Automation

Clusters a GitHub issue backlog by root cause into a handful of plan-master issues plus design docs, then bundles PRs that close each cluster atomically.

Drives the agent-browser CLI so Claude can navigate sites, fill forms, capture screenshots and extract page data.

A browser-automation skill that keeps named pages alive across script runs so Claude can navigate, fill forms, screenshot, and scrape incrementally.

A research orchestrator that fans parallel explore/librarian/browsing workers across your codebase, the web, official docs and OSS repos, recursively expands every lead, and ships a fully cited PDF/DOCX report.

A command reference that lets Claude drive a real browser with the agent-browser CLI for navigation, form filling, screenshots and data extraction.

An Atlassian org-admin skill that walks through user provisioning, permissions, SSO, apps, audits, and disaster recovery with real console paths and REST endpoints.

Runs a 6-phase, multi-role executive deliberation on a strategic question, with a mandatory founder approval gate before decisions are logged.

Builds production-grade Playwright workflows for scraping, form filling, screenshot/PDF capture, session reuse and anti-detection.

End-to-end guidance for building, running, configuring, and debugging Nextflow and nf-core pipelines.

Assembles a role-based AI team of doers, directors, and critics to run meetings, debates, and system design end to end.

Drive Chrome over the DevTools Protocol to reuse existing logins — open pages, run JavaScript, click elements, and pull auth tokens.

Give it a person's name — or just a vague problem — and it researches deeply, distills their thinking framework, and writes a runnable persona Skill for you.

A skill for wiring Jira and Confluence into Claude Code via MCP to run JQL/CQL queries, manage tickets, and automate sprints safely.

Designs safe, hypothesis-driven chaos experiments, failure-injection code and game day exercises for distributed systems.

Splits a research goal into parallel sub-goals, runs them as headless `claude -p` subprocesses, and aggregates plus chapter-by-chapter polishes the results into a standalone report file.

Mines your recent agent transcripts and asks targeted questions to produce a personal `-mode` skill that agents follow.

An interactive advisor that re-architects repetitive PM work into a set of parallel, specialized AI agents with clear boundaries, monitoring, and evals.

Turns a trade plan into stop, target and flat-by-close alerts, tracks NYSE hours, and pulls free delayed quotes.

Drives a real Chrome browser to compose and publish X posts, images, videos, quote tweets, and Markdown long-form Articles.

Captures your in-session corrections via hooks and applies them to CLAUDE.md through a reviewed /reflect command.