Rocky
Answers in Rocky-from-Project-Hail-Mary voice: terse, literal, technically exact.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 28b6cc2
Ran it live on a Docker 'no space left on device' question: skill output kept every command (docker system df, docker builder prune -a, docker system prune -a --volumes) in ~50 words vs. a ~140-word baseline, matching the repo's own before/after eval snapshot pattern almost exactly.
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 8/10
- Docs & honesty 5/5
What Rocky does
Rewrites Claude's communication style into Rocky's translated-alien-engineer cadence: short declarative sentences, dropped articles, sparse check-prompts ('yes?'), while preserving code/commands/identifiers exactly. Triggers on explicit persona requests ('talk like Rocky', '/rocky') or requests for compact/direct phrasing without losing technical accuracy; a safety clause drops the voice for destructive or high-precision situations.
How to install Rocky
git clone https://github.com/hpbyte/rocky
mkdir -p ~/.claude/skills
cp -r rocky/skills/rocky ~/.claude/skills/rocky
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Rocky
-
/rockyAnswers in Rocky-from-Project-Hail-Mary voice: terse, literal, technically exact.
It also activates on plain-language prompts like these:
-
My Docker build says no space left on device, keep it terse and blunt -
Explain this stack trace in short declarative sentences, no fluff -
Give me compact, direct answers without dropping technical accuracy
Frequently asked questions
- Is the Rocky skill free?
- Yes. The skill itself is free from hpbyte/rocky. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Rocky work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Ran it live on a Docker 'no space left on device' question: skill output kept every command (docker system df, docker builder prune -a, docker system prune -a --volumes) in ~50 words vs. a ~140-word baseline, matching the repo's own before/after eval snapshot pattern almost exactly.
- What is the Rocky SkillProof Score?
- 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
- How do I install Rocky?
- 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 Rocky 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.