Filter what needs me out of the wall of text, into one section at the end of every reply.
Audit cross-platform attribution, conversion definitions, reporting windows, GA4, AdServices and AdAttributionKit, MMPs, browser and…
Audio Unit v3 (AUAudioUnit) format adapter for Pulp — render-block wiring, parameter tree bridging, MIDI / sysex via AURenderEvent…
Streamlines the creation of professional audiobooks through AI-powered character analysis, voice synthesis, and sound effect orchestration.
Use when an agent, harness, gateway, MCP workflow, or multi-step automation claims completion and the available traces, checkpoints…
Diagnoses Universal Dev Standards (UDS) health, detects development patterns, and identifies workflow friction points.
Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices…
Use when reviewing or changing a React, Next.js, Tailwind, or shadcn interface and you need evidence-backed findings for accessibility…
Audit uploaded or pointed-at HTML training like a craftsman ID.
Filter and summarise the cross-library KB audit log.
Orchestrate a scoped, goal-backed multi-agent audit loop from one parent thread only when the audit is large or complex enough to benefit…
Prepares codebases for security review using Trail of Bits' checklist.
Efficiency audit of a skill library on four measured axes — token cost, ceremony/duplication bloat, trigger-description precision, and…
Investigate a Datadog product usage or cost spike by correlating Usage Metering data (when/what spiked) with Audit Trail config changes…
Audit work, verify claims with concrete evidence, and explain the result in simple grade-5 language.
Use to lint a repo's agent onboarding files (AGENTS.md, CLAUDE.md, .claude/rules/*.md) for bloat, contradictions, duplication, stale or…
Systematically audit AWS S3 bucket permissions to identify publicly
Audit AWS, Azure, and GCP environments against the CIS Foundations Benchmarks by running automated scans with tools like Prowler and…
Auditing Terraform infrastructure-as-code for security misconfigurations
Sonnet Amplified fullstack engine. 34 modes, SEC-01~15 OWASP security, 13 runtime hooks, 75% token reduction.
This skill should be used when the user asks "where should validation live", "how do I stop re-checking this everywhere", "how do I make…