investigate-issue
Investigate a GitHub issue and post structured findings as a comment. Use when the user wants to analyze a bug report, reproduce it, and share findings on the issue thread.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Investigate a GitHub issue and post structured findings as a comment. Use when the user wants to analyze a bug report, reproduce it, and share findings on the issue thread.
Write a new Playwright E2E test for Vortex. Accepts a plain-text description of what to test, or a Linear issue ID to fetch the description automatically. Uses Chrome DevTools MCP to inspect the live app and source code to produce a well-structured spec.
Diagnose the health of a nao context at any stage of its lifecycle. Use when the user wants a structured review of what's been synced, how RULES.md compares to the target structure, whether every table is documented, whether the data model is MECE, whether tests exist and what their failures reveal, and whether context files are bloated. Outputs a structured audit report with ranked recommendations. Do not use for first-time setup (setup-context) or routine rule writing (write-context-rules).
Generate a test suite of natural-language → SQL pairs that becomes the quality benchmark for a nao agent, then run it via `nao test`. Use when the user wants to start measuring agent reliability, extend an existing test suite, or add tests for new metrics. Tests are the only honest answer to "is the context working?". Do not use for writing rules (write-context-rules) or diagnosing failures (audit-context).
Guide to implement rigorous validation layers including static analysis, automated testing, structured logging, and security scanning.
Run pnpm check:push (lint, types, tests) before git push or PR-ready work. Use when the user asks to push, open a PR, reports a failed pre-push hook, or when substantive code changes are finished and push is next.
QA the PocketHost dashboard in the Cursor IDE browser (cursor-ide-browser MCP). Use when verifying UI changes, testing login flows, checking styling, or when the user asks to open or test the dashboard in the browser.
Run Ethereum multi-client devnets using Kurtosis and the ethpandaops/ethereum-package. Use for spinning up local testnets, validating cross-client interop, testing fork transitions, running assertoor checks, debugging CL/EL client interactions, or verifying new feature implementations across multiple consensus and execution clients.
Debug Lodestar beacon node issues by running a local mainnet node with checkpoint sync and engineMock. Use for investigating networking bugs, peer discovery issues, identify failures, metrics anomalies, or any behavior that needs real-world peer interactions without a full execution client.