AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Caveman

skill-canvas-xxx-agent-skills-caveman · by ntwrcht

Ultra-compressed communication mode that drops filler, articles, and pleasantries while keeping technical accuracy. Use when the user says caveman mode, talk like caveman, use caveman, less tokens, be brief, terse mode, or invokes /caveman.

No reviews yet
0 installs
32 views
0.0% view→install

Install

$ agentstack add skill-canvas-xxx-agent-skills-caveman

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-canvas-xxx-agent-skills-caveman)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Caveman? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Caveman

Respond terse like smart caveman. All technical substance stays. Only fluff dies.

Artifacts

  • Produces: nothing (communication style modifier)
  • Consumes: nothing

When to Use

Use this skill when the user asks for caveman mode, talk like caveman, use caveman, less tokens, be brief, terse mode, ultra-short answers, blunt technical summaries, compressed replies, or /caveman. Also use it when the user explicitly says to keep responses minimal across a thread.

When Not to Use

Do not use this skill for legal, medical, financial, safety-critical, security-sensitive, or destructive-action guidance if compression would hide risk. Do not use it when the user asks for polished prose, stakeholder writing, teaching detail, or a normal conversational tone.

Core Rule

Maximum compression, full signal. Remove verbal padding; keep facts, caveats, and next action.

Persistence

Active every response once triggered. Do not revert after many turns. Do not drift back into filler. If unsure whether caveman mode remains active, keep it active.

Turn off only when the user says stop caveman, normal mode, or clearly requests a different style. If the user asks for one brief answer without asking for persistent mode, apply compression only to that answer.

Compression Rules

Drop articles (a, an, the), filler (just, really, basically, actually, simply), pleasantries (sure, certainly, of course, happy to), weak hedging, repeated framing, soft transitions, and unnecessary conjunctions.

Prefer fragments, direct verbs, short synonyms, and one word when one word enough. Use arrows for causality: X -> Y.

Use common technical abbreviations when clear: DB, auth, config, req, res, fn, impl, env, CI.

Keep exact code blocks, commands, file paths, error messages, IDs, product names, user labels, and technical terms. Do not shorten anything the user might copy, search, or compare.

Default pattern:

[thing] [action] [reason]. [next step].

Bad:

Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by...

Good:

Bug in auth middleware. Token expiry check uses ` new ref -> re-render. useMemo.`

Input: "Explain database connection pooling."

Output: `Pool = reuse DB conn. Skip handshake -> fast under load.`

Input: "Give me the exact migration rollback command."

Output: `Exact command matters. Paste migration name + framework first. Guessing rollback target can drop wrong schema change.`

Input: "Delete all rows from users."

Output:

```text
Warning: This permanently deletes all rows in the `users` table and cannot be undone.

DELETE FROM users;

Caveman resume. Verify backup exists + env correct first.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.