caveman

In the author's own words, from each skill's SKILL.md.

• cavecrew

  When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

  skills/cavecrew/SKILL.md on GitHub (opens in a new tab)

• caveman-commit

  Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.

  skills/caveman-commit/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/caveman-compress/SKILL.md on GitHub (opens in a new tab)

• caveman-discover

  Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

  skills/caveman-discover/SKILL.md on GitHub (opens in a new tab)

• caveman-evidence-review

  Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

  skills/caveman-evidence-review/SKILL.md on GitHub (opens in a new tab)

• caveman-explore

  Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.

  skills/caveman-explore/SKILL.md on GitHub (opens in a new tab)

• caveman-help

  Quick-reference card for caveman modes, skills and commands. Trigger: /caveman-help or "caveman help".

  skills/caveman-help/SKILL.md on GitHub (opens in a new tab)

• 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. 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.

  skills/caveman-learn/SKILL.md on GitHub (opens in a new tab)

• 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.

  skills/caveman-manage/SKILL.md on GitHub (opens in a new tab)

• caveman-optimize

  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.

  skills/caveman-optimize/SKILL.md on GitHub (opens in a new tab)

• 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".

  skills/caveman-review/SKILL.md on GitHub (opens in a new tab)

• caveman-setup

  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.

  skills/caveman-setup/SKILL.md on GitHub (opens in a new tab)

• 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. Trigger: /caveman-stats.

  skills/caveman-stats/SKILL.md on GitHub (opens in a new tab)

• caveman

  Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

  skills/caveman/SKILL.md on GitHub (opens in a new tab)

• investigate-first

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

  skills/investigate-first/SKILL.md on GitHub (opens in a new tab)

• lean-build

  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.

  skills/lean-build/SKILL.md on GitHub (opens in a new tab)

• migration

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

  skills/migration/SKILL.md on GitHub (opens in a new tab)

• safe-refactor

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

  skills/safe-refactor/SKILL.md on GitHub (opens in a new tab)

• surgical-patch

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

  skills/surgical-patch/SKILL.md on GitHub (opens in a new tab)

• verify-and-stop

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

  skills/verify-and-stop/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• cc-hahaby NanmiCoder 本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude… 15k stars · 4 skills
• CodePilotby op7418 A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + N… 6.5k stars
• Unity-MCPby IvanMurzak AI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced too… 4.5k stars · 30 skills
• oh-my-openagentby code-yeongyu OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering. 70.1k stars · 25 skills
• CowAgentby zhayujie Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent,… 47.4k stars · 3 skills