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 spreadsheetControls response brevity through lite, full, ultra, and wenyan variants. Aims to reduce output token use while preserving technical accuracy.
Provides an ultra-compressed communication style intended to reduce token usage while preserving technical accuracy. Supports multiple intensity levels, including wenyan variants, and activates for requests for brevity or token efficiency.
Terse communication that stays easy to parse. Drops filler, pleasantries and hedging while keeping full technical accuracy. Chat keeps natural language, because humans read it; files, docs, comments and commit messages save tokens through cut fluff and flat sentence structure, never through nested clauses. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be br…
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
Creates Conventional Commits messages compressed to the essential intent of a change.
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
Converts memory files such as CLAUDE.md and todo lists into compressed caveman format. Keeps a readable backup while reducing input token usage.
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
Identifies and labels LLM workflows throughout a repository. Enables Caveman Cloud to attribute spending to individual workflows rather than a single aggregate bucket.
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
Provides read-only analysis of Caveman Cloud evidence, including costs, Cave Score, traces, latency, errors, routing, and savings. Helps explain findings and where LLM spending goes.
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
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