All skills

Autonomously scans a codebase for personal data, runs an all-99-article GDPR gap analysis, and generates pre-filled DPA, ROPA and operational compliance documents.

Reads your `.skill-state.json` learning plan and progress, then hands you at most three concrete tasks for today with completion criteria, saving every artifact to disk.

Pulls real BOSS Zhipin job postings and finds roles at the intersection of high pay, learnable-for-you, and still needed in the AI era.

A routing skill that makes Claude use trace-mcp's semantic code tools instead of Read/Grep/Glob, cutting tokens while improving accuracy.

Forces Claude to use trace-mcp's apply_codemod for any edit pattern repeated 2+ times instead of firing off repetitive Edit calls.

A skill that turns your CLAUDE.md into AGENTS.md and wraps OpenAI Codex CLI calls so Claude Code and Codex work together.

Rules for passing subagent results through files instead of TaskOutput so the main conversation's context stays clean.

A developer reference for wiring Agentica agents to a Claude Code CLI proxy, covering required flags, response formats, and common failures.

Wires Claude Code hooks so sessions, turns, and every tool call are logged as hierarchical Braintrust traces.

A short rule set that tells Claude to delegate implementation work to sub-agents so the main conversation keeps its context.

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.

A skill that applies Anthropic's official brand colors and typography consistently across documents, slides, and design artifacts.

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.