Skip to content
store
caveman-learn

Free alternatives to caveman-learn

50 free AI Skills apps to use instead, best rated first.

Top picks

  1. W

    webapp-testing

    Launch

    Native Python Playwright scripts for testing local web applications with server lifecycle management. Includes with_server.py helper to automatically start and manage single or multiple servers before running automation scripts. Supports re

  2. C

    content-research-writer

    Launch

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on

  3. O

    openhue

    Launch

    openhue is an agent skill from the OpenClaw project, listed on skills.sh. It lets an agent control Philips Hue lights and scenes through a Hue Bridge with the OpenHue CLI: turn lights on and off, dim rooms, set scenes such as movie mode, an

  4. B

    batch-grill-me

    Launch

    batch-grill-me is an agent skill from Matt Pocock's skills collection, listed on skills.sh. It interviews you relentlessly about a plan until you share an understanding. It maps decisions as a tree and asks every question it can answer now

  5. I

    implement

    Launch

    implement is an agent skill from Matt Pocock's skills collection, listed on skills.sh. It implements work from a spec or tickets: it fetches the ticket, works test-first at agreed seams, runs type checks and tests as it goes, reviews the re

  6. F

    frontend-design

    Launch

    Distinctive, production-grade frontend interfaces that reject generic AI aesthetics through intentional design choices. Guides aesthetic direction selection (brutalist, maximalist, retro-futuristic, luxury, organic, etc.) before implementat

More AI Skills apps

See all
7
A

artifacts-builder

Suite of tools for creating elaborate

Launch
8
C

canvas-design

Design beautiful visual art in .png and .pdf formats using design philosophies

Launch
9
M

mcp-builder

Guide for creating high-quality MCP servers to integrate external APIs

Launch
10
P

pdf

Extract text, tables, metadata, merge & annotate PDFs

Launch
11
X

xlsx

Spreadsheet manipulation: formulas, charts, data transformations

Launch
12
F

find-skills

Discover and install specialized agent skills from the open ecosystem

Launch
13
B

brainstorming

Transform rough ideas into fully-formed designs through structured questioning

Launch
14
F

finishing-a-development-branch

Guides completion of development work by presenting clear options

Launch
15
S

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior

Launch
16
T

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

Launch
17
U

using-git-worktrees

Creates isolated git worktrees

Launch
18
1

1password

Set up and use 1Password CLI for sign-in, desktop integration

Launch
19
A

apple-notes

Create, view, edit, delete, search, move, or export Apple Notes

Launch
20
A

apple-reminders

List, add, edit, complete, or delete Apple Reminders and reminder lists

Launch
21
B

bear-notes

Create, search, and manage Bear notes via grizzly CLI

Launch
22
B

blogwatcher

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI

Launch
23
B

blucli

BluOS CLI (blu) for discovery, playback, grouping, and volume

Launch
24
C

camsnap

Capture frames or clips from RTSP/ONVIF cameras and local webcams

Launch
25
C

clawhub

Search ClawHub for plugins by default, or skills when explicitly requested

Launch
26
C

coding-agent

Delegate coding work to Codex, Claude Code, or OpenCode as background workers

Launch
27
D

discord

Discord messaging workflows through OpenClaw's message tool

Launch
28
E

eightctl

Control Eight Sleep pods (status, temperature, alarms, schedules)

Launch
29
G

gemini

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP

Launch
30
G

gh-issues

Fetch GitHub issues, select candidates, spawn background fix agents, open PRs

Launch
31
G

gifgrep

Search GIF providers with CLI/TUI, download results, and extract stills/sheets

Launch
32
G

github

GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos

Launch
33
G

gog

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs

Launch
34
G

goplaces

Query Google Places for text search, place details, resolve, reviews

Launch
35
H

healthcheck

Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups

Launch
36
H

himalaya

Himalaya CLI for IMAP/SMTP mail: list, read, search, compose, reply, forward

Launch
37
I

imsg

Use the imsg CLI from OpenClaw agents for iMessage/SMS DMs, groups, replies

Launch
38
M

mcporter

List, configure, authenticate, call, and inspect MCP servers/tools

Launch
39
M

model-usage

Summarize CodexBar local cost logs by model for Codex or Claude

Launch
40
N

nano-pdf

Edit PDFs with natural-language instructions using the nano-pdf CLI

Launch
41
N

notion

Notion CLI/API for pages, Markdown content, data sources, files, comments

Launch
42
O

obsidian

Work with Obsidian vaults

Launch
43
O

openai-whisper

Local speech-to-text with the Whisper CLI (no API key)

Launch
44
O

openai-whisper-api

OpenAI Audio Transcriptions API via curl

Launch
45
O

oracle

Oracle CLI second-model review/debug/refactor/design

Launch
46
O

ordercli

Foodora-only CLI for checking past orders and active order status

Launch
47
P

peekaboo

Capture and automate macOS UI with the Peekaboo CLI

Launch
48
S

sag

ElevenLabs text-to-speech with mac-style say UX

Launch
49
S

session-logs

Search and analyze your own session logs (older/parent conversations) using jq

Launch
50
S

sherpa-onnx-tts

Local text-to-speech via sherpa-onnx (offline, no cloud)

Launch

About caveman-learn

C

caveman-learn

Act on a Caveman learn report

caveman-learn is an agent skill from the caveman project that acts on a Caveman learn report. The learn command measures where an agent's tokens go, and this skill is the consent-gated half that turns those findings into edits. It reviews the ranked token sinks, proposes cost-lowering fixes, applies each edit only with the user's approval, and then reports what the fixes returned. It is built on two rules: it never claims a saving it has not measured, and it never makes the agent less capable to save tokens. The report includes several kinds of finding, which the skill explains. Cache efficiency shows what a million input tokens cost after cache reuse, and it is a rate used to price the other sinks, not a volume to add. Tool output portfolio ranks the call shapes that take up most of the context. Session outcomes shows the share of tokens in sessions with no commit in their window, which the skill presents as a correlation rather than proof of waste. Subagent spend is for visibility only, and the skill does not turn it into advice to use fewer subagents. Procedure repeat findings are candidates for distilling into a skill.

View caveman-learnAll AI Skills apps
Price
Free
Made by
juliusbrussee
Category
AI Skills
Website
github.com/juliusbrussee/caveman/caveman-learn