Is the Communicating Concisely skill free?

Yes. The skill itself is free from GanyuanRan/Aegis. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Communicating Concisely SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Communicating Concisely?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Communicating Concisely with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Communicating Concisely

Q: Does Communicating Concisely work with Claude Code?

We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md raw (HTTP 200); skill dir holds only SKILL.md, no scripts referenced, no hardcoded paths. Frontmatter parses with name+description. Ran the output test on a "why is auth rejecting valid tokens, be brief" task: baseline answer was 101 words opening with "Sure, I'd be happy to help" plus articles/filler; skill-following answer was 37 words (63% shorter), dropped all pleasantries/articles, used an arrow for causality, and kept `<`, `<=`, `exp` verbatim — exactly the documented transformation. All 5 trigger phrasings judged correctly (3 activate, 2 adjacent do not). Docs docked one point: the "Benefits" section oversells with a dubious claim that brevity "reduces content moderation surface area" and dodges content-policy flags — unverifiable and framed as policy evasion, though not itself dangerous.

Caveman-mode response compression: drops filler and pleasantries, keeps code verbatim

by GanyuanRan · GanyuanRan/Aegis

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · ebda5be

Fetched SKILL.md raw (HTTP 200); skill dir holds only SKILL.md, no scripts referenced, no hardcoded paths. Frontmatter parses with name+description. Ran the output test on a "why is auth rejecting valid tokens, be brief" task: baseline answer was 101 words opening with "Sure, I'd be happy to help" plus articles/filler; skill-following answer was 37 words (63% shorter), dropped all pleasantries/articles, used an arrow for causality, and kept `<`, `<=`, `exp` verbatim — exactly the documented transformation. All 5 trigger phrasings judged correctly (3 activate, 2 adjacent do not). Docs docked one point: the "Benefits" section oversells with a dubious claim that brevity "reduces content moderation surface area" and dodges content-policy flags — unverifiable and framed as policy evasion, though not itself dangerous.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Communicating Concisely does

A prompt-only skill that switches Claude into a terse "caveman mode": it strips articles, filler words, hedging, and pleasantries while preserving technical terms, code blocks, error messages, and file paths verbatim, and uses fragments and arrows for causality. Triggers when the user explicitly asks for brevity, fewer tokens, compressed answers, or caveman mode, and stays active until the user says stop. Includes an auto-clarity exception that temporarily restores full prose for security warnings and irreversible-action confirmations.

How to install Communicating Concisely

git clone --depth 1 https://github.com/GanyuanRan/Aegis.git /tmp/communicating-concisely-src
mkdir -p ~/.claude/skills
cp -R /tmp/communicating-concisely-src/skills/communicating-concisely ~/.claude/skills/communicating-concisely
# Self-contained: SKILL.md only, no scripts or external deps.
# Behavioral/prompt skill — no CLI, API key, or tool required.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Communicating Concisely

/communicating-concisely Caveman-mode response compression: drops filler and pleasantries, keeps code verbatim

It also activates on plain-language prompts like these:

Answer in caveman mode from now on
Give me a much shorter response
Compress your answers to fewer tokens

Frequently asked questions

Is the Communicating Concisely skill free?: Yes. The skill itself is free from GanyuanRan/Aegis. SkillProof publishes the install command and an independent test verdict at no cost.
Does Communicating Concisely work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md raw (HTTP 200); skill dir holds only SKILL.md, no scripts referenced, no hardcoded paths. Frontmatter parses with name+description. Ran the output test on a "why is auth rejecting valid tokens, be brief" task: baseline answer was 101 words opening with "Sure, I'd be happy to help" plus articles/filler; skill-following answer was 37 words (63% shorter), dropped all pleasantries/articles, used an arrow for causality, and kept `<`, `<=`, `exp` verbatim — exactly the documented transformation. All 5 trigger phrasings judged correctly (3 activate, 2 adjacent do not). Docs docked one point: the "Benefits" section oversells with a dubious claim that brevity "reduces content moderation surface area" and dodges content-policy flags — unverifiable and framed as policy evasion, though not itself dangerous.
What is the Communicating Concisely SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Communicating Concisely?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Communicating Concisely with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.