By Hainrixz
Subject any idea, plan, or project to a structured eight-angle devil's advocate critique that identifies fatal flaws, assumptions, and blind spots, delivering a prioritized verdict of what to fix before investing resources.
The skill that turns Claude against you and tears your idea apart.
English · Español
A Claude Code skill (and plugin) that takes on the role of a hostile devil's advocate: it grabs your idea, plan, pitch, or an entire project and critiques it hard — no validation, no softening — until it hands you a blunt verdict with a prioritized list of what to fix first.
Built by the tododeia community. Full guide (Spanish): tododeia.com/community/abogado-del-diablo
By default, Claude tends to agree with you. It validates, softens, and finds the upside in everything. That feels good and ruins decisions. When you're about to bet time, money, or your reputation, you don't need "wow, great idea" — you need someone to find the cracks before the market does.
This skill is that someone. It assumes your idea will fail and sets out to prove it — not out of cruelty, but because every crack it finds here is one you no longer discover late and expensive.
Inside a Claude Code session:
/plugin marketplace add Hainrixz/abogado-del-diablo
/plugin install abogado-del-diablo@abogado-del-diablo
Then invoke it with /abogado-del-diablo.
Copy skills/abogado-del-diablo/ into ~/.claude/skills/ (or .claude/skills/
inside your project). Or download SKILL.md and drop it at
~/.claude/skills/abogado-del-diablo/SKILL.md.
Paste the contents of SKILL.md as the first message in claude.ai or
Cowork, then your idea below it. Same devil's advocate, nothing to install.
/abogado-del-diablo
I want to launch a healthy-snack subscription box at $25/month.
Other forms:
/abogado-del-diablo --proyecto/abogado-del-diablo --demolicionThe skill responds in the user's language (Spanish by default, since it's built for a Spanish-first community).
VERDICT
This isn't a startup, it's a grocery-margin business dressed up as tech, and the
numbers don't add up from day one. Four cracks, deadliest first:
1. The economics don't close — that's problem number one.
- The hit: ...
- Why it's lethal: ...
- What would have to be true: ...
...
THE ONE THAT KILLS IT
Unit economics.
IF YOU INSIST, FIX THIS FIRST
1. ...
Full example in skills/abogado-del-diablo/references/ejemplos.md.
abogado-del-diablo/
├── .claude-plugin/{marketplace.json, plugin.json}
├── commands/abogado-del-diablo.md # the slash command
├── skills/abogado-del-diablo/
│ ├── SKILL.md # the skill's brain
│ └── references/{angulos.md, ejemplos.md}
└── SKILL.md # copy for download / direct paste
MIT. Use it, modify it, share it.
Built by tododeia and maintained by @Hainrixz. Not affiliated with Anthropic. If it saved you from a bad decision, drop a ⭐ and pass it to someone who needs the truth.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub hainrixz/abogado-del-diablo --plugin abogado-del-diabloOpen-source cybersecurity analysis agent. Scans any local project for vulnerabilities: code security (SAST), dependency CVEs (SCA), secret leaks, authentication/authorization flaws, cryptographic weaknesses, misconfigurations, supply chain risks, and CI/CD security. Covers all OWASP 2025 Top 10 and CWE Top 25 categories. Generates prioritized reports with remediation guidance. Invoke with /cyber-neo [path].
Tododeia — Multi-agent investment analysis system for market research, portfolio recommendations, and interactive reporting across crypto, stocks, forex, and commodities.
Free-first paid advertising audit and AI creative generation for Claude Code, focused on the 3 platforms where 95% of advertiser spend lives: Meta, Google, TikTok. Includes a guided first-run wizard (/ads start) with step-by-step OAuth verification and a continuous coach (/ads next) that ranks Quick Wins after every audit. ~158 weighted audit checks, parallel agents, industry templates, PPC math, A/B test design, PDF reports, /ads update for refreshing platform references, and /ads publish to 14+ social networks via Zernio (free for 2 accounts).
Design, audit, and safely migrate any database with Claude. Multi-paradigm (SQL, document, key-value, wide-column, vector, time-series, graph), two independent scores (Design & Integrity + Performance & Scale), reproducible findings, and opt-in fixes. Works offline.
EN: Reflect on the current conversation and save reusable learnings (memories, anti-patterns / Reflexion-style lessons, skill stubs, project-doc updates) with explicit confirmation. ES: Reflexiona sobre la conversación actual y guarda aprendizajes reusables (memorias, anti-patrones estilo Reflexion, stubs de skills, actualizaciones de project-docs) con confirmación explícita.
Skills that get AI assistants to stop agreeing with bad product ideas by default — pressure-test premises, separate hobbies from businesses, and refuse validation theater.
Truth-seeking sparring partner for Claude Code. Challenges claims, decisions, and documents through structured dialectical analysis.
Structured thinking methods that counteract LLM reasoning biases during problem exploration — first principles, inversion, constraint manipulation, perspective forcing, analogy search, and more, with user-gated parallel subagent exploration for deep dives
Adversarial thinking partner for founders and executives. Stress-tests plans, prepares for board meetings, navigates hard decisions, and forces honest post-mortems.
Three lenses for clarity: vague requirements → specs (vague), strategy blind spots → 4-quadrant playbook (unknown), content vs form → leverage shift (metamedium)
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.