analyzer
01Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
773 5d ago A 0 tokens
copy · 100% MIT
comparator
02Agent
Compare two outputs WITHOUT knowing which skill produced them.
773 5d ago A 0 tokens
copy · 100% MIT
grader
03Agent
Evaluate expectations against an execution transcript and outputs.
773 5d ago A 0 tokens
copy · 100% MIT
devlab
04mattgierhart/PRD-driven-context-engineering
Agent
Build agent for PRD lifecycle v0.6-v0.8. Use for architecture design, technical specification, implementation, testing, and deployment planning. Use proactively when working on technical execution after strategy validation.
183 12d ago A 45 tokens
original MIT
horizon
05mattgierhart/PRD-driven-context-engineering
Agent
Strategy agent for PRD lifecycle v0.1-v0.5. Use for market research, problem framing, competitive analysis, persona definition, user journey mapping, and risk discovery. Use proactively when working on early-stage product strategy.
183 12d ago A 50 tokens
original MIT
metro
06mattgierhart/PRD-driven-context-engineering
Agent
Ops agent for PRD lifecycle v0.9-v1.0. Use for go-to-market strategy, launch metrics, feedback loop setup, and market adoption tracking. Use proactively when preparing for and executing product launches.
183 12d ago A 46 tokens
original MIT
code-review
07YuDefine/nuxt-supabase-starter
Agent Claude Code
A code-review agent for Nuxt 4, Vue 3, TypeScript, and Supabase projects. Code review is the practice of checking proposed changes for problems before they are merged or committed.
45 3d ago A 34 tokens
original MIT
YuDefine/nuxt-supabase-starter
Agent Claude Code
A fallback agent for carrying out scan, extraction, file-reading, and pattern-matching work when specified model service quotas are exhausted. It follows routing rules that determine when it may take over and which model level to use.
45 3d ago A 155 tokens
original MIT
YuDefine/nuxt-supabase-starter
Agent Claude Code
An agent for taking screenshots of a website or app and checking whether its interface looks correct. It returns a report based on the requested visual checks.
45 3d ago A 73 tokens
original MIT
Agent Claude Code
Autonomous architecture enforcer. Validates and fixes hexagonal architecture boundary violations.
9 5d ago A 20 tokens
original MIT
Agent Claude Code
You are the NPM Optimization Agent for the Kaiord monorepo. Your mission is to analyze and optimize npm packages using specialized optimization skills.
9 5d ago A 0 tokens
original MIT
orchestrator
12Agent Claude Code
Review-execution cycle orchestrator. Use to execute plans with automatic review until convergence.
9 5d ago A 20 tokens
original MIT