sai

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.

1 skill · 27 agents

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

1 skill · 9 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.

1 skill · 8 agents

Critique an implementation plan before approving execution. Persona reviewers (Skeptic, Architect, Verifier) evaluate the plan against the codebase and return an Approve/Reject/Refine verdict.

1 skill · 3 agents

Fast two-pass adversarial code review: a Code Adversary subagent hunts the concrete bug, then a clean-context Findings Adversary subagent refutes false positives.

1 skill · 2 agents

Adversarial manual testing: a clean-context Test Adversary subagent runs the real product surface in isolated state and tries to break it; every reproduction is rerun before it counts.

1 skill · 1 agent

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

1 skill · 1 agent

Audit and fix CLAUDE.md files using tiered binary checklist

1 skill · 1 agent

Write, improve and split GitHub issues and agent briefs that coding agents can implement without asking questions

1 skill

Make 3Blue1Brown-style explainer videos: Manim animations narrated with ElevenLabs, from a topic to a checked 1080p60 MP4

1 skill

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

1 skill

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

1 skill

Clean up local branches with deleted remote tracking and their worktrees

1 skill

Non-interactive hunk staging for selective git add without TTY

1 skill

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

1 skill

Write and rewrite text plainly and concisely without losing meaning

1 skill

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

1 skill

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.

1 skill

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

1 skill

Audit work for overbuilt or oversimplified design, and write or rewrite design docs, decision records, pitches and plans that pass the simplicity rules

1 skill

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.

1 skill

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

1 skill

Explore an idea, assess its value and alternatives, and choose small next steps when you want a plan. Keep one note per idea, add a Mermaid map when useful, and create a Miro board on request

1 skill

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

1 skill

Audit a repo for technical debt and file an umbrella GitHub tracker with one rated sub-issue per finding

1 skill

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

1 skill

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

1 skill