All skills

Turns a codeck deck into a word-for-word presenter script with stage directions and fragment-synced speaker notes.

A single entry point that analyzes your question and routes it to the right one of six specialist deliberation rooms (engineering, business, life, relationships, psychology, creativity).

Convenes a panel of Feynman, Ada, Torvalds, Popper, Occam, Nietzsche and Wittgenstein to run an evidence-based, structured debate on architecture, debugging, refactoring and code review.

One-command code structure and blast-radius queries to run before you refactor anything.

Step-by-step guides for migrating a test suite from Cypress or Selenium/WebDriver to Playwright.

Playwright POM patterns plus a decision framework for choosing between page objects, fixtures, and helpers.

Crawls a site with a real browser to detect its platform, dataLayer events, and live GTM containers, then emits structured analysis artifacts.

Designs, validates, and finalizes GA4/GTM event schemas into an approval-ready tracking plan.

Drive real websites from Claude using the `agent-browser` CLI: snapshot refs, click and fill, then verify the result.

A hook-driven memory system for Claude Code that auto-saves session context, hands off work between windows, and learns from repeated mistakes.

A skill that guides asdf (asdf-vm) installation, plugin management, .tool-versions workflows, and shim troubleshooting.

A skill that scans source code for endpoints and produces Markdown or OpenAPI 3.0 API documentation.

A skill that scans source code for endpoints and produces Markdown or OpenAPI 3.0 API documentation.

Enforces a five-stage ship pipeline — verify gate, commit strategy, docs, PR, human-approved merge — with code integrity checks.

Search, query and inspect Claude's persistent memory stored in a single portable .mv2 file.

A decision-framework skill for designing cloud networks: VPC topology, subnet strategy, zero trust, and hybrid connectivity.

A governance gate skill that reads harness.json and audits AI-generated project docs (PRD, spec, progress ledger) rule by rule, then emits a fix list.

Runs the liarjs CLI to cross-check a browser's JS fingerprint (canvas, WebGL, audio, fonts, WebRTC, timezone) against the TLS/HTTP/ASN view of the same request and scores the contradictions.

Measures whether your Playwright, Puppeteer, Selenium or CDP browser presents a self-consistent fingerprint, scoring an existing Page object in place.

A brand-protection skill that flags unauthorized eBay sellers, counterfeits and trademark abuse, then drafts VeRO complaints.