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

Yeet

ASecurity

Ship fast with throwaway automation: quick scripts and one-off automations built in minutes, used, then discarded. Use when a small annoying task needs doing now, not a system designed.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgodebuggingapi

Works with

api

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill yeet --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Yeet?

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

Security grade badge for Yeet
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-yeet-awesome-muse-skills/badge)](https://www.skillsdirectory.com/skills/aicodedecode-yeet-awesome-muse-skills)

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: yeet
description: Ship fast with throwaway automation: quick scripts and one-off automations built in minutes, used, then discarded. Use when a small annoying task needs doing now, not a system designed.
category: workflow-automation
---

# Yeet

## Overview

Yeet is the discipline of fast, disposable automation: a 20-line script written in 15 minutes that saves hours this week — then gets deleted without ceremony.

Not every automation deserves architecture. Some tasks need doing once, urgently, and perfectly is the enemy of done.

The yeet mindset: bias to action, timeboxed effort, good-enough correctness, and zero guilt about deleting it after.

## When to use

- A one-off data cleanup or migration needed today
- Repetitive task you'll do 50 times this week then never again
- Prototyping an automation before building it properly
- Quick personal productivity hacks
- When 'proper solution' estimates say 2 weeks and you need it now

## Core concepts

- **Timebox the build.**
  15-60 minutes max. If it takes longer, it's not a yeet — it's a project. Set a timer; ship or stop.
- **Good-enough correctness.**
  Handle the 95% case visibly; log or skip the edge cases. A yeet that handles everything is just slow engineering.
- **Read-only first.**
  Prefer scripts that read and report over scripts that write. When writing: dry-run mode, backups, and a revert plan.
- **Disposable by design.**
  One file, inline config, minimal dependencies. If it needs a README and tests, it's graduated beyond yeet.
- **The 3x rule.**
  Yeet when: time to build < (time saved / 3). Rough math keeps you from gold-plating throwaways.
- **Know when to graduate.**
  Used three times? Promoted to a real script with error handling. Used by others? Now it's a tool with docs. Yeets have lifecycles.
- **Delete without ceremony.**
  Task done, yeet served its purpose: delete it. A graveyard of one-off scripts becomes unmaintainable clutter.
- **Log what it did.**
  Even throwaways should print what they changed. Future debugging (including 'what did that script do?') needs the trail.

## Practical workflow

1. **Identify the annoyance.**
   What's the concrete, painful, repetitive thing? Name it in one sentence. Vague annoyances make vague scripts.
2. **Timebox it.**
   Decide upfront: 20 minutes? An hour? The box is the discipline — it forces the simple solution.
3. **Write the smallest script.**
   One file, standard library preferred, hardcoded values fine. Read the data, do the thing, print results.
4. **Dry-run first.**
   If it writes/deletes: preview mode showing what would happen. Review the preview. Then run for real.
5. **Run and verify.**
   Check the output actually fixed the problem. Spot-check results; yeets earn trust through verification, not ceremony.
6. **Decide: keep or delete.**
   One-off done? Delete. Recurring? Graduate it (error handling, config, docs) or schedule the next yeet.
7. **Note the pattern.**
   Yeeted the same class of task twice? That's a signal — the third time, build it properly.
8. **Share the trick.**
   A yeet that helped you might help the team. Share the snippet; let usefulness decide if it graduates.

## Common pitfalls

- **Yeeting the irreversible.**
  Throwaway scripts doing bulk deletes without dry-run or backup. Speed doesn't excuse recklessness with destructive ops.
- **No timebox.**
  'Quick script' becoming a 3-day project. The timebox is what makes it a yeet; without it, it's just sloppy engineering.
- **Keeping every yeet.**
  200 throwaway scripts in ~/scripts, none documented. Delete on completion or graduate deliberately.
- **Yeeting the recurring.**
  Manually re-running a 'one-off' script weekly for a year. Third use = graduate it properly.
- **No verification.**
  Assuming the script worked. Spot-check output — yeets are fast, not infallible.
- **Secrets in throwaways.**
  API keys pasted into quick scripts, then the script gets shared or committed. Even yeets use env vars.
- **Yeeting what should be a product.**
  Customer-facing or team-critical workflows built as throwaways. Yeets are for internal, reversible, timeboxed needs.
- **Analysis paralysis.**
  Spending an hour deciding whether to yeet. The whole point is speed — if the 3x rule says yes, start typing.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
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', ...

698431 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 →