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…
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
acos-meta
ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook…
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
model-routing
Intelligent model selection - routes tasks to Haiku (fast/cheap), Sonnet (balanced), or Opus (complex/strategic) based on task complexity analysis
santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies…
huggingface model trainer
Train and fine-tune LLMs using HuggingFace TRL, Transformers, and cloud GPU infrastructure with SFT, DPO, GRPO methods
todo-discipline
Use when starting any complex task (3+ steps) or before declaring work complete. Enforces todo/task state to match reality — merge updates + read verification.…
Oracle AI Architect
Extended reference material for Oracle AI architecture with deep technical implementations
feynman-thinking
Transform Claude into a Feynman mentor. Focuses on simple explanations, architectural models, Socratic questioning, and stripping away unnecessary complexity.…
skill-builder
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build…
langgraph patterns expert
Build production-grade agentic workflows with LangGraph using graph-based orchestration, state machines, human-in-the-loop, and advanced control flow
spartan warrior
Embody the unbreakable Spartan ethos of discipline, courage, and relentless excellence through laconic wisdom and warrior mentality forged in hardship
langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing…
skill-share
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
ai-counterpart-discipline
Bounded-authority AI counterpart that occupies the human seat at interactive checkpoints of unattended runs: answers intake questions, picks among pre-approved…
artcraft-cli
Use ArtCraft when you need to query actual command parameters and capabilities, invoke public CLI, MCP, and diagnostics; this skill includes first-time installation and the public CLI entry point.
artcraft-harness
ArtCraft built-in execution harness—the unified execution channel for all artcraft domain skills (artcraft-use, artcraft-cli, and each scenario skill). Executes workflow orchestration, public CLI...
1panel-setup
Set up or diagnose a 1Panel MCP connection using a pinned official executable and private plugin data; use for authentication, missing tools, transport and…
future-skill-creator
Create or update a skill so it encodes judgment, not just knowledge — decision trees, do/don't pairs, on-demand references, a check script with tests, and a…
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time…
google-ads-mcp-setup-guide
Install and verify the official Google Ads MCP server with gcloud ADC, connect an AI client, and diagnose onboarding failures. Use for Google Ads MCP setup or…