plan-checker
Verifies plans will achieve phase goals before execution. Goal-backward analysis of plan quality across 10 dimensions.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
5,813 agents across 587 plugins.
Verifies plans will achieve phase goals before execution. Goal-backward analysis of plan quality across 10 dimensions.
Creates executable phase plans with task breakdown, dependency analysis, wave assignment, and goal-backward verification. Also creates roadmaps.
Reviews document presentation: voice consistency, audience fit, AI trope detection, readability, and formatting.
Judges candidate code-review findings against the code as CONFIRMED, PLAUSIBLE, or REFUTED. Spawned by the review:code skill's verify phase.
Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes…
Full-stack implementation specialist for isolated worktree work. Follows existing codebase patterns, implements a single task independently with tests. Use for…
Pragmatic ROI analyst for overengineering detection, effort-vs-value assessment, scope creep identification, and "good enough" evaluation. Use when reviewing…
Prompt & guardrail engineering specialist. MUST BE USED for system-prompt design, prompt templates, prompt eval/test suites, prompt-injection defense, and…
Documentation researcher. MUST BE USED for new API integration, library questions, best practices. PROACTIVELY gathers version-specific documentation and…
Senior code reviewer, security specialist, and quality assurance expert. Use for all code reviews, security analysis, threat modeling, and compliance review.…
OpenAI Codex MCP 연동 에이전트. 꼼꼼한 구현, 코드 리뷰, 엣지케이스 검증. Agent Teams Team Lead.
Mobile app development (React Native, Flutter), offline-first, push notifications
Workflow coordination expert for multi-PRD orchestration
Application performance optimization and profiling expert
Referenced skill does not exist in .claude/skills directory
Agent tools must be an array of tool names, cannot be used with disallowed-tools
Use this agent when the user needs to discover, collect, quality-assess, and store research sources with metadata for systematic research workflows. Performs…
Emulates a real end user interacting with a newly-built product. Informed by PRD and design system, makes judgement calls about whether it's good — catching…
A weighted matrix does not make a decision objective. It makes the judgment *visible*, which is more useful — but only if you actively defend against the…
Two things here: a **blank template** to copy, and a **fully worked example** (with the JSON that `scripts/decision-score.mjs` consumes so the arithmetic and…
The artifact this agent leaves behind — findable, dated, revisitable.
Specialized agent for implementing comprehensive application monitoring, analytics tracking, performance optimization, and observability across web…
Protect the platform that delivers clean water to those in need. Every security measure ensures donor trust and recipient impact.
Specialized agent for implementing comprehensive testing strategies, code quality assurance, and maintaining high standards across the H2All Web CMS project,…
Dimensional modeling architect for dbt projects. Designs fact and dimension tables following Kimball methodology, plans model DAG structure, defines grain and…
Analytics engineer specializing in dbt projects on a cloud data warehouse. Implements dimensional models, dbt transformations, tests, and domain logic. Use…
Isolate root cause from symptoms, reproduce failures, and propose the smallest high-confidence fix path.
Автономный критический анализ — long-list идей → critique → отсев. Не спрашивает пользователя про каждую — решает сам по критериям. Возвращает топ-3-5 с…
Генерация идей в 2 раунда. Round 1 — 10+ идей с аргументацией. Round 2 — после фидбэка пользователя (берём/не берём) — глубже копаем выбранные. Каждая идея с…
Автономная валидация бизнес-модели Top-3 идей. Проверяет: рынок размер, конкуренты, monetization потенциал, риски. Возвращает validation score 0-100 +…
The `max` rung of `cad-planner`; `bin/route.mjs` picks it, not the user.
The `xhigh` rung of `cad-planner`; `bin/route.mjs` picks it, not the user.
The `high` rung of `cad-reviewer` (adversarial artifact review); `bin/route.mjs` picks it, not the user.
Stage 1 peer code reviewer focused on Rust ownership, lifetimes, and idiomatic patterns.
Stage 1 peer code reviewer focused on schema correctness, query quality, and migration safety.
Stage 1 peer code reviewer focused on Swift idioms, iOS patterns, and memory safety.
Use to set up and own the repository's plumbing — git branch model, commit/PR conventions, CI, signing, fastlane, build flavors, and secrets handling. Produces…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic