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

Slop Audit

ASecurity

Hunt for slop in a codebase and remove it: useless tests, unnecessary function wrappers, dead abstractions, copy-pasted helpers, comments that restate code. Use when the user says "slop audit", "find slop", "clean up slop", "what can we delete", "this codebase feels bloated", or runs /theo-mode slop.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsgogit

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add al3rez/theo-mode --skill slop-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Slop Audit?

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

Security grade badge for Slop Audit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/al3rez-slop-audit/badge)](https://www.skillsdirectory.com/skills/al3rez-slop-audit)

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: slop-audit
description: >
  Hunt for slop in a codebase and remove it: useless tests, unnecessary function
  wrappers, dead abstractions, copy-pasted helpers, comments that restate code.
  Use when the user says "slop audit", "find slop", "clean up slop", "what can we
  delete", "this codebase feels bloated", or runs /theo-mode slop.
---

# Slop Audit

Goal: leave the codebase smaller and no less correct. Deletions are the
deliverable. Refactors that add code are out of scope.

## What counts as slop

Look for these, in rough order of payoff:

1. **Tests that cannot fail.** Tests that assert a mock returns what the mock
   was told to return. Tests with no assertions. Snapshot tests nobody reads.
   Tests that duplicate another test with different names.
2. **Pass-through wrappers.** `function getUser(id) { return db.getUser(id) }`.
   One-call-site helpers whose name is longer than their body. Classes with one
   method and no state.
3. **Dead code.** Exports nothing imports. Feature flags that are always on.
   Branches for platforms or versions the project no longer supports.
4. **Defensive noise.** Null checks on values the type system already
   guarantees. try/catch that rethrows. Validation of inputs that come from
   your own code.
5. **Comment slop.** Comments that restate the line below. JSDoc on private
   functions that says `@param id the id`. TODOs older than the last release.
6. **Abstraction slop.** Interfaces with one implementation. Config objects
   with one caller. Generic utilities used exactly once.

## Process

1. **Scope.** Count source and test files. If over ~300 files, pick the three
   directories with the most churn (`git log --format= --name-only | sort |
   uniq -c | sort -rn | head`) and audit those first. Say which.
2. **Find candidates fast.** Use the tools the repo already has: `knip` or
   `ts-prune` for dead exports, coverage output for untested-but-tested-looking
   code, `grep -rn "return .*(" --include=*.ts` for wrappers. Do not read every
   file top to bottom.
3. **Verify each deletion is safe** before making it:
   - Wrapper: every call site can call the wrapped thing directly.
   - Test: the test either cannot fail or is covered by another test. Prove it
     by temporarily breaking the code under test and watching the test stay
     green.
   - Dead export: grep the whole repo including configs, scripts, and docs.
4. **Delete in batches** of related changes. Run the test suite after each
   batch, not after each file. Commit each batch with a message that says what
   was removed and why it was safe.
5. **Report** as a table: what was removed, lines deleted, how you proved it
   was safe. Total lines deleted at the bottom.

## Do not

- Do not "clean up" style, naming, or formatting. That is not slop, that is
  churn.
- Do not delete tests that exercise real behavior just because they are ugly.
- Do not replace a wrapper with a different wrapper.
- Do not touch generated files, vendored code, or migrations.

Attribution

al3rezal3rez
View sourceSee grades on GitHubMore from al3rez →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

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 Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 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', ...

697551 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 →