Explorar skills

Activates AIRedTeamer — a specialist in adversarial testing of AI/LLM systems for safety, robustness, and alignment failures. Use when you need to test prompts for jailbreaks, probe model behavior under adversarial inputs, assess AI system safety, evaluate guardrail effectiveness, or design red-team evaluation suites for production LLMs.

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.

Full-spectrum product research pipeline. Runs competitive analysis, technology trend scouting, user feedback analysis, and feature ideation. Trigger on: research, competitive research, market research, feature discovery, what should we build next, technology trends, user feedback, app store reviews, GitHub issues analysis, competitive landscape, product strategy.

Autonomous performance optimization for interfaces — content-visibility, CSS containment, scroll-driven animations replacing JS, view transitions replacing SPA transitions, image optimization, and bundle trimming. Use when: 'optimize UI performance', 'speed up the frontend', 'reduce bundle size', 'improve web vitals', 'optimize rendering', 'make it faster', 'performance audit'.

Architect-level story review with component reuse, domain consistency, data privacy, service architecture, and infrastructure checks. Design review before coding or implementation validation after.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Monitor federal grant opportunities across Grants.gov (Simpler.grants.gov is the modern UX), SAM.gov assistance listings (the post-CFDA replacement that preserves CFDA program numbers), and direct agency portals — NIH RePORTER + NIH Guide, NSF Funding, DOE OSTI, USDA NIFA, EPA Grants, NEH/NEA, IES (Education), CDC, FEMA, HUD CPD, ACF. Generates a daily pipeline with eligibility filtering (501(c)(3

Systematic audit against the OWASP 2021 Top 10 web application security risks with severity-rated, file-level findings. Checks A01 Broken Access Control (IDOR, path traversal, CORS, privilege escalation), A02 Cryptographic Failures (weak algorithms, exposed secrets, missing TLS), A03 Injection (SQL, NoSQL, command, XSS, LDAP, XPath, template injection), A04 Insecure Design (missing rate limiting,

Analyze government benefits processing software for eligibility determination, application workflow efficiency, document verification, error rates, appeal tracking, multi-program coordination, and ADA/Section 508 compliance. USE THIS SKILL WHEN: user mentions benefits eligibility, SNAP, Medicaid, TANF, WIC, government assistance programs, social services software, eligibility rules engine, casewor

Audit mobile app revenue implementation -- in-app purchases, subscriptions, ad SDKs, paywall design, trial conversion funnels, and store billing compliance. Covers StoreKit 2, Google Play Billing, RevenueCat, AdMob, Unity Ads, receipt validation, entitlement sync, and pricing localization. Use when reviewing IAP flows, optimizing subscription conversion, checking ad mediation setup, or preparing f

Guides rigorous evidence extraction from papers. Use when reviewing literature to ensure proper provenance tracking.

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library