Configure and run Playwright tests on BrowserStack's cloud grid, then summarize results per browser.
Pressure-tests any AI plan with six CAIO questions covering eval sets, hallucination SLOs, EU AI Act tiering, cost trajectory and AI hiring.
Generates a phased, documentation-grounded implementation plan where each phase can be executed in a fresh chat context.
An installer skill that wires the NanoClaw container agent to local models served by the Atomic Chat desktop app via MCP.
Wires an Emacs channel into NanoClaw so you can chat with your agent from a buffer or straight inside org-mode.
Wires a local monitoring dashboard into a NanoClaw project to visualize agents, sessions, tokens and live logs.
A routing skill that guides installing, configuring, extending, and embedding Pi — the minimal terminal coding harness.
A product-development coach that applies Getting Real, Rework and Shape Up so you cut scope, fix time, and ship every six weeks.
Audits and fixes web accessibility issues against WCAG 2.2 with concrete HTML/CSS/JS patterns.
Explains a single file, function, or module in depth by combining a prebuilt knowledge graph with the actual source code.
x
Answers questions about your codebase by grepping a prebuilt knowledge graph at `.ua/knowledge-graph.json`.
Cross-references a git diff or PR against your project's knowledge graph to report changed components, blast radius and risk.
Extracts business domains, flows, and process steps from any codebase and renders them as an interactive flow graph.
A maintainer-grade PR review workflow that judges contributor PRs by the real merge result against the current base branch, not a stale web diff.
Teaches Claude the gh CLI and GitHub API patterns needed to manage PRs, issues, and Actions for you.
Delegates coding, refactoring, and review tasks to your locally installed OpenAI Codex CLI as a non-interactive sub-agent.
Restores a repomix-packed repository back into its original files and directory structure.
A pre-implementation workflow that clarifies requirements through dialogue, compares 2-3 approaches, and commits an approved design spec before any code is written.
A release gate skill that fans out 16 parallel agents to audit every unpublished change and returns a SAFE/CAUTION/RISKY/BLOCK verdict before you npm publish.