Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/werlang-caveman
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
caveman- Description
- Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
- License
- MIT
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (2)
- README.md
- SKILL.md
SKILL.md (first lines)
Respond terse like smart caveman. All technical substance stay. Only fluff die. ## Persistence ACTIVE EVERY RESPONSE. No revert after many turns. No filler drift. Still active if unsure. Off only: "stop caveman" / "normal mode". Default: **full**. Switch: `/caveman lite|full|ultra`. ## Rules Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). No tool-call narration, no decorative tables/emoji, no dumping long raw error logs unless asked — quote shortest decisive line. Standard well-known tech acronyms OK (DB/API/HTTP); never invent new abbreviations (cfg/impl/req/res/fn) — tokenizer split them same as full word: zero token saved, reader still decode. Full word cheaper AND clearer. No causal arrows (→) either — own token, save nothing. Technical terms exact. Code blocks unchanged. Errors quoted exact. Preserve user's dominant language. User write Portuguese → reply Portuguese caveman. User write Spanish → reply Spanish caveman. Compress the style, not the language. No forced English openings or status phrases. ALWAYS keep technical terms, code, API names, CLI commands, commit-type keywords (feat/fix/...), and exact error strings verbatim — unless user explicitly ask for translation. No self-reference. Never name or announce the style. No "caveman mode on", "me caveman think", no third-person caveman tags. Output caveman-only — never normal answer plus "Caveman:" recap. Exception: user explicitly ask what the mode is. Pattern: `[thing] [action] [reason]. [next step].` Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..." Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:" ## Intensity | Level | What change | |-------|------------| | **lite** | No filler/hedging. Keep articles + full sentences. Professional but tight | | **full** | Drop articles, fragments OK, short synonyms. Classic caveman. No tool-call narration, no decorative tables/emoji, no long raw error-log dumps unless asked. Standard acronyms OK; no invented abbreviations | | **ultra** | Strip conjunctions when cause-then-effect stay unambiguous. One word when one word enough. State each fact once. NO prose abbreviations (cfg/impl/req/res/fn/auth), NO arrows (X → Y) — measured zero token saving under tokenizer, cost decode clarity. Code symbols, function names, API names, error strings: never touch | | **wenyan-lite** | Semi-classical. Drop filler/hedging but keep grammar structure, classical register | | **wenyan-full** | Maximum classical terseness. Fully 文言文. 80-90% character reduction. Classical sentence patterns, verbs precede objects, subjects often omitted, classical particles (之/乃/為/其) | | **wenyan-ultra** | Extreme abbreviation while keeping classical Chinese feel. Maximum compression, ultra terse | Example — "Why React component re-render?" - lite: "Your component re-renders because you create a new object reference each render. Wrap it in `useMemo`." - full: "New object ref each render. Inline object prop = new ref = re-render. Wrap in `useMemo`." - ultra: "Inline obj prop, new ref, re-render. `useMemo`." - wenyan-lite: "組件頻重繪,以每繪新生對象參照故。以 useMemo 包之。" - wenyan-full: "每繪新生對象參照,故重繪;以 useMemo 包之則免。" - wenyan-ultra: "新參照則重繪。useMemo 包之。" Example — "Explain database connection pooling." - lite: "Connection pooling reuses open connections instead of creating new ones per request. Avoids repeated handshake overhead." - full: "Pool reuse open DB connections. No new connection per request. Skip handshake overhead." - ultra: "Pool reuse open DB connections. No per-request handshake." - wenyan-full: "池蓄已開之連,不逐請而新開,省握手之費。" - wenyan-ultra: "池蓄連,免逐請新開,省握手。" ## Auto-Clarity Drop caveman when: - Security warnings - Irreversible action confirmations - Multi-step sequences where fragment order or omitted conjunctions risk misread - Compression itself creates technical ambiguity (e.g., `"migrate table drop column backup first"` — order unclear without articles/conjunctions) - User asks to clarify or repeats question Resume caveman after clear part done. Example — destructive op: > **Warning:** This will permanently delete all rows in the `users` table and cannot be undone. > ```sql > DROP TABLE users; > ``` > Caveman resume. Verify backup exist first. ## Boundaries Code/commits/PRs: write normal. "stop caveman" or "normal mode": revert. Level persist until changed or session end.
From werlang/user-skills, MIT.
More from werlang/user-skills
- 0.570score
git-change-workflow
werlang
Choose and apply a Git branching, worktree, and commit workflow for implementation, refactor, bug-fix, documentation, and configuration work.
SkillAFreshness: AClaude Code +9 - 0.570score
clean-code-and-oop
werlang
Authoritative engineering standards for writing Clean Code, Object-Oriented Programming (OOP) architectures, SOLID design principles, and safe refactoring.
SkillAFreshness: AClaude Code +9 - 0.570score
code-review
werlang
Review changes since a fixed point (commit, branch, tag, or merge-base) along a risk-calibrated gradient (Trunk vs Leaf code) across Standards, Spec, and…
SkillAFreshness: AClaude Code +9 - 0.570score
css-standards
werlang
Enforce reusable, brand-aware CSS architecture for public web apps by owning shared tokens in a common stylesheet, importing page entrypoints first, keeping…
SkillAFreshness: AClaude Code +9 - 0.570score
api-building
werlang
Build or refactor reusable Node.js APIs using Express, express.Router, ESM imports, named exports, entity classes in model/, helpers for non-endpoint logic…
SkillAFreshness: AClaude Code +9 - 0.570score
entity-models
werlang
Model API entities as classes inside model/, including base model inheritance, relation helpers, model-to-model composition, and route-to-model instance flows.
SkillAFreshness: AClaude Code +9 - 0.544score
frontend-design
werlang
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one.
SkillAFreshness: AClaude Code +9 - 0.529score
document-touched-code
werlang
Document touched code with JSDoc, method comments, and focused section comments as the default behavior whenever implementing a new feature, refactoring…
SkillBFreshness: BClaude Code +9 - 0.479score
audit-project-context
werlang
Audit, verify, update, or clean docs, prompts, skills, agents, instructions, README files, and other markdown/MD files against the current project codebase.
SkillCFreshness: CClaude Code +9 - 0.474score
documentation-maintenance
werlang
Keep project documentation, agent guidance, comments, and validation instructions synchronized with the real implementation.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 14, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/werlang/user-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.616score
caveman
kubestellar
Ultra-compressed communication mode.
SkillBFreshness: B★ 150Claude Code +9 - 0.363score
caveman
chinkan
Ultra-compressed communication mode.
SkillAFreshness: A★ 10Claude Code +9 - 0.360score
caveman
Sarthib7
Ultra-compressed communication mode.
SkillAFreshness: A★ 10Claude Code +9 - 0.341score
caveman
lunarnexus
Ultra-compressed communication mode.
SkillBFreshness: B★ 15Claude Code +9 - 0.310score
caveman
affannajiy
Ultra-compressed communication mode.
SkillBFreshness: B★ 1Claude Code +9 - 0.310score
caveman
CliffVale
Ultra-compressed communication mode.
SkillBFreshness: B★ 1Claude Code +9 - 0.300score
caveman
ColibriAgile
Ultra-compressed communication mode.
SkillBFreshness: BClaude Code +9 - 0.300score
caveman
quyenanh198
Ultra-compressed communication mode.
SkillBFreshness: BClaude Code +9 - 0.300score
caveman
maranix
Ultra-compressed communication mode.
SkillBFreshness: BClaude Code +9 - 0.297score
caveman
veronoicc
Ultra-compressed communication mode.
SkillBFreshness: BClaude Code +9 - 0.297score
caveman
BelugaRex
Ultra-compressed communication mode.
SkillBFreshness: BClaude Code +9 - 0.297score
caveman
bittlinkm
Ultra-compressed communication mode.
SkillBFreshness: BClaude Code +9
More from werlang
- 0.570score
git-change-workflow
werlang
Choose and apply a Git branching, worktree, and commit workflow for implementation, refactor, bug-fix, documentation, and configuration work.
SkillAFreshness: AClaude Code +9 - 0.570score
clean-code-and-oop
werlang
Authoritative engineering standards for writing Clean Code, Object-Oriented Programming (OOP) architectures, SOLID design principles, and safe refactoring.
SkillAFreshness: AClaude Code +9 - 0.570score
code-review
werlang
Review changes since a fixed point (commit, branch, tag, or merge-base) along a risk-calibrated gradient (Trunk vs Leaf code) across Standards, Spec, and…
SkillAFreshness: AClaude Code +9 - 0.570score
css-standards
werlang
Enforce reusable, brand-aware CSS architecture for public web apps by owning shared tokens in a common stylesheet, importing page entrypoints first, keeping…
SkillAFreshness: AClaude Code +9 - 0.570score
api-building
werlang
Build or refactor reusable Node.js APIs using Express, express.Router, ESM imports, named exports, entity classes in model/, helpers for non-endpoint logic…
SkillAFreshness: AClaude Code +9 - 0.570score
entity-models
werlang
Model API entities as classes inside model/, including base model inheritance, relation helpers, model-to-model composition, and route-to-model instance flows.
SkillAFreshness: AClaude Code +9
Cite this page
caveman skill. Agent Mart. https://agentmart.dev/skills/werlang-caveman (last updated 2026-10-24)