Explore skills

A multi-framework compliance officer's 6-question interrogation for any compliance program. Use before starting a new framework, planning the annual audit calendar, or preparing for certification stage 1.

Code review automation for various languages, analyzing PRs for complexity and risk, checking code quality for SOLID violations and code smells, and generating review reports. Useful for reviewing pull requests, analyzing code quality, and identifying issues.

Use when writing, reviewing, or committing code to enforce Karpathy's 4 coding principles: surface assumptions before coding, keep it simple, make surgical changes, and define verifiable goals. It triggers on phrases like review my diff or any code quality concern where the LLM might be overcoding.

Use when a security incident has been detected or declared and needs classification, triage, escalation path determination, and forensic evidence collection. Covers SEV1-SEV4 classification, false positive filtering, incident taxonomy, and NIST SP 800-61 lifecycle.

Use when hunting for threats in an environment, analyzing IOCs, or detecting behavioral anomalies in telemetry. Covers hypothesis-driven threat hunting, IOC sweep generation, z-score anomaly detection, and MITRE ATT&CK-mapped signal prioritization.

A personal coach that teaches users to become Claude power users. Activate this skill the first time a user asks to learn or improve with Claude, and use it on subsequent turns to detect missed optimization opportunities.

Show experiment dashboard with results, active loops, and progress.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Use when adding, retiring, or auditing feature flags, triggering on terms like 'add a flag', 'rollout plan', 'kill switch', 'flag debt', provider names (LaunchDarkly, GrowthBook, Statsig, Unleash, Flipt), or any progressive-delivery question. It ships a flag debt scanner, rollout planner, and kill-switch auditor (all stdlib Python), along with references on flag taxonomy and provider trade-offs.

Run a single experiment iteration. Edit the target file, evaluate, keep or discard.

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.

Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows. NOT for testing — use playwright-pro for that.