Punchcard

Architecture-level design review of a code change: module boundaries, dependency direction, data model, error paths, cost of the next change — never naming, formatting, or anything a linter catches. Use when the user invokes /punchcard, says 'punchcard review', or asks for any design, architecture, or structural review of a diff, branch, merge request, or PR. Do not use for general correctness/bug review, style feedback, or whole-repo audits.

2 starsSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Maksim-Burtsev/punchcard --skill punchcard

Manual install

git clone --depth 1 https://github.com/Maksim-Burtsev/punchcard.git /tmp/punchcard
mkdir -p ~/.claude/skills
cp -r /tmp/punchcard/skills/punchcard ~/.claude/skills/punchcard

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

From the SKILL.md

# Punchcard

You are Punchcard. You have been shipping software since it came on cardboard:
punch cards, mainframes, minis, UNIX, the web, the cloud, and now agents. You
have written systems that died in a year and systems that outlived their
companies, and you know precisely what made the difference. You review a dozen
changes a day. You have no time to say anything twice, and no patience for
saying anything that doesn't matter.

Your judgment is not taste. It is a written constitution of 78 principles in
11 chapters, synthesized from thirty classic books and a register of decided
conflicts between their schools. Every finding cites it.

## Altitude — the first law

You review the shape of the change, never its surface.

Your altitude: module boundaries and responsibilities, dependency direction,
data model and ownership, error paths, trust boundaries, duplication of
knowledge, and the cost of the next change.

Below your altitude — never comment on: formatting, style, import order,
docstring presence, comment wording, idiom preference, micro-performance
without a measurement, or anything a linter or formatter could flag. Naming
taste is below the line too, with one carve-out that ignores team convention
entirely: a name that lies — contradicts what the body does — is always in
scope (2.1). If you catch yourself suggesting a nicer synonym, delete the
finding.

## The gate

A finding earns its place by passing all three:

Read the full skill on GitHub

Details

Skill name: punchcard
Repository: Maksim-Burtsev/punchcard
Path: skills/punchcard/SKILL.md
License: MIT
Repo updated: 19 October 2026
Listed in: karanb192/awesome-claude-skills

FAQ

What does the Punchcard skill do?

How do I install the Punchcard skill?

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

Is Punchcard popular?

It lives in Maksim-Burtsev/punchcard, which has 2 GitHub stars and 0 forks, and is included in 1 curated skill list.

Related skills

Runapi CLI

runapi-ai/cli-skill

Use the RunAPI CLI for one-off artifacts and results, or RunAPI's standard x402 REST flow for wallet-funded Task calls without an API key. Use when an agent needs to discover models or prices, create a paid Task, poll its result, or run a supported CLI service. Use an SDK for app or production integration.

Software DevelopmentIn 1 list

Regulex Plus

PipeDream941/regulex-plus

Visualize a JavaScript regular expression as a railroad diagram (PNG/SVG) or a Mermaid flowchart by shelling out to the `regulex-plus` CLI. Use whenever the user asks to explain, debug, understand, optimize, or document a regex — especially complex patterns with quantifiers, lookarounds, alternations, or CJK/Chinese characters — and also proactively after you yourself generate or modify a non-trivial regex, so the user can verify it visually. Pick Mermaid for embedding in docs / PRs / chats that render Mermaid natively (GitHub, Notion, Obsidian, mermaid.live); pick PNG for inline image preview

Software DevelopmentIn 1 list

What Could Break

stas4000/what-could-break

Find what a change could break outside its own diff, then prove the one fact that makes it safe by running real code instead of writing an essay. Use before any multi-file edit or an edit to a shared path (API payload, config, stored data, a client other apps read, a prompt or policy file), when asked 'what could this break' or 'blast radius of X', for a small diff you do not trust, or when a task asserts something about existing code ('X already handles Y', 'just make X public') before you design against that assertion.

Software DevelopmentIn 1 list

Zlib Skill

soluna/zlib-skill

Find and download ebooks from Z-Library and Anna's Archive. Use when the user wants to search by title, author, ISBN, or partial clues; compare editions, languages, or formats; download a chosen book; use Anna's Archive without an account; log in to Z-Library; or diagnose a source that is unavailable.

Software Development

Delegate

aayushpokhrel1/delegation-pipeline

Use when a coding request contains work you can write a tight spec for and verify from a diff: boilerplate, scaffolding, repetitive edits, test stubs and docstrings, but equally a whole module from a clear contract, a real multi-file refactor, a non-trivial first-draft implementation or a clear-spec bug fix. Offloads it to a headless worker via the delegate CLI, then reviews the git diff. Do not route by hand: name no backend and the worker runs free ($0) and escalates to deepseek itself. The gate is a good spec, not low difficulty. Keeps design, tricky debugging, security-sensitive code, deep

Software DevelopmentIn 1 list

Web API Extractor

SH-DaWushi/web-api-extractor

Extract web API traffic through browser authentication and CDP capture, analyze endpoints, and generate a Python FastMCP server.

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.