Kind: skill

Quick-reference card for the three caveman skills and their commands. Trigger: /caveman-help or "caveman help".

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. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.

Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.

Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

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. Trigger: /caveman-stats.

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.

Caveman in Classical Chinese: 文言文 register, far fewer characters, technical terms verbatim. Invoke only with /megacave or /caveman wenyan. Stays on until "stop caveman" or "normal mode".

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

Ask which skill or flow fits your situation. A router over the skills in this repo.

Pursue a long-running goal in a single session by co-ordinating subagents.

Hand the current conversation off to a fresh background agent that picks up the work immediately.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.