generator-build-integr…
Action-specific Auto-Harness Generator integrator for parallel sprint implementation. Use only when the current legal action is generator_build_parallel.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
4,481 agents across 361 plugins.
Action-specific Auto-Harness Generator integrator for parallel sprint implementation. Use only when the current legal action is generator_build_parallel.
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
Generates comprehensive test scenarios from acceptance criteria (happy path, negative, boundary, edge cases)
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…
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
Governance specialist. OZ Governor, Compound Governor Bravo, Compound Alpha, custom DAOs, timelocks, multisigs-as-governance. Use when target involves voting,…
Intent-based protocol specialist — ERC-7683 (cross-chain intents), CoW Protocol, UniswapX, Across, 1inch Fusion. Use when target involves intents, solvers,…
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,…
Drives an authorized penetration test end-to-end using a recognized methodology (PTES / OWASP WSTG / NIST 800-115): scoping, recon, testing, and reporting. Use…
Runs full-scope, objectives-based red-team engagements that emulate a real threat actor's TTPs (ATT&CK) to reach an objective and test detection/response. Use…
Stands up and runs an AI governance program: use-case intake and risk-tiering, oversight and accountability, documentation discipline, and regulatory…
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.
Dispatched leaf for single-URL SEO review — one pass over on-page elements, meta, content, schema, images, observable performance, and internal links on a URL…
Dispatched leaf for Schema.org structured data — runs the bundled JSON-LD validator/generator to detect present markup, check required and recommended…
Dispatched leaf for XML sitemap work — runs the bundled tools to validate structure (well-formed XML, the 50,000-URL / 50 MB limits, absolute URLs) and…
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.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic