smykla-skalski/sai

Daily AI news digest covering technical advances, business news, and engineering impact

Council of 27 sourced engineering and UX persona agents that review code, design docs, architecture, refactors, UI surfaces, dashboards, and strategy through opinionated lenses, then synthesize convergence, disagreement, and concrete next moves.

Generate a lean, high-signal CLAUDE.md from codebase analysis; built to pass review-claude-md

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

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

Make text sound natural by removing AI writing patterns

Interactive KubeCon CFP submission writer with data-driven insights from 1,100+ accepted talks

Critique a Claude implementation plan before approving execution. Spawns parallel persona subagents (Skeptic, Architect, Verifier) to evaluate the plan against the codebase.

Turn rough instructions into optimized, evidence-based prompts for AI agents

Refactoring review through 7 sourced refactoring personas (Fowler, Uncle Bob, Feathers, Beck, Metz, Ousterhout, Tornhill): scans smells + git hotspots, synthesizes a safety-first plan, then an adversary red-teams it.

Audit and fix CLAUDE.md files using tiered binary checklist

Diagnose and fix flaky e2e tests and connectivity issues in service mesh environments (Kuma, Istio, Linkerd, Consul). 11 root causes, Envoy debug scripts, minimal fixes.

Take a GitHub issue from implementation through adversarial review and testing, PR, CI and Copilot review, merge, and closure.

Staff-engineer-level code review evaluating architectural alignment, failure modes, observability, security, and cross-team impact.

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

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