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.
Plugin plan-critic from marketplace sai in smykla-skalski/sai. Commands read from the repo's manifest — 13 days ago.
plan-criticCritique an implementation plan before approving execution. Runs three persona reviewers (Skeptic, Architect, Verifier) against the codebase, in parallel on Claude Code and one at a time on other agents, and returns an Approve/Reject/Refine verdict with concrete refinements. Use when a plan has been
architect-reviewerPlan-critic Architect persona. Judges whether an implementation plan is structurally sound - file selection, execution order, convention fit, scope, and backward compatibility. Spawn only inside a plan-critic workflow, with the full plan text and the Grounding Brief.
skeptic-reviewerPlan-critic Skeptic persona. Hunts what an implementation plan is missing - unhandled edge cases, failure modes, rollback gaps, test gaps, and missing verification criteria. Spawn only inside a plan-critic workflow, with the full plan text and the Grounding Brief.
verifier-reviewerPlan-critic Verifier persona. Decides whether an implementation plan shows the author actually read the code - symbol specificity, cross-check against the Grounding Brief, hidden assumptions. Spawn only inside a plan-critic workflow, with the full plan text and the Grounding Brief.
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
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
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.