caveman-mode
ultra-compressed responses that drop filler, articles, and pleasantries while keeping full technical accuracy — for when the user wants brevity or says…
Skill by Hugofsco
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/hugofsco-caveman-mode
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-mode
What's inside
- Skill name
caveman-mode- Description
- ultra-compressed responses that drop filler, articles, and pleasantries while keeping full technical accuracy — for when the user wants brevity or says "caveman mode"/"be brief"/"less tokens"
- License
- MIT
- Instructions
- 22 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Caveman mode
Once triggered ("caveman mode", "be brief", "less tokens", "/caveman"), stay terse for
EVERY response until the user says "stop caveman" / "normal mode" — don't drift back after
a few turns.
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries
(sure/certainly/happy to), hedging, conjunctions. Fragments OK. Short synonyms (big not
extensive, fix not "implement a solution for"). Abbreviate common terms (DB/auth/config/req/
fn/impl). Use `->` for causality.
Keep exact: technical terms, code blocks, quoted error text.
Pattern: `[thing] [action] [reason]. [next step].`
Not: "Sure! I'd be happy to help. The issue you're seeing is likely caused by..."
Yes: "Bug in auth middleware. Token expiry check uses `<` not `<=`. Fix:"
**Exception — drop caveman temporarily for:** security warnings, confirming an irreversible
action (delete, DROP TABLE, force-push), multi-step sequences where a fragment risks being
misread, or when the user asks you to clarify. Resume caveman right after.From Hugofsco/oceano, MIT.
More from Hugofsco/oceano
- 0.526score
aeo-content-citations
Hugofsco
audit and optimize written content so LLMs (ChatGPT, Perplexity, Claude, Gemini) cite it as a source, and track which pages get cited — use for brand/store…
SkillBFreshness: BClaude Code +9 - 0.479score
aws-solution-architect
Hugofsco
design an AWS architecture (serverless, three-tier, microservices) from requirements, generate CloudFormation/CDK/Terraform, and estimate/optimize costs — use…
SkillCFreshness: CClaude Code +9 - 0.479score
academic-literature-search
Hugofsco
search real academic literature (PubMed + OpenAlex) with structured, citable metadata instead of generic web search — use when the topic is…
SkillCFreshness: CClaude Code +9 - 0.479score
content-humanizer
Hugofsco
rewrite AI-sounding content (store copy, emails, social posts) so it reads like a person wrote it, not a committee — use when content feels robotic, generic…
SkillCFreshness: CClaude Code +9 - 0.479score
agent-workflow-designer
Hugofsco
pick the right multi-agent/multi-step pattern (sequential, parallel, router, orchestrator, evaluator) and scaffold it before building — use when designing one…
SkillCFreshness: CClaude Code +9 - 0.479score
changelog-generator
Hugofsco
generate a CHANGELOG.md and compute the next semver version from Conventional Commits — use when cutting a release for a real project, or to check what…
SkillCFreshness: CClaude Code +9 - 0.476score
copywriting
Hugofsco
write or rewrite marketing/store copy — headlines, CTAs, product pages, landing pages — use for "write copy for", "improve this copy", headline help, or CTA…
SkillCFreshness: CClaude Code +9 - 0.476score
a11y-audit
Hugofsco
scan React/Vue/Next.js/plain-HTML code for WCAG 2.2 violations and check color contrast — use before shipping a new component or page, or when auditing the…
SkillCFreshness: CClaude Code +9 - 0.474score
backend-api-tools
Hugofsco
scaffold API routes from an OpenAPI spec, analyze/migrate a database schema, or load-test an endpoint — use when building or hardening a backend API
SkillCFreshness: CClaude Code +9 - 0.474score
azure-cloud-architect
Hugofsco
design an Azure architecture (App Service, AKS, serverless), generate Bicep templates, and estimate/optimize costs — use when deploying something to Azure…
SkillCFreshness: CClaude Code +9 - 0.474score
api-design-reviewer
Hugofsco
lint an OpenAPI/REST API spec for convention violations, detect breaking changes between two spec versions, and score overall design quality — use when…
SkillCFreshness: CClaude Code +9 - 0.474score
ci-cd-pipeline-builder
Hugofsco
detect a project's stack and generate a GitHub Actions or GitLab CI pipeline from it — use when a real project has no CI yet, or its pipeline doesn't match…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 5, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Hugofsco/oceano
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Hugofsco
- 0.526score
aeo-content-citations
Hugofsco
audit and optimize written content so LLMs (ChatGPT, Perplexity, Claude, Gemini) cite it as a source, and track which pages get cited — use for brand/store…
SkillBFreshness: BClaude Code +9 - 0.479score
aws-solution-architect
Hugofsco
design an AWS architecture (serverless, three-tier, microservices) from requirements, generate CloudFormation/CDK/Terraform, and estimate/optimize costs — use…
SkillCFreshness: CClaude Code +9 - 0.479score
agent-workflow-designer
Hugofsco
pick the right multi-agent/multi-step pattern (sequential, parallel, router, orchestrator, evaluator) and scaffold it before building — use when designing one…
SkillCFreshness: CClaude Code +9 - 0.479score
academic-literature-search
Hugofsco
search real academic literature (PubMed + OpenAlex) with structured, citable metadata instead of generic web search — use when the topic is…
SkillCFreshness: CClaude Code +9 - 0.479score
changelog-generator
Hugofsco
generate a CHANGELOG.md and compute the next semver version from Conventional Commits — use when cutting a release for a real project, or to check what…
SkillCFreshness: CClaude Code +9 - 0.479score
content-humanizer
Hugofsco
rewrite AI-sounding content (store copy, emails, social posts) so it reads like a person wrote it, not a committee — use when content feels robotic, generic…
SkillCFreshness: CClaude Code +9
Cite this page
caveman-mode skill. Agent Mart. https://agentmart.dev/skills/hugofsco-caveman-mode (last updated 2026-10-24)