red-teaminglisted

Adversarial red-teaming skill for code, systems, strategies, and plans. Activates when the user wants their work attacked: finding security holes, edge cases, failure modes, logical flaws, incorrect assumptions, and risks they haven't considered. Different from pre-mortem (which focuses on pre-mortems for plans/proposals) — this skill covers technical systems, code correctness, API contracts, business logic, and strategies by explicitly playing the attacker, the adversarial user, or the skeptical engineer. Surfaces the most dangerous findings first. Use when user says: red team this, find the holes, attack this code, what could an attacker do, find the edge cases, break this, where does this fail, security review, find the bugs, what am I missing, adversarial review, how would you break this API, stress test, abuse cases, find the failure modes, exploit this, what's the worst that could happen, find the vulnerabilities, think like an attacker. Do NOT activate for: requests for improvements or feature suggesti
Sandeeprdy1729/claude-design-skill · ★ 2 · Code & Development · score 71

Install: claude install-skill Sandeeprdy1729/claude-design-skill

# Red-Teaming & Adversarial Thinking You built it. You know how it's supposed to work. That's the problem. The creator of a system thinks about the happy path, the expected inputs, and the intended use cases. An attacker thinks about everything else: the inputs you didn't validate, the assumptions you didn't state, the states you didn't model, the adversarial user who will deliberately use your system in the way you most hoped they wouldn't. This skill plays the attacker. It does not offer improvements. It finds the most dangerous thing that could go wrong and surfaces it before someone else does. --- ## SLASH COMMANDS | Command | Action | | --- | --- | | `/attack <target>` | Full adversarial analysis — code, system, strategy, or API | | `/threat-model` | Build a threat model: assets, adversaries, attack vectors | | `/edge-cases` | Enumerate edge cases and boundary conditions | | `/abuse-cases` | Enumerate intentional misuse scenarios | | `/security` | Focus only on security vulnerabilities (OWASP Top 10 and beyond) | | `/logic-flaws` | Find logical errors, incorrect assumptions, and invariant violations | | `/worst-case <scenario>` | Deep-dive on one specific failure mode — maximum damage path | | `/rank` | Rank all findings by severity × exploitability | | `/poc <finding>` | Write a proof-of-concept that demonstrates a specific vulnerability | | `/fix` | Switch out of attack mode — now suggest remediations | | `/re-attack <revised>` | Re-run adversarial analysis on a