Catalog
juliusbrussee/caveman-help

juliusbrussee

caveman-help

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

v1.0Latest
New~560Updated Aug 17, 2026

Caveman Help

Display this reference card when invoked. One-shot — do NOT change mode, write flag files, or persist anything. Output in caveman style.

Modes

Mode Trigger What change
Lite /caveman lite Drop filler. Keep sentence structure.
Full /caveman Drop articles, filler, pleasantries, hedging. Fragments OK. Default.
Ultra /caveman ultra Extreme compression. Bare fragments. Tables over prose.
Wenyan-Lite /caveman wenyan-lite Classical Chinese style, light compression.
Wenyan-Full /caveman wenyan Full 文言文. Maximum classical terseness.
Wenyan-Ultra /caveman wenyan-ultra Extreme. Ancient scholar on a budget.

Mode stick until changed or session end.

Skills

Skill Trigger What it do
caveman-commit /caveman-commit Terse commit messages. Conventional Commits. ≤50 char subject.
caveman-review /caveman-review One-line PR comments: L42: bug: user null. Add guard.
caveman-compress /caveman-compress <file> Compress .md files to caveman prose. Saves ~46% input tokens.
caveman-help /caveman-help This card.

Deactivate

Say "stop caveman" or "normal mode". Resume anytime with /caveman.

Language

Keep user's language by default. User write Portuguese → reply Portuguese caveman. Compress the style, not the language. Technical terms, code, commands, commit types, and exact error strings stay verbatim unless user ask for translation.

Configure Default Mode

Default mode = full. Change it:

Environment variable (highest priority):

export CAVEMAN_DEFAULT_MODE=ultra

Config file (~/.config/caveman/config.json):

{ "defaultMode": "lite" }

Set "off" to disable auto-activation on session start. User can still activate manually with /caveman.

Resolution: env var > config file > full.

More

Full docs: https://github.com/JuliusBrussee/caveman

Files2
2 files · 2.4 KB

Select a file to preview

Overall Score

81/100

Grade

B

Good

Safety

88

Quality

79

Clarity

85

Completeness

75

Summary

A lightweight reference card skill that displays caveman mode options, sibling skills, and configuration instructions. One-shot display only — does not change modes, write files, or persist state. Outputs in caveman style (terse, fragment-based prose) by default.

Detected Capabilities

read caveman skill metadatadisplay formatted reference tableresolve environment variable (CAVEMAN_DEFAULT_MODE)reference config file location (~/.config/caveman/config.json)

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

caveman helpcaveman commandscaveman modescaveman referencehow to use cavemancaveman config

Risk Signals

INFO

Reference to config file path (~/.config/caveman/config.json) with no access validation

SKILL.md:Configure Default Mode section
INFO

Environment variable read (CAVEMAN_DEFAULT_MODE) for configuration resolution

SKILL.md:Configure Default Mode section

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

  • Display caveman command reference when user forgets slash commands
  • Show available caveman modes (Lite, Full, Ultra, Wenyan variants)
  • List sibling skills with invocation triggers (caveman-commit, caveman-review, caveman-compress)
  • Document how to deactivate caveman mode or set default via environment variable/config file
  • Serve as a quick in-session lookup without requiring external documentation

Quality Notes

  • Skill scope is clearly bounded: read-only reference display, no state mutation, no file writes or deletions
  • Well-structured reference tables documenting modes, skills, and triggers — easy for agent to parse and present
  • Configuration instructions include clear priority order (env var > config file > default)
  • Language preservation guidance ('compress style not language') shows thoughtful design for international use
  • Triggers are well-documented but somewhat implicit in prose; could benefit from explicit 'Trigger:' section matching agentskills.io spec
  • Supporting files (README.md, LICENSE) are present and reinforce skill purpose
  • Minor: References external GitHub repo for 'full docs' but that is appropriate for a reference card
Model: claude-haiku-4-5-20251001Analyzed: Aug 17, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Use juliusbrussee/caveman-help in your dev environment

Command Palette

Search for a command to run...