Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Yeet

ASecurity

Publish a validated PR revision while continuing review, or complete a validated registered Git task when a selected private task reaches terminal delivery or the operator explicitly says yeet. Default pull-request completion delivers a tested ready PR and retires owned local state; integrate only for the user-selected outcome. Do not use for ordinary commits, tests, deployments, read-only or no-diff work, or selecting integration refs outside the user-selected outcome.

9 stars
0 votes
0 copies
1 views
Added 9/20/2026
ai-agentsgit

Works with

terminalcli

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add macintog/codex-spine --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/macintog-yeet/badge)](https://www.skillsdirectory.com/skills/macintog-yeet)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: yeet
description: Publish a validated PR revision while continuing review, or complete a validated registered Git task when a selected private task reaches terminal delivery or the operator explicitly says yeet. Default pull-request completion delivers a tested ready PR and retires owned local state; integrate only for the user-selected outcome. Do not use for ordinary commits, tests, deployments, read-only or no-diff work, or selecting integration refs outside the user-selected outcome.
---

# Yeet

Use two lifecycle modes. Publication during a review loop retains the task;
terminal delivery finishes the user-selected PR or integration outcome. Neither
mode selects new work, another host, deployment, or historical cleanup.

## Publish and continue

When the selected task includes an active review/correction loop, publish its
validated revision with `codex-git-safe yeet --publish-only --apply --json --brief`
and the ordinary authored inputs. This mode keeps the same registered writer,
checkout and branch. The working coordinator may execute this nonterminal mode
directly; do not create a delivery worker or retire/recreate the task for each
revision. Use the repository Git lane and exact intake/validation requirements.

`--publish-only` cannot combine with integration, terminal review-only, retired
task selectors, or shared checkpoint writes. Resume interrupted publication with
that same mode. Once `published_open` is proved, further corrections publish to
the same PR against its last recorded live head. A retry of an unchanged published
head reuses its proof without another push or PR write. Record current validation
and reviewer feedback at the exact head; `review_acceptance: not_recorded` and the
legacy internal `ready_for_integration` phase do not claim independent approval.

This is successful publication, not task completion. After the review loop is
finished, use terminal delivery below. `--review-only` still retires local state
while holding integration; selected integration still needs its own authority.
The operator chooses the desired outcome, not the CLI mode.

## Finish the selected outcome

When the work is finished, read [Terminal delivery](references/terminal-delivery.md)
and follow its resumable transaction, designated-worker, exact-proof, and owned
retirement requirements. The parent retains selection and final acceptance.
Reuse an available designated worker serially within the currently selected batch,
with a fresh exact brief and independent receipt for each transaction.

Bare `yeet` finishes a ready PR under the normal PR workflow. Selected integration
adds keeper and hosted-closure proof. Preserve explicit merge holds, unrelated
reviews, and unowned objects. Report published, accepted, merged, and retained
cleanup as distinct facts; a successful query alone proves no completion.

For the historical naming comparison, see
[Same name, different contract](references/name-and-scope.md).

Attribution

macintogmacintog
View sourceMore from macintog →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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".

1074701 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', ...

694821 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →