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/thorstarlord-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 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
- 41 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 ThorStarlord/interface-skills, MIT.
More from ThorStarlord/interface-skills
- 0.502score
repo-sensemaker
ThorStarlord
analyze a repository to produce a repository sensemaking brief.
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
problem-framer
ThorStarlord
analyze a vague idea or repository fog to produce a structured problem frame.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
setup-interface-skills
ThorStarlord
Configure a repository for Interface Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
prompt-handoff
ThorStarlord
convert a sensemaking artifact into a ready-to-copy prompt for the next specialized skill.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
handoff
ThorStarlord
Use when the user ends a session, asks for a session summary, or needs to create a handoff document for another agent to continue the work.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
ui-brief
ThorStarlord
Turn a vague UI idea into a structured product and design brief before any layout, component, or code work begins.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
sensemaking-docs-reconciler
ThorStarlord
challenge the sensemaking repository's architecture against its documentation, registries, templates, and examples.
SkillCFreshness: C★ 1Claude Code +9 - 0.477score
git-guardrails-claude-code
ThorStarlord
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.
SkillCFreshness: C★ 1Claude Code +9 - 0.477score
diagnose
ThorStarlord
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
improve-codebase-architecture
ThorStarlord
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
grill-with-docs
ThorStarlord
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as…
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill-me
ThorStarlord
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 9
- Last commit (this folder)
- May 13, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ThorStarlord/interface-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ThorStarlord
- 0.570score
change-impact-analysis
ThorStarlord
analyze a bounded contemplated or completed repository change to identify decision-relevant affected…
SkillAFreshness: AClaude Code +9 - 0.529score
acceptance-criteria
ThorStarlord
Turn a bounded user story, feature rule, or delivery requirement into explicit testable acceptance scenarios covering happy paths, edge cases, errors, state…
SkillBFreshness: BClaude Code +9 - 0.529score
battlecard
ThorStarlord
Create an evidence-aware competitive battlecard for a named product, competitor, and segment using current market, product, pricing, review, and win-loss…
SkillBFreshness: BClaude Code +9 - 0.529score
competitive-analysis
ThorStarlord
Compare a product with named direct or indirect alternatives using source-dated market evidence, identify parity, gaps, strengths, weaknesses, threats, and…
SkillBFreshness: BClaude Code +9 - 0.529score
customer-journey
ThorStarlord
Map a bounded customer journey for a named persona or segment across relevant stages, touchpoints, actions, questions, emotions, pain points, opportunities…
SkillBFreshness: BClaude Code +9 - 0.529score
discovery
ThorStarlord
Frame an uncertain product problem into evidence-aware problem hypotheses, learning questions, validation approaches, and decision criteria.
SkillBFreshness: BClaude Code +9
Cite this page
caveman skill. Agent Mart. https://agentmart.dev/skills/thorstarlord-caveman (last updated 2026-10-24)