proctor
claudeHook-enforced development discipline for Claude Code. Skills teach methodology (TDD, debugging, verification, SDD); hooks enforce compliance (git gates, branch protection, test evidence); store survives compaction.
14 skills
Dr. House engineering persona plus four diagnostic protocol skills: critic (code autopsy), architect (system design), visual (UI/CSS/accessibility), core (algorithms/concurrency). Each protocol triggers on its own noun domain.
Plugin diagnosticianul from marketplace nalyk-skills in nalyk/nalyk-skills. Commands read from the repo's manifest — yesterday.
diagnosticianulDr. House engineering persona — invoke explicitly or via the protocol skills.
protocol-architectUse for system architecture work: "system design", "database schema", "API design", "microservices vs monolith", "tech stack choice". Rigid planning or refusal if the spec is napkin-grade.
protocol-coreUse for algorithm and concurrency pathology: "time complexity", "memory leak", "race condition", "deadlock", "recursion", "sorting", "searching", data structures, Big-O analysis. Surgically precise diagnosis via invariants.
protocol-criticUse for forensic code autopsy: "code smell", "antipattern", "dead code", "AI slop", "code autopsy". Severity-graded verdicts with line-level evidence.
protocol-visualUse for visual interface quality: "CSS", "typography", "accessibility", "design system", "color scheme", "responsive design", "component styling". Aesthetic dictatorship against default design.
Hook-enforced development discipline for Claude Code. Skills teach methodology (TDD, debugging, verification, SDD); hooks enforce compliance (git gates, branch protection, test evidence); store survives compaction.
14 skills
Multi-model adversarial debate. Claude defends positions against external CLI models (agy/Gemini, Codex, Mistral Vibe) in parallel rounds. Refuses to run Claude-only; outputs consensus, tradeoff documents, or ADRs.
2 skills · 3 commands · 4 agents
Deterministic SEO analysis: Python engine (98 atomic checks) with multi-page crawler, real CWV via PageSpeed, optional GSC data, link graph/PageRank, auto-fix generation, and audit history with regression detection. One orchestrator skill plus 7 specialist agents.
1 skill · 7 agents
Philosophical reasoning engine for engineering decisions and code reviews: 63 principles (0-62) from 20 philosophers, via /organon, /organon:decide, /organon:review.
1 skill · 3 commands · 1 agent
Audit commands: /jobs-audit (design simplification), /carlin-audit (BS detection), /vibe-audit (engineering quality), /multi-audit (parallel run + synthesis).
4 commands
Decompose a task into parallel subagent workstreams via /orchestrate, /parallel, /plan-only
1 skill · 3 commands
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 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
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
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
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.