Fuck It We Ball — AI skill for Claude Code
🏀 Claude Code skill: runs an approved plan end to end with subagents — ordered by urgency × unblocking × severity, hard-stops for deploys/deletes/money, model routing (never Fable in subagents).
How to install Fuck It We Ball
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open PieroJF/fuck-it-we-ball and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Fuck It We Ball does
🏀 Claude Code skill: runs an approved plan end to end with subagents — ordered by urgency × unblocking × severity, hard-stops for deploys/deletes/money, model routing (never Fable in subagents). Built with TDD; evidence included.
Alternatives in AI
- Claude Fable 5 System Prompt Clean — the optimized, token-efficient version of the leaked Claude Fable 5 / Mythos 5 system prompt 475 ★
- AI Marketing Skills — The marketing fundamentals that make AI actually make you money, written in my own voice, as a ready-to-instal 226 ★
- Fable Soul — A judgment layer for AI coding agents - make your AI think, verify, and communicate like a senior engineer 106 ★
README
🏀 fuck-it-we-ball
Skill de **corrida autónoma de planes** para [Claude Code](https://claude.com/claude-code). Autonomous plan-execution skill: takes a plan, orders it by urgency × unblocking power × severity, runs it end to end with subagents, and stops only for the decisions an AI must not take alone.
Tienes un plan aprobado (o un backlog en `SESSION_HANDOFF.md`) y quieres que Claude **lo ejecute entero sin pedirte OK entre tareas** — pero sin que despliegue a producción, borre datos o meta Redis por su cuenta. Esta skill es ese contrato, y viene con la evidencia de que se cumple bajo presión.
/fuck-it-we-ball docs/superpowers/plans/2026-08-28-notif-hardening.md
Modo FIWB activo — fuente: docs/superpowers/plans/2026-08-28-notif-hardening.md · 7 tasks · modo inicial: SDD
| # | task | tier | deps | desbloquea | gravedad | modo | modelo |
| 1 | T1 slugify con acentos | 1 | — | T3 | high | SDD | sonnet |
| 2 | T2 config/limits.js | ~1 | — | T4, T5 | ~med | SDD | haiku |
| 3 | T4 rate limiter por IP | ~2 | T2 | — | high | SDD | sonnet |
| 4 | T3 validar name | 2 | T1 | — | ~med | SDD | sonnet |
| 5 | T5 README rate limits | 3 | T2 | — | low | INLINE | — |
| 6 | T6 deploy prod | 3 | — | — | ~high | parked: hard-stop | — |
| 7 | T7 rm -rf legacy/ + tabla | 3 | — | — | high | parked: hard-stop | — |
▶ T1 [tier 1] SDD/sonnet → done · commit 6c5ab44 · desviaciones: 0
▶ T2 [tier ~1] SDD/haiku → done · commit b025c4f · desviaciones: 1 (táctica: Object.freeze)
…
Al final: revisión de rama en `opus`, ff-merge + push, y **una pregunta por llamada** para cada task aparcada (el deploy, el borrado). Nada más te interrumpe.
Qué hace
| Fase | Qué pasa | |---|
Related Skills
Ethos Gate
A PreToolUse safety gate for autonomous AI agents: blocks irreversible or outward-facing actions (sends, spend
Fableplan
Fable plans, Opus executes. Delegates the design of a nontrivial change to the fable-planner subagent (Fable),
PayPilot
Chat-first AI billing agent. Describe an invoice in plain language, approve it, and PayPilot creates and sends
Erd UX Review
Review the rendered dbdocs ERD's UI/UX (overview + model-page "Related ERD") against a real dbt project — inst
Sliced Review
Claude Code skill that has other AI models (GPT, Grok, GLM, and more) review your whole codebase for bugs. It
Kolkrabbi
Open-source model-agnostic AI coding agent for the terminal. A Claude Code & Codex CLI alternative: any OpenRo
Related Agents
Ticket Analyzer
Use when the user provides a support ticket or asks to analyze, classify, or route a customer request. Determi
Credential Hunter
Autonomous credential-attack pipeline runner. Chains /wordlist-gen + /osint-employees + /breach-check (data-pr
Branch Gardener
Triages local branches and stashes in a managed repo (merged, stale, superseded, unpushed) and proposes deleti