20 Caveman alternatives
Caveman: A response-style skill that makes a coding agent answer tersely, answer first with filler cut, while keeping every command, path, number and error verbatim, to save output tokens. 20 agent skills do similar work, most sharing Coding Agent, Cost Optimization and Claude Code, ranked by how much they have in common with Caveman.
-
by Julius Brussee
The Caveman family's commit-message skill: terse Conventional Commits that state intent, an imperative subject of 50 to 72 characters, a body only when the why is not obvious, and no AI attribution.
-
by Karl Lowenbjer
Claude Code plugin whose 22 writing rules cut reply length roughly in half and strip slogans, metaphors and filler from every answer.
Also: Claude Code, Token Optimization
-
by Matt Pocock
Matt Pocock's test-driven development skill: one red-to-green slice at a time, tests only at seams agreed with you first, and a named list of test anti-patterns to avoid.
Also: Claude Code, Coding Agent
-
by AMD
AMD's official meta-skill: permanently reroutes an agent's image generation, text-to-speech and speech-to-text to a local Lemonade Server instead of a paid cloud API.
Also: Cost Optimization
-
by Microsoft
Microsoft's official Azure skill for cost work: query historical spend, forecast it, and hunt down waste like orphaned disks and oversized VMs.
Also: Cost Optimization
-
by Datadog
Search Datadog logs from an agent and keep the bill under control — query syntax, exclusion filters, log-based metrics, archives and PII scrubbing.
Also: Cost Optimization
-
by Vercel
Vercel's official optimization skill: collects real production metrics first, then returns ranked, citation-checked cost and performance fixes.
Also: Cost Optimization
-
by thedotmack
Persistent cross-session memory for coding agents: hooks capture each session, a local SQLite + vector store compresses it, and a mem-search skill reads it back.
Also: Coding Agent
-
by Convex
Convex's official top-level agent skill — routes an agent to the right convex-* skill for the task and to a served capability catalogue that stays current without a reinstall.
Also: Coding Agent
-
by Vercel
The skill for Vercel Labs' agent-browser, a fast Rust CLI that lets coding agents open sites, fill forms, click, screenshot and scrape through Chrome DevTools Protocol, using accessibility-tree snapshots with stable element refs.
Also: Coding Agent
-
by Vercel
Vercel's skill for discovering agent skills: when you ask how to do something, the agent searches the open skills ecosystem with the Skills CLI, vets results by installs, source and stars, and offers the install command.
Also: Coding Agent
-
by OpenQodex
Open source pre-push AI code review for Claude Code and Codex: scanners plus a separate reviewer that verifies every finding.
Also: Coding Agent
-
by dbwls99706
A single progressive-disclosure skill for production ROS 2 work — rclcpp/rclpy, colcon, QoS and DDS, tf2/URDF, ros2_control, Nav2, MoveIt 2, plus ROS 1 migration and hardware safety gates.
Also: Coding Agent
-
by arpitg1304
Ten SKILL.md modules that give coding agents real ROS engineering judgement — ROS 1 and ROS 2, design patterns, perception, testing, Docker, bringup and robot security.
Also: Coding Agent
-
by zubair-trabzada
Claude Code skill that audits a site for visibility in AI answers — citability scoring, AI-crawler access, llms.txt, schema markup and brand-mention scanning — plus classic technical SEO.
Also: Coding Agent
-
by Cheng-I Wu
A four-skill bundle that runs the academic pipeline end to end — deep research, paper writing, peer review and revision — as multi-agent workflows inside Claude Code.
Also: Coding Agent
-
by ayghri
An output-style skill that stops a coding agent burying the answer: action first, numbered steps, state restated every turn, no preamble or filler.
Also: Coding Agent
-
by Snowflake
Snowflake's official skill that routes Snowflake work from Claude Code to the Cortex Code CLI, with semantic routing, approval modes and audit logging.
Also: Coding Agent
-
by Addy Osmani
Reduces accumulated complexity without changing behaviour, using Chesterton's Fence to avoid deleting the thing that was load-bearing.
Also: Coding Agent
-
by Addy Osmani
Sends every non-trivial decision to a fresh-context adversarial reviewer before it stands — for production, security-sensitive or irreversible work.
Also: Coding Agent
