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 spreadsheetRoutes a repository through the Caveman Cloud gateway so every LLM request is measured. Adds LLM spending observability without changing behavior.
Show real token usage and estimated savings for the current session, read from the session log. Trigger: /caveman-stats.
Shows recorded output tokens, cache-read token usage, and mode attribution for the current Claude Code session. Can also locate the host's native usage report.
Explains context management, verification strategies, explore-plan-implement workflows, prompting, and session management in Claude Code. Addresses parallel sessions, automation, and failure patterns such as repeated mistakes or lost instructions.
Identified as a development skill from everything-claude-code. Its name refers to continuous learning, but the description provides no specific workflow or capabilities.
Covers frontend development patterns for React and Next.js. Includes state management, performance optimization, and UI best practices.
Provides an example of a project guidelines skill. The description does not specify its contents or intended project environment.
Focuses on code security best practices and vulnerability identification. Applies to authentication, authorization, user input, file uploads, and new API endpoints.
Identified as a development skill from everything-claude-code under the name strategic compact. The description provides no specific workflow or capabilities.
Runs lengthy implementation, debugging, testing, or interactive CLI work through an inner coding agent in tmux. The outer agent decomposes tasks, reads stable screen snapshots, corrects direction, performs acceptance checks, and destroys the session afterward. Also covers evaluating external scheduler triggers.
Supports code search with ccc and cocoindex-code, including finding relevant code during broader tasks. Also handles indexing the codebase after changes and questions about the codebase index.
Provides a shared preflight for CCFA skills after the humanization step. Applies routing, scope, prerequisite, evidence, handoff, and artifact rules, and supports auditing and maintaining those rules while leaving research deliverables to specialists.
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