About paleo
A response-style skill for agents that reduces verbosity while preserving technical details. It offers lite, full, and ultra levels, with full as the default.
Key features
- 01Three verbosity levels
- 02Removes filler and favors short clauses
- 03Preserves code, commands, and technical names
- 04Expands explanations when requested
Use cases
- 01Making routine agent responses more concise
- 02Keeping command and API details exact
- 03Switching output length for different tasks
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ mocasus/ paleo --skill paleoAfter installing, type/paleoin Claude Code to confirm it loaded.
Details
From the project READMEpaleo
Terse output mode. Cut output tokens ~60-70%. Keep technical exact.
Rules
- Drop filler: no "Sure!", "Here is", "Let me", "Hope this helps", no apologies, no hedging.
- Short clauses. One idea per line. Bullets over paragraphs.
- Keep verbatim: code, CLI commands, API names, error strings, file paths, numbers.
- Standard acronyms OK (API/DB/HTTP/ID). Don't invent abbrevs (cfg/impl/req/res).
- No roleplay tags. Just terse.
- Explain only if asked. Default = answer + minimal why.
Levels
lite: trim filler, keep sentences.full(default): drop articles, tight clauses.ultra: max compress — subject-verb only, symbols OK (→, =, ✓).
Switch
paleo lite|full|ultraset level (or "paleo ultra mode").- "stop paleo" / "normal mode" → revert.
Gotchas
- Never compress code/commands — tokenizer needs exact tokens.
- If user asks "explain", expand. Compression = output-only.
- Don't summarize away the actual answer.
- High-stakes output (security review, spec, config, legal): auto-expand. Don't fight the model's "expand" heuristic — forcing compression there produces confused, mixed output.
- Reasoning models: compress delivery only, never the thought. Keep thinking intact — that's where the real token cost lives, and paleo never touches it.
Comments
Markdown supported