user wants to edit a Scrivener Draft as plain text in an external folder and re-sync the changes back — the agent-native round-trip that avoids RTF…
handoff
Produce a self-contained context payload that lets a fresh agent continue without re-deriving what this session established. Use for cross-boundary transfer…
task-splitting
Split large tasks into smaller subtasks. Use when a task spans many modules or requires phased implementation.
agent-loop-skill
Build and run long-running AI agent workflows for Codex, Claude Code, Cursor, and other coding agents with contracts, disk-backed state, role separation,…
creating-skills
Create custom agent capabilities when discovering novel tools, receiving task-agnostic tips from reviewers, or after researching specialized workflows not…
agentic-workflows
Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
analyze-sessions
Analyzes your local Copilot CLI sessions for dotnet/maui to drive iterative improvements to the PR-review agent (and other agents, skills, and instruction…
update-os-coverage
Update OS version references in Helix queue definitions to add new versions, replace EOL versions, or audit coverage against the supported-os matrix. USE FOR:…
picking-models
Picks which model runs a subagent, workflow step, or agent team member by classifying the task's role, then taking the cheapest model that clears that role's…
skill-writing
Writes and improves agent skills to meet the Agent Skills open standard (agentskills.io). Use when creating a new skill from scratch, revising an existing one…
vet-skill-idea
Evaluates whether an idea should become an agent skill, checking it against worthiness criteria and routing it to build, split, redirect, or drop. Use when…
writing-skills
Knowledge for writing agent skills — the tenets, design axes, and craft of a SKILL.md, plus a spec validator. Use it before creating a new skill or revising an…
copilot-sdk
Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing…
notion-archive-container-mcp
Use this skill when working with the Notion Dev Containers MCP server. Covers container-based Notion data archiving, database operations, page management, and…
notion-custom-mcp
Use this skill when interacting with the NotionCustomMCP server. Covers all available tools, database operations, page management, block manipulation, and best…
ask-user-question
Make the agent ask the user to choose between options through its structured question tool (Claude Code's AskUserQuestion or an equivalent) instead of a text…
do.agent
Detect agent CLIs installed on this machine (omp, claude, gemini, codex), let the user pick one for DeepOrbit to hand execution to, and show the current…