Skills from JuliusBrussee/caveman: 22 agent skills

• cavecrew — When to delegate to `cavecrew-investigator` (locate code).
• caveman — Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens".
• caveman-commit — Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
• caveman-compress — 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.
• caveman-discover — Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket.
• caveman-evidence-review — Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.
• caveman-explore — Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed.
• caveman-help — Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".
• caveman-learn — Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.
• caveman-manage — Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
• caveman-optimize — Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation.
• caveman-review — Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
• caveman-setup — Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change.
• caveman-stats — Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report.
• investigate-first — Diagnose ambiguous failures before editing.
• lean-build — Build feature work with high overbuilding risk.
• megacave — Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan.
• migration — Implement reversible compatibility-safe transitions.
• safe-refactor — Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
• surgical-patch — Fix bugs and small behavior changes at the narrowest responsible layer.
• ultracave — Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra.
• verify-and-stop — Prove existing work meets acceptance conditions without expanding scope.