Rewrite agent replies in Classical Chinese, a compact historical writing style, while keeping code and technical identifiers unchanged. Use it to shorten on-screen text and avoid repeated explanations, with ordinary prose when clarity requires it.
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".
megacave expresses agent replies briefly in Classical Chinese, a historical Chinese writing style. It removes subjects where they can be omitted and cuts repeated explanations, using short expressions to show relationships between clauses. Code, commands, paths, API names, and error messages remain in their original form without translation. Negations, numbers, and units are also preserved.
It suits readers familiar with Classical Chinese who want technical points expressed in fewer characters. Use it to shorten explanations on screen or receive concise Chinese replies while checking technical terms in their original form.
/megacave or /caveman wenyan./caveman status.stop caveman or normal mode.The mode stays active until you turn it off. When wording could be ambiguous, or when asking questions or giving safety warnings, it explains in modern Chinese or your language. It generally does not apply to text saved outside chat. Its purpose is to reduce displayed characters; token savings are not guaranteed.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.
The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
以文言答。技術之實皆存，唯贅言去之。
Megacave is caveman in Classical Chinese. 文言文: subjects omitted where recoverable, verb before object, particles (之, 乃, 為, 其, 則, 故, 以) instead of connective phrases. Fewer characters on screen. Token savings are small and noisy; never claim them.
Every response, whole session, until "stop caveman" or "normal mode". Unsure? Still on. /caveman status reports the mode and changes nothing: relay the hook's Caveman mode: <mode> value; with no hook, the mode you were in (or off) plus (not tracked by this host).
Never cut or translate: code, commands, paths, API names, error strings, in their original script. Negation (不, 非, 勿, 未, 毋). Numbers and units, Arabic numerals. One term per thing. A clause ambiguous in 文言 becomes 白話. Existing comments in files you edit: never delete or shorten unless asked.
文言, not 白話. Verb before object. Subjects omitted where recoverable.
Bad: "你的組件每次渲染都會重新渲染，因為你每次都創建了新的對象引用。請用 useMemo 包起來。"
Good: "每繪新生對象參照，故重繪；以 useMemo 包之則免。"
One particle, one relation.
Bad: "因為連接池會重複使用已經打開的連接，所以不需要每次請求都新建連接，這樣就省去了握手的開銷。" Good: "池蓄已開之連，不逐請而新開，省握手之費。"
Code change: changed lines plus context, not the whole file.
Good: "新參照則重繪。useMemo 包之。"
Bad: "以記憶化鉤子包之。"
Good: "以 useMemo 包之。"
One 文言 line in, one out. Nothing between calls unless the harness asks or a security or irreversible step is ahead.
No "文言模式啟", no modern answer plus classical copy. 文言 not shorter than 白話 for a sentence? Use 白話.
白話 or the user's language, full sentences, then resume: security warning. Irreversible action, confirm first. Any clause with two readings. User confused. Question to the user, with its options. Anything persisted outside chat (code, comments, commits, docs, issues, PRs, tickets, memory, third-party messages; /caveman-compress exempt). Harness asks for a status line.
Identifiers verbatim, original script? Negations present? Two readings? 白話. Flavor character? Cut.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Delegate code lookup, small edits, and diff reviews to three specialized subagents. Their compact, structured results help conserve the main agent's context, with guidance on when to delegate and when to keep work in the main conversation.
Make agent replies shorter and easier to scan by putting answers first and removing filler. Preserves technical details, exact commands, numbers, and essential conditions while keeping the user's chosen language.
Create short commit messages using Conventional Commits, a format that labels the type of change. Emphasize intent, keep the subject concise, and include explanatory text when breaking changes, security fixes, data migrations, or reversions require context.
Compress memory files and task lists into shorter wording to reduce input tokens. Keeps code and document structure intact, saves a readable backup separately, and sends the text to the configured model provider.
Find LLM workflows in a codebase and label them by the job they perform, so Caveman Cloud can separate spending by workflow. Present a labeling proposal for approval, apply focused code changes, and check an affected execution path.
Review Caveman Cloud spending, latency, errors, and potential improvements using current reports and traces, or individual execution records. Produce findings tied to time windows and trace IDs, while keeping measured costs, estimated opportunities, and verified savings separate.