Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access."..." for exact phrases · Try typography, debugging or spreadsheetAutomatically loads project context at session start, tracks sessions alongside git activity, and writes to native memory. Uses deterministic Node.js scripts for consistent command behavior across model versions.
Set up and verify C/C++ language intelligence with clangd in Cursor (extension, compile_commands.json, CMake) or Claude Code (clangd-lsp plugin). Use for .cpp/.h files, missing completions, or Blunder Engine C++20 development.
Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use.
Covers substitution ciphers, Vigenere, transposition, XOR, and encoded text encountered in CTF challenges. Includes frequency analysis, Kasiski examination, and known-plaintext cryptanalysis.
Defines an authoritative, nearly achromatic page style inspired by research journals and warm stone. Uses warm ivory parchment backgrounds and near-black slate as the dominant ink.
Get a second opinion from Claude Code. Use from Codex when you want to cross-check your reasoning, validate a plan, or get an independent review from Claude.
Covers model identifiers, pricing, parameters, token counting, streaming, tool use, MCP, and agent development. Supports Claude integrations, model migrations, and troubleshooting issues involving refusals, cutoffs, tool calls, or token behavior.
Analyze a codebase and recommend AI automations (MCP servers, skills, hooks, subagents, slash commands). Use when the user asks for automation recommendations, wants to optimize Claude Code or Cursor setup, mentions improving agent workflows, asks how to set up a project for AI coding, or what hooks/skills/MCP to use.
Evaluates a codebase to recommend suitable Claude Code automations. Supports initial project setup and workflow improvements involving hooks, subagents, skills, plugins, and MCP servers.
Supports four Claude certification tracks with onboarding, interactive lessons, verified labs, and scored artifacts. Includes diagnostics, mock exams, progress resumption, and remediation of weak exam domains.
Hands coding tasks or queues to a separate Claude Code CLI process or Claude session when explicitly requested. The delegating agent retains responsibility for reviewing and integrating the resulting diff.
Hand the current conversation off to a fresh background agent that picks up the work immediately.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name