Smykla Skalski Labs

Generate a lean, high-signal CLAUDE.md from codebase analysis. Grounded in Anthropic best practices and empirical studies; built to pass review-claude-md's critical checks.

List, reply to, resolve, and create GitHub PR review comment threads

Clean up local branches with deleted remote tracking and their worktrees

Non-interactive hunk staging for selective git add without TTY. Stage only part of a file, specific hunks, or pattern-matched changes when git add -p is unavailable.

Auto-review Go code for 100+ common mistakes from 100go.co. Checks error handling, concurrency, interfaces, performance, testing, and stdlib usage with severity tiers and direct mistake references.

Make text sound natural by removing AI writing patterns. For commit messages, PR descriptions, review comments, docs, changelogs, and any text that sounds robotic or AI-generated.

Interactive KubeCon CFP submission writer with data-driven insights from 1,100+ accepted talks and official reviewer criteria.

Fill the monthly KUP report (Polish 50% creative-work tax deduction) from your merged GitHub pull requests and write it to your KUP Google Sheet.

Turn rough instructions into optimized, evidence-based prompts for AI agents, coding agents, tools, eval graders, and subagent briefings. Built on Anthropic / OpenAI guidance through April 2026 and the 2025-2026 academic literature. Copies to the clipboard on macOS, Linux and Windows.

Diagnose and fix flaky e2e tests and connectivity issues in service mesh environments (Kuma, Istio, Linkerd, Consul). Covers 11 root causes: timing races, xDS propagation delays, Gomega misuse, pod availability races, mTLS/SDS readiness, Envoy circuit breakers, and outlier detection. Includes Python scripts for live Envoy diagnostics.

Ship a change or coordinate an approved plan through independent issues, adversarial gates, PRs, CI, Copilot review, and merge.

Build and refine staff-level engineering resumes through interactive coaching, research-backed best practices, and per-job tailoring.

Audit a repo for technical debt, research version-specific best practices, and file an umbrella GitHub tracker issue with one rated, actionable sub-issue per finding. Re-runs reuse the umbrella and dedupe against its sub-issues.

Write tests that verify behavior (not implementation), use table-driven/parameterized patterns, and minimize mocking. Supports Go, Python, TypeScript, Java, and Rust.

Summarize a YouTube video from its transcript into a concise Markdown note, saved to a folder you configure or printed in chat.