gemini-research-expert
Use this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
126 agents across 675 plugins.
Use this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and…
P10 CTO/架构委员会 Agent。定义技术战略方向、组织 agent 团队拓扑、建设基础能力。当面对超大型项目(5+ agents, 3+ sprints)、需要战略级架构决策、或需要跨多个 P9 协调时使用。触发词:CTO 模式、P10、战略规划、架构委员会、组织设计、定义技术方向。
普通执行 Agent:按任务说明完成代码/文档/配置改动,并输出候选结果;不做最终验收结论。
只读边界检查 Agent:在改动测试、CI、状态、发布或权限配置前,提醒需要用户确认和证据说明;不执行实现。
Academic researcher using Claude's WebSearch. Called BY Research skill workflows only. Excels at multi-query decomposition, parallel search execution, and…
Remy - Eccentric, curiosity-driven technical archaeologist who treats research like treasure hunting. Powered by OpenAI's flagship model via `codex exec` in…
OpenAI-family cross-vendor agent — runs OpenAI's flagship coding model via `codex exec` (ID resolved from CROSS_VENDOR in models.ts, never pinned in prose).…
Fresh-context, read-only verifier for a proposed claude-obsidian change or release. Inspects the requested staged diff, unstaged worktree, explicit paths, or…
Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts,…
Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings…
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Proactive methodology guidance agent. Monitors note creation and provides real-time quality advice. Suggests connections, flags quality issues, recommends MOC…
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Analyze session token usage and cost patterns. Identify expensive operations and recommend optimizations. Use to understand and reduce session costs.
Specialized debugging agent. Use when facing hard bugs, test failures, or runtime errors that need systematic investigation.
Search and find previous code agent sessions (Claude-Code or Codex-CLI) for specific work, decisions, or code patterns. Use when user asks about previous…
Use this agent when the user explicitly requests UI testing, interface validation, or browser-based inspection tasks. This agent is specifically designed to…
Analyze alignment between daily activities and long-term goals. Identify gaps, over/under-investment, and suggest rebalancing. Use for goal audits and priority…
Process inbox items using GTD principles. Categorize, clarify, and organize captured notes into actionable items. Use for inbox zero and capture processing.
Organize and restructure vault notes. Fix broken links, consolidate duplicates, suggest connections, and maintain vault hygiene. Use when managing vault…
This document is a reference for implementing a new **agent provider** in Nimbalyst. It is the architectural counterpart to `docs/AI_PROVIDER_TYPES.md` (which…
Status: **STUCK**. Three approaches tried, none reliably solves the pre-edit race for `update`-kind file_change items. This doc captures everything learned so…
Run E2E tests in a dev container for isolated, reproducible test execution. Use proactively when asked to run Playwright tests, E2E tests, or when in a…
Builds interactive HTML explorables for Engram threshold concepts under the binding Explorable Contract. Use after encoding a threshold node, or to re-encode a…
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the…
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns…
公司 CEO(Jeff Bezos 思维模型)。当需要评估新产品/功能想法、商业模式和定价方向、重大战略选择、资源分配和优先级排序时使用。
公司 CTO(Werner Vogels 思维模型)。当需要技术架构设计、技术选型决策、系统性能和可靠性评估、技术债务评估时使用。
全栈技术主管(DHH 思维模型)。当需要写代码和实现功能、技术实现方案选择、代码审查和重构、开发工具和流程优化时使用。
Scans a single company's career portal for job openings. Spawned by the scan skill when processing multiple companies from a watchlist. <example> Context: User…
Efficient email management, meeting notes, and administrative tasks
Use this agent when reviewing code to ensure features are agent-native - that any action a user can take, an agent can also take, and anything a user can see,…
Use this agent when you need to create or update README files following the Ankane-style template for Ruby gems. This includes writing concise documentation…
Use this agent when you need to analyze code changes from an architectural perspective, evaluate system design decisions, or ensure that modifications align…
GTD-style processing of incoming entries. Decide action for each item - do now, schedule, delegate, save, or delete.
Organize vault, find orphan notes, suggest connections, update MOC indexes, consolidate duplicates.
Automation Specialist. Use proactively for API integrations, MCP server setup, webhook receivers, OAuth flows, automations, and the connection layer of…
HR / Talent Acquisition. Use proactively when the user asks to hire a new specialist, asks "can the team do X" where X isn't covered by the current six, or…
Senior Researcher. Use proactively for any task that needs cross-source verification before action — hire research briefs (mandatory step in SOP-001),…
Generates Obsidian canvas files from memory data. Creates visual dashboards for relationship maps, morning briefs, and project boards.
PRIMARY handler for pasted content. Formats, adds provenance, prepares for filing.
Extracts structured data from documents. Tables, lists, action items.
Kod geçmişi araştırmacısı. Git blame, commit geçmişi ve diff analizi yaparak kodun neden böyle yazıldığını ortaya çıkarır. Kullanıcı bir kodun geçmişini, bir…
Kalite ve bütünlük denetçisi. Yapılan işi CLAUDE.md kuralları, bilgi tabanı ve önceki kararlarla çapraz kontrol eder. Stop hook ile otomatik, /audit komutuyla…
Veri bazlı çalışma koçu. Günlük notlar, görev panosu ve denetim kayıtlarını analiz ederek verimlilik kalıplarını, tükenmişlik sinyallerini ve kaçırılan…
Read-only Resume Team auditor that returns an exhaustive PASS or FAIL verdict without editing the draft.
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic