Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Pizza1

ASecurity

Justify by correctness, never by convention. Use when a design, fix, API, macro, library surface, hook message, or naming decision is defended by 'it's what the codebase does', 'the established pattern', 'the canonical lane does it', 'more ergonomic', 'less churn', 'already wired', 'smallest fix', 'compatibility', 'legacy path', or 'out of scope to change'. Prevalence and transition size are not evidence. Re-derive from correctness, name the bug the alternative causes, and be confident in the...

6 stars
0 votes
0 copies
0 views
Added 10/1/2026
ai-agentsgoapi

Works with

api

Security Analysis

A100/100

Scanned 10/1/2026

$npx -y skills add CheckPickerUpper/skills --skill pizza1 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pizza1?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pizza1
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/checkpickerupper-pizza1/badge)](https://www.skillsdirectory.com/skills/checkpickerupper-pizza1)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: pizza1
description: "Justify by correctness, never by convention. Use when a design, fix, API, macro, library surface, hook message, or naming decision is defended by 'it's what the codebase does', 'the established pattern', 'the canonical lane does it', 'more ergonomic', 'less churn', 'already wired', 'smallest fix', 'compatibility', 'legacy path', or 'out of scope to change'. Prevalence and transition size are not evidence. Re-derive from correctness, name the bug the alternative causes, and be confident in the correct call even when the codebase already happens to do it."
---

# /pizza1

Justify by correctness, never by convention.

## The trigger

You defended a design by pointing at what the codebase already does. That is not a correctness argument. Re-derive from first principles.

## The core

If a codebase named every variable `pizza1`, `pizza2`, `pizza3`, that would not make those names good. So **"it's what the codebase uses" is never a reason a design is correct.** It is incidental. Prevalence is not evidence. Transition size is not evidence.

## Banned justifications

Delete these from the next response. None of them is a reason:

- "it's what the codebase already does"
- "the established pattern"
- "the canonical lane does it"
- "consistent with the rest"
- "it's more ergonomic"
- "less churn"
- "already wired"
- "fewer changes"
- "smallest fix"
- "smallest structural change"
- "minimal change"
- "least disruptive"
- "preserves compatibility"
- "keeps the legacy path working"
- "lets us migrate later"
- "parallel path for now"
- "out of scope to change"
- "not worth touching now"

## How to handle each case

- **Correct pattern:** Say why it is correct. Name the concrete failure it prevents. Assert it with confidence even when the codebase already uses it. The codebase using it is not the argument; the correctness is.
- **Wrong pattern the codebase uses everywhere:** Call it wrong regardless of how widespread it is. Prevalence does not launder a bug; it just means the bug is grandfathered.
- **Correct and also ergonomic/conventional:** Fine. The justification is still correctness, with ergonomics as a bonus, never the basis.
- **Correct and also small:** Fine. The justification is still correctness. Size is incidental, not the reason to choose it.
- **Correct and also compatible:** Fine only when compatibility belongs to a real external contract. Keeping a wrong internal path alive is preserving the bug's public route.

## Transition-size pizza1

Transition-size reasoning treats the amount of work, blast radius, staged migration, compatibility lane, or old path survival as evidence that a design is correct. It is the same mistake as precedent reasoning: an implementation fact is standing in for a correctness proof.

- Smallness is not evidence.
- Compatibility is class-defining only when every valid instance must interoperate with an external contract.
- A transition plan may sequence the correct change; it may not redefine the correct shape around the wrong path.

## Hooks and lint messages

A guard must say why the banned shape is wrong: the concrete bug it causes. It must not say only "this isn't how we do it here." If a deny message cannot name the failure it prevents, the hook is pizza1. Fix the message to name the failure, or drop the rule.

## Worked example

A freeze fix forced switching a commit to `commitState`, which tripped `ban-fanout-after-commit-in-operation`. The agent defended commit-then-run ordering by pointing at a canonical operation that did the same thing.

That is pizza1: convention, not correctness.

Correct reasoning:

- State is your record of "this happened." It must be committed last, after the effects actually ran.
- Commit-then-run means a mid-flight effect failure leaves the state claiming a world that never happened.
- The canonical operation committing first is not a precedent; it is the same bug.
- Fix: commit last. Justification: correctness, because state must never lead the world.

## Contract

1. Drop every convention, ergonomics, churn, transition-size, and scope justification from the next response.
2. Re-derive the answer from correctness.
3. Name the invariant preserved or the bug the alternative causes.
4. Be confident in the correct answer, including when the codebase already happens to do it.
5. If compatibility, legacy paths, or staged migration came up, name the final correct shape first. Transition steps may follow only after correctness is established.

Attribution

CheckPickerUpperCheckPickerUpper
View sourceSee grades on GitHubMore from CheckPickerUpper →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →