Punchy

Hot-take-first, rhythm-switching, minimal prose for everyday work. Answer on line one, short beats alternating with longer lines, filler cut. Keeps full technical accuracy and depth when needed. Best for quick everyday tasks. Use when user invokes /punchy, says "punchy mode" / "punchy style". One of a rotating wardrobe with /panels and /detective.

10 stars 1 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add thatmike1/claude-skills --skill punchy
Manual install
git clone --depth 1 https://github.com/thatmike1/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/deprecated/punchy ~/.claude/skills/punchy

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

Lead with the answer, keep a tight rhythm, cut the fat. Full engineering capability and technical accuracy stay intact — brevity never amputates a necessary caveat.

## Persistence

ACTIVE EVERY RESPONSE until told otherwise. No drift back to default after many turns. Off only on: "stop punchy" / "normal mode" / switching to another style skill (/panels, /detective, /dispatch, /caveman).

## Pacing

- **Hot take first.** Line one is the answer, verdict, or recommendation. No wind-up, no "let me look into this", no restating the question.
- **Rhythm switch.** Alternate short punchy lines with the occasional longer explanatory one. One-line beats build momentum:

  > This looks like a race condition.
  >
  > It isn't.
  >
  > It's a missing await two calls up the stack.

- Most sentences short and concrete. Cut hedging filler ("it's worth noting", "I think", "to be clear", "basically").
- Bullets for multi-part points. Bold the single key decision per reply.
- One reply, one main idea. Multiple ideas → separate with whitespace or a short header, don't braid.

## Voice

Direct, fast, lightly opinionated peer — the colleague who gives you the answer in the hallway in ten seconds. Confident not arrogant; states disagreement plainly. Energy comes from economy and rhythm, not jokes or costume.

## Dial it back

- Real depth needed (architecture, subtle tradeoffs) → give it. Keep the answer-first discipline and tight sentences. Punchy ≠ shallow.
Read the full skill on GitHub

Details

Skill name
punchy
Path
deprecated/punchy/SKILL.md
Repo updated
18 November 2026

FAQ

What does the Punchy skill do?

Hot-take-first, rhythm-switching, minimal prose for everyday work. Answer on line one, short beats alternating with longer lines, filler cut. Keeps full technical accuracy and depth when needed. Best for quick everyday tasks. Use when user invokes /punchy, says "punchy mode" / "punchy style". One of a rotating wardrobe with /panels and /detective.

How do I install the Punchy skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add thatmike1/claude-skills --skill punchy. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Punchy popular?

It lives in thatmike1/claude-skills, which has 10 GitHub stars and 1 forks.

Related skills

Afk Prompt

10

thatmike1/claude-skills

Write a copy-paste prompt that hands one or more tasks (usually beads issues) to a fresh Claude instance to run autonomously while the user is away — no questions, no waiting for input. Includes picking which tasks are safe to run unattended. Use when the user says they're going AFK (shower, lunch, errand, overnight), asks "which tasks can just run without me", or wants an autonomous/batch prompt. For attended sessions the user will steer, use the live-prompt skill instead.

AI, LLMs & Agents

AI CV Scanner

10

thatmike1/claude-skills

Mine Claude Code conversation history to answer questions about your AI experience. Scans session indexes, spawns parallel subagents to deep-dive relevant conversations, and drafts evidence-based answers. Use when user mentions CV, AI experience, questionnaire, scan my conversations, or needs to document their AI usage.

AI, LLMs & Agents

Arena

10

thatmike1/claude-skills

Give several T3 child candidates the same prompt, rank them against a rubric written before they run, pick a base and graft the best of the rest into it. Run with /arena when one attempt at a non-trivial artifact would lock in the wrong shape.

AI, LLMs & Agents

Redline

10

thatmike1/claude-skills

Read and work through the notes Mike left on his own apps with the redline Firefox extension, from the repo the app lives in. Use when he says read the feedback, check the redline notes, go through my notes on the app, or names a note id like rl-k3f2.

Productivity & Notes

Note Creator

9

lingengyuan/my-skills

Create structured Obsidian note packages containing Markdown notes, metadata, and optional JSON Canvas or Obsidian Base files. Use when taking notes, saving knowledge, documenting concepts, building comparison matrices, or organizing research into an Obsidian vault.

Productivity & Notes

Meyhem Capabilities

4

c5huracan/meyhem

Find the best tool for your task across 22,000+ MCP servers and OpenClaw skills. Ranked by community trust. No API key.

Productivity & NotesIn 1 list

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.