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/ntk148v-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
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/caveman
What's inside
- Skill name
caveman- Description
- Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
- License
- MIT
- Instructions
- 42 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Respond terse like smart caveman. All technical substance stay. Only fluff die. ## Persistence ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop caveman" or "normal mode". ## 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"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough. Technical terms stay exact. Code blocks unchanged. Errors quoted exact. 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:" ### Examples **"Why React component re-render?"** > Inline obj prop -> new ref -> re-render. `useMemo`. **"Explain database connection pooling."** > Pool = reuse DB conn. Skip handshake -> fast under load. ## Auto-Clarity Exception Drop caveman temporarily for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, 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.
From ntk148v/skills, MIT.
More from ntk148v/skills
- 0.497score
skill-authoring
ntk148v
Use when creating, editing, auditing, or validating Agent Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
repo-analyzer
ntk148v
Use when the user mentions "analyzing a project", "analyzing a repository", "analyzing GitHub", "project analysis", "source code analysis", "architecture…
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill
ntk148v
Interview the user relentlessly about a plan, design, or domain model until reaching shared understanding.
SkillCFreshness: C★ 1Claude Code +9 - 0.461score
handoff
ntk148v
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: C★ 1Claude Code +9 - 0.432score
conventional-commits
ntk148v
Use when creating git commits, writing commit messages, or when the user mentions conventional commits, semantic versioning, or automated changelog generation.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
code-reviewer
ntk148v
Use when reviewing code, conducting code reviews, analyzing pull requests, or when the user mentions "code review", "PR review", "code quality", or "static…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
deep-wiki
ntk148v
Use when generating comprehensive documentation for a codebase, creating wiki pages, documenting architecture, or when the user mentions "deep wiki"…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
security-expert
ntk148v
Use when analyzing security vulnerabilities, conducting security reviews, checking for common vulnerabilities, or when the user mentions "security"…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
system-performance
ntk148v
Use when analyzing system performance, debugging performance issues, investigating bottlenecks, or when the user mentions "performance analysis", "USE…
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- May 19, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ntk148v/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ntk148v
- 0.497score
skill-authoring
ntk148v
Use when creating, editing, auditing, or validating Agent Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
repo-analyzer
ntk148v
Use when the user mentions "analyzing a project", "analyzing a repository", "analyzing GitHub", "project analysis", "source code analysis", "architecture…
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill
ntk148v
Interview the user relentlessly about a plan, design, or domain model until reaching shared understanding.
SkillCFreshness: C★ 1Claude Code +9 - 0.461score
handoff
ntk148v
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: C★ 1Claude Code +9 - 0.432score
conventional-commits
ntk148v
Use when creating git commits, writing commit messages, or when the user mentions conventional commits, semantic versioning, or automated changelog generation.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
code-reviewer
ntk148v
Use when reviewing code, conducting code reviews, analyzing pull requests, or when the user mentions "code review", "PR review", "code quality", or "static…
SkillDFreshness: D★ 1Claude Code +9
Cite this page
caveman skill. Agent Mart. https://agentmart.dev/skills/ntk148v-caveman (last updated 2026-10-24)