gsd-ai-researcher
Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
3,719 agents across 361 plugins.
Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for…
Deeply analyzes codebase for a phase and returns structured assumptions with evidence. Spawned by discuss-phase assumptions mode.
USE WHEN /repo-doctor --semantic runs. Judges whether discoverability artifacts (AGENTS.md, README, ADRs, GLOSSARY, per-dir AGENTS.md) are truthful,…
Use for codebase discovery. Use to find where something is defined or imported. Use to identify patterns used across files. Use proactively before making…
Use to understand how something works in the codebase before making changes. Use when asked to explain a pattern or flow that spans multiple files. Use…
Use this agent when you need to review code changes for convention compliance, security issues, or correctness before merging. <example>Context: A wave of…
Use this agent when you need to audit project state, map affected modules, or verify assumptions before implementation. <example>Context: Before adding a new…
Use this agent when you need to verify a repo meets quality standards before a release, merge, or deployment decision. <example>Context: The session is about…
PRD analysis specialist. Finds weaknesses, gaps, and risks across 4 categories (Completeness, Feasibility, Security, Consistency). Quality gate for /implement:…
Team-based parallel BUILD coordinator for /implement command. Dynamically assigns teams (Backend, Frontend, AI Server, Ops) based on PRD analysis, manages…
Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine…
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4…
The creative product mind that knows why some features become part of someone's identity and others get used once. Consult when evaluating feature ideas,…
Use this agent when an MSP needs to audit backup and BC/DR health across their Datto RMM managed client portfolio — not a general fleet health check, but a…
Use this agent when an MSP owner, billing coordinator, or service manager needs a billing completeness and accuracy audit in Syncro — finding tickets that…
Use this agent when an MSP billing team, controller, or account manager needs to run a portfolio-wide sweep for contract-vs-invoice mismatches — surfacing…
성능 최적화 전문가. 벤치마킹, 프로파일링, 병목 분석. Guardian Team 병렬 실행 (--perf 플래그 또는 NFR 존재 시).
아키텍처 계획 전문가. 복잡한 태스크를 파일 매니페스트+에이전트 할당으로 분해. Use proactively for BUILD/SPEC tasks requiring multi-file implementation.
PM 모드 기회 발견 분석가. OST(Opportunity Solution Tree) 기반 고객 니즈·페인포인트 분석. Use proactively in PM mode.
Intent evolution and drift detector — analyzes session patterns to propose alignment updates
Code quality gate - reviews code for patterns, testing, documentation compliance
Security scanning and vulnerability detection - OWASP compliance checker
This agent should be used when the arn-code-bug-spec skill needs diagnostic investigation of a bug, or when the user needs to trace a bug's root cause through…
This agent should be used when the user is starting a new project from scratch and needs recommended code patterns, testing strategies, and architectural best…
This agent should be used when the arn-code-bug-spec skill's simple fix path needs a brief, structured fix plan before execution, or when any skill needs to…
盲測比較代理 —— 在不知道哪個技能產生哪個輸出的情況下比較兩個輸出。 純粹根據輸出品質和任務完成度進行判斷。 使用範例: - "比較兩個版本的技能輸出" - "盲測評估哪個輸出更好"
分析 Git 歷史,識別可能引入問題的提交,追蹤程式碼變更。 擅長從版本控制歷史中找出問題的引入時間點,分析變更對功能的影響。 使用時機: - "檢查最近的程式碼變更" - "找出可能引入這個 bug 的提交" - "比較正常版本和問題版本的差異" - "分析這個檔案的修改歷史" - "誰最近修改了這個功能"
評分代理 —— 根據執行記錄和輸出評估期望值。 同時批判評估本身的品質,識別薄弱或遺漏的斷言。 使用範例: - "評估技能執行是否符合預期" - "對測試結果進行評分" - "驗證輸出是否滿足所有斷言"
Combines all tool outputs and agent findings into unified health report. Generates architecture.md, calculates health score, classifies severity.
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans for beast-plan. Produces plans that a fresh Claude session can execute without…
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check.…
Security architecture specialist. Authentication, authorization, compliance.
Specialized code generation. Invoked by implement-specialist.
Documentation generation. README, API docs, guides.
Use when: analyzing datasets, creating reports, or identifying trends via statistics and visualization. Do NOT use for: building production data pipelines/ETL…
Use when: designing or auditing a design system, a marketing site, a web app screen, or an iOS/Android mockup. Do NOT use for: wiring components into a…
Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Do NOT use for: documentation…
Focus on front-end and browser-side security reviews: XSS, client key leaks, dangerous DOM/API usage, third-party scripts, CSP, dependencies and supply chains,…
Front-end test strategy planning subagent: Develop a coverage matrix according to risk and test levels, distinguishing static inspection, unit, component,…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic