Everything in the catalog

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline…

Terse caveman voice: answer first, fluff gone, every technical fact kept.

Write a Conventional Commits message compressed to intent only.

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket.

Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed.

Compressed code review - one line per finding with location, problem and fix.

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change.

Babysit a shipped release after merge, publication, or deployment.

Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim.

Token-optimized structural code search using tree-sitter AST parsing.

Caveman at maximum compression: fragments, one word when one word is enough, each fact once.

Turn one document into a kawaii NotebookLM slide deck.

Open-source AI job search agent -- evaluate offers, generate CVs, scan portals, track applications.

Conduct periodic access reviews and certifications.

Deploy Azure resources with ARM templates and Bicep.

Maintain IT asset inventory and configuration management database.

Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-login observer, or remote cmem.ai.

Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cmem.ai inference.

Set up or check claude-mem cloud sync with cmem.ai Pro.

Systematically explore and test a web application to find bugs, UX issues, and other problems.

Interact with Slack workspaces using browser automation.

twinny - AI Code Completion and Chat

twinnydotdev

AI code completion, chat, inline edit and code review on models you run.

Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.