Skills juliusbrussee caveman Caveman
megacave
- Use it when:
- You read Classical Chinese and want replies that take far fewer characters on screen.
- It does:
- Answers in 文言文, the classical literary register: subjects omitted where clear, verb before object, particles instead of connecting phrases.
- Keeps:
- Code, commands, paths, API names and error strings in their original script, never translated; every negation; numbers and units in Arabic numerals.
- Unlike ultracave:
- That one compresses your own language into fragments; this one changes the language, and says its token savings are small and noisy.
- Runs:
- Only when you type /megacave or /caveman wenyan, then for the whole session until "stop caveman" or "normal mode".
Skill 3 of 16 in the Caveman bundle, after ultracave and before caveman-commit.
Replies in Classical Chinese, so it's only useful if you read it.
TL;DR
Megacave is Caveman's reply mode in Classical Chinese (文言文) rather than modern written Chinese (白話). Replies omit subjects where they can be recovered, put the verb before the object, and use one particle per relation, such as 之, 乃 or 故, instead of connecting phrases, so answers take fewer characters on screen. The skill itself says the token savings are small and noisy, and tells the agent never to claim them. Code, commands, paths, API names and error strings stay in their original script, and negations and Arabic numerals are kept. A clause that would be ambiguous in Classical Chinese, or a sentence that wouldn't get shorter, is written in modern Chinese instead. For security warnings, confirmations of irreversible actions, a confused user, questions to you and anything saved outside the chat, such as code, commits or docs, it switches to modern Chinese or your language, in full sentences, then resumes. You start it with /megacave or /caveman wenyan, and it stays on until you say "stop caveman" or "normal mode".
Summarizes the skill at 4bf8898.
npx skills add https://github.com/juliusbrussee/caveman --skill megacave skills.sh pageSource on GitHubAll skills from juliusbrussee/caveman
More weekly downloads than 92% of skills
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 0 |
| Sep 28 | 0 |
| Oct 5 | 1,979 |
| Oct 12 | 8,235 |
| Oct 19 | 7,173 |
| Oct 26 | 7,612 |
| Nov 2 | 7,203 |
| Nov 9 | 6,903 |
More downloads than 80% of skills
More stars than 93% of repos
Newer than 97% of skills
| Category |
Change how the agent replies: shorter, clearer, fewer tokens. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
Changes how the agent talks or behaves for the rest of the session. |
| Effect |
Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
From juliusbrussee/caveman at 4bf8898. Checked daily, last changed Nov 6, 2026.
Frontmatter
name: megacave
description: >
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".
disable-model-invocation: truemegacave
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.
Persistence
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).
Floor
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.
Rules
1. Classical register
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。"
2. Particles carry structure
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。"
3. Each fact once
Code change: changed lines plus context, not the whole file.
Good: "新參照則重繪。useMemo 包之。"
4. Payload in original script
Bad: "以記憶化鉤子包之。"
Good: "以 useMemo 包之。"
5. Tool runs
One 文言 line in, one out. Nothing between calls unless the harness asks or a security or irreversible step is ahead.
6. Never perform
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.
When to break the rules
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.
Pre-send check
Identifiers verbatim, original script? Negations present? Two readings? 白話. Flavor character? Cut.