Certified Agent Skills

Patterns for adding governance, safety, and trust controls to AI-agent systems — policy-based tool access, intent classification, trust scoring, audit trails, rate limits, and content filters for agents that call external tools.

Checks an AI-agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use to evaluate an agent system security posture, run a compliance check, map controls to the 10 agentic risks, or generate an audit report.

Verifies supply-chain integrity for AI-agent plugins, tools, and dependencies — SHA-256 integrity manifests, tamper detection, dependency-pinning audits, and dev-to-prod provenance chains for agent components.

AWS CDK expert for infrastructure-as-code in TypeScript/Python — CDK stacks, constructs, stack composition, and deployment workflows. Use for CDK, CloudFormation, cdk synth/deploy, or defining AWS infrastructure programmatically.

AWS cost optimization, monitoring, and operational excellence — analyze bills, estimate costs, set CloudWatch alarms, query logs, audit CloudTrail, and assess security posture. Use for AWS costs, budgets, observability, or auditing.

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines, automating quality gates, configuring test runners in CI, or establishing deployment strategies.

Conducts multi-axis code review before merging any change. Use when reviewing code written by yourself, another agent, or a human, to assess quality across multiple dimensions before it enters the main branch.

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or recording context that future engineers and agents need to understand the codebase.

Removes signs of AI-generated writing so text reads naturally — detects and fixes inflated symbolism, promotional language, vague attributions, rule-of-three, and other tells from Wikipedia's "Signs of AI writing" guide. Use when editing or reviewing text.

A 1.0–10.0 "engineering working-mode" dial for coding agents — tunes agency, assumption budget, verification, and security posture from fast prototyping to maintainer-grade rigor. Triggers on "Linus Level", "LL n", or set-rigor / maintainer-mode requests.

Applies the Nothing design system to UI work. Use when the user explicitly asks for "Nothing style", "Nothing design", or to apply the Nothing design system — never automatically for generic UI tasks.

Instruments code so production behavior is visible and diagnosable — logging, metrics, tracing, alerting. Use when shipping features that run in production or when you cannot tell what happened from available data.

Browser automation with Playwright: auto-detects dev servers, writes test scripts, fills forms, takes screenshots, checks responsive design, validates UX, and tests login flows and links. Use to test websites or automate browser interactions.

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations, or building any feature that accepts untrusted data, manages sessions, or calls third-party services.