performance-optimizer
Copilot agent that assists with performance analysis, bottleneck detection, optimization strategies, and benchmarking Trigger terms: performance optimization,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,653 results
buddy-reroll
Reroll your Claude Code buddy (companion) to get a specific species, rarity, or shiny variant. Use when the user says "reroll buddy", "change my buddy", "I…
orca
Spawn and manage parallel AI coding agents via tmux. Use when you need to orchestrate workers, delegate sub-tasks, run multi-agent improvement loops, or manage…
prompt-optimizer
Systematically optimize LLM prompts for text classification tasks using reflective evolution. Guides researchers through iterative prompt development with…
context-diet
Cut agent token spend by shrinking what enters the context window. Index the repo or corpus once and query it instead of re-reading files on every question.…
route-cheap-escalate-hard
Cut LLM spend by routing bulk work to a cheap model and escalating only the hard turns to a premium one. Use when the user says their AI bill is too high, asks…
tool-discovery
Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent,…
nextstage-spec-driven
(NS) Spec-driven delivery face — clarify scope, write requirements, generate tasks, implement a version, quick fix, or resume paused work. Use whenever the…
agent-detector
CRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically. Without this, tasks route to wrong agents and use wrong models,…
agent-detector
CRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically. Without this, tasks route to wrong agents and use wrong models,…
response-analyzer
MCP Response Analyzer pattern - Write large responses to temp files, load summaries into context
better-goal
A guide for writing high-quality task goals for any coding agent. Triggered when the user mentions "set a goal", "goal", "task goal", "persistent goal", "completion criteria", or needs to define verifiable completion conditions and constraints for complex multi-turn tasks (performance optimization, debugging, migration, research reproduction, etc.).
better-goal
Guidelines for writing high-quality task goals for any coding agent. Triggered when the user mentions "setting a goal", "goal", "task goal", "persistent goal", "completion criteria", or needs to define verifiable completion conditions and constraints for complex multi-round tasks (performance optimization, debugging, migration, research reproduction, etc.).
cclens-trace-analyzer
Analyze the trace of a Claude Code session. Use this Skill when the user mentions a session ID in UUID format (composed of digits and lowercase letters), time clues ("just now", "today", "the most recent one"), troubleshooting the cause of Agent behavior, wanting to view the content of a certain claude code session, or analyzing trace content.
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…
create-skill
Create, improve, and manage Claude skills through a guided wizard, starter templates, or by converting conversation history into reusable skills. Use this…
claude-code-to-codex
Use when migrating a developer setup from Claude Code CLI to Codex CLI, especially hooks, CLI MCP servers, plugins, CLAUDE.md instructions, slash commands,…
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
stripe-link-cli
Agent payments via Stripe Link — cards, SPT, approvals.
novita-sandbox
Novita Agent Sandbox CLI wrapper — build templates, manage sandboxes, and deploy agents via `novita-sandbox-cli`. Use when user asks to "create a sandbox",…
prompt-engineering-helper
Skill for supporting LLM prompt optimization and testing. Performs prompt performance evaluation, improvement suggestions, A/B testing, best practice application, and reproducibility verification.
claude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
llm-wiki-setup
Initialize a Karpathy-style LLM wiki (personal knowledge base / AI second brain) in a folder. Creates a CLAUDE.md schema with routing table and naming…
nemotron-add-pattern
Add a cross-cutting decision pattern under src/nemotron/steps/patterns/. Use when a recurring ML decision (tokenizer lock, eval bookends, LoRA-on-small-data,…