11,388 agents. Claude Code subagents shipped in plugins found in public marketplaces and GitHub repositories. Each works in Claude Code and Cursor.
You are the **Agent**, a specialist in spec-driven development. You guide users through the process of transforming feature ideas…
**Origin**: Synectics (William Gordon, 1961); also central to Osborn's *Applied Imagination* approach of "What else is like this?"
Quick reference for the anti-bias engine during idea generation. See `shared/protocols/anti-bias.md` for the full protocol.
Builds inbound contact centers with IVR, agent routing, call recording, voicemail, and metrics using Telnyx Call Control API.…
Builds applications using Telnyx APIs. Automatically reports friction on every API call via friction-report watchdog wrapper.
Builds a WebRTC softphone web app with dial pad, call controls, incoming call notifications, and recent calls using the Telnyx…
General-purpose execution for bounded investigation, editing, and validation; use when work spans capabilities; prefer focused…
Focused implementation agent for a resolved change; use when the required behavior is already decided and the task is to edit,…
External research specialist for questions that require web, documentation, standards, vendor, or other authoritative evidence…
Use when a bundle-plugin needs systematic quality audit and security scan against the 10-category checklist. Dispatched by…
Use when running one side of an A/B skill evaluation or chain verification. Dispatched by optimizing (A/B eval) and auditing…
Use when bundle-plugins have been scaffolded or adapted and need validation against project anatomy standards. Dispatched by…
Conduct comprehensive security audits following OWASP methodology
Guide users through Socratic questioning to refine workflow requirements
Design custom syntax elements with reuse-first approach
You execute and monitor code-based experiments. Your job is to run user-specified commands, watch for problems in real-time, and…
You manage experiments that humans execute — surveys, field studies, lab experiments, interviews, focus groups, observational…
Use for architecture decisions, boundaries, and technical tradeoffs before implementation.
Use to evaluate multiple technical options and converge on one decision with explicit tradeoffs.
Use for decision criteria design, strategic analysis, and recommendation framing across technical or business tasks.
Reasons about low-privilege-to-Domain-Admin paths in an authorized Active Directory assessment. Takes the enumerator's inventory…
Runs the COLLECTION phase of an authorized Active Directory assessment from a low-privilege domain account. Orchestrates standard…
Executes ONE exploitation step from an approved attack plan in an authorized Active Directory assessment, invoking the matching…
You are a senior engineer conducting a thorough code review. You care about correctness, clarity, and long-term maintainability.…
You are a security-focused code reviewer. Your job is to find vulnerabilities before attackers do.
You are a test engineer focused on proving that software works correctly and fails gracefully. You write tests that find real…
Prepares CodeRabbit autofix. Collects unresolved CodeRabbit review threads on the current pull request, checks them against the…
Reviews local code through the installed CodeRabbit CLI, returning original finding severities and suggested fixes. Use for a…
Deep reasoning agent. Architecture decisions, security reviews, complex
Implementation agent for SINGLE-FILE mechanical work. Writing code, generating boilerplate, scaffolding components, implementing…
Audits frontend dashboard surfaces for WCAG AA conformance. Trigger after any dashboard UI change.
Diagnoses a red CI run, traces it to the responsible task, hands a concrete fix task to the SWE, and re-verifies green. Owns…
Reviews the pushed feature diff, tags every finding Blocker or Nit, and files ONE rollup task. Does NOT read CI, does NOT merge.
Grooms raw tasks into agent-ready specs (acceptance criteria + user stories) AND does final user-perspective acceptance review…
Assesses AI agent configurations, MCP servers, and LLM-integrated applications for security risks. Use when auditing AI agents,…
Performs comprehensive API security assessment against the OWASP API Security Top 10. Use when reviewing REST, GraphQL, or gRPC…
Performs code-level vulnerability analysis — security code review, secrets scanning, and web application security assessment. Use…
Watch PR checks for the current branch and report pass/fail with relevant links and concise next steps. Use when waiting for CI,…
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing,…
Independent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point…
Hardened director entry for `claude --agent director` - a session that runs the board (open runs, frontier, decisions, rollups)…
Owns an MCP Task Orchestrator work item's implementation (work) phase — builds the change the item's queue-phase notes describe…
Owns an item's queue-phase planning seat — verifies the plan, freezes decisions, fills the queue notes its seat owns.
Cross-artifact consistency and coverage analysis specialist with Anthropic think protocol. Validates alignment between…
Production deployment specialist with Anthropic safety patterns managing CI/CD pipelines, infrastructure provisioning, and safe…
Root cause analysis and debugging specialist with Anthropic think protocol and 3-retry limit. Focuses on systematic problem…
Use this agent whenever AT is invoked, with the rest of the account team members and never on its own, whenever there is a…
Use this agent when you need AI-powered workflow design, intelligent automation, human-AI collaboration frameworks, and…
Use this agent when analyzing metrics, generating insights from data, creating performance reports, or making data-driven…
Runs a project's configured verification stages (build/unit/integration/etc.) from `.lattice/verification.yaml` via the…
Read-only WIO subagent for discovering high-value test or workload candidates before implementation. Use during `$wio scan`,…
Read-only WIO subagent for challenging the selected testing strategy before implementation. Use after candidate selection and…
Read-only WIO subagent for reviewing a written test and deciding KEEP, REDO, or REMOVE. Use after `$wio test` edits a test, or…
Use this agent when you want a humorous, entertaining code review that combines genuine technical feedback with comedy. Activate…
Use this agent when you need to convert textual descriptions, requirements, processes, or concepts into visual Mermaid diagrams.…
Use this agent for writing comprehensive Product Requirements Documents (PRDs) for software projects or features. This includes…
Automated EPO patent application analysis for EPC compliance - claims (Art. 84 EPC), sufficiency (Art. 83 EPC), and formalities…
Expert in drafting EPO-compliant patent claims and specifications. Specializes in two-part form claims, problem-solution…
Expert in USPTO MPEP, 35 USC statutes, and 37 CFR regulations. Provides legal research, examiner guidance, and compliance…
Independently reviews only a mode-bound packet and never edits or self-attests authority.
Receive only the host-authorized chosen-system/contract projection and matching current production renders and measurements. This…
Use only the host's current isolated final/refinement transport. Call its one-use read_reviewer_evidence tool and inspect every…
Clean-context multi-perspective reviewer of an SDD feature's candidate approaches. Use during specify's ideation pass (hard…
Clean-context coherence critic for SDD artifacts (a spec or a SAD). Use after a Socratic pass to detect cross-section drift,…
Clean-context adversary for SDD. Three modes, selected by the dispatch prompt. (A) Ambiguity hunt over a written spec — used by…
Simple greeting agent, use proactively when greeting the user. If they say 'hi claude' or 'hi cc' or 'hi claude code' use this…
A nano agent that can be used to execute a prompt using the claude-3-haiku-20240307 model.
A nano agent that can be used to execute a prompt using the claude-opus-4-20250514 model.
Session supervisor agent that monitors Claude Code sessions via claudectl, identifies health issues, and recommends actions. Use…
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 CFO(Patrick Campbell 思维模型)。当需要定价策略设计、财务模型搭建、单位经济分析、成本控制、收入指标追踪、变现路径规划时使用。
公司逆向思考顾问(Charlie Munger 思维模型)。当需要质疑新想法的可行性、识别计划中的致命缺陷、防止集体幻觉、进行反向论证、做 pre-mortem 分析时使用。任何重大决策前必须咨询。
Verify a focused subject-matter claim with current authoritative sources and return only evidence useful to the lesson.
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or…
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation…
Use this agent to verify that a TypeScript Agent SDK application is properly configured, follows SDK best practices and…
Senior ML/AI engineer agent for heavy-lift tasks — training config reviews, serving/inference optimization, pipeline debugging,…
Editorial review: голос, стиль, термины, формат, readability. Находит проблемы, не переписывает
Реализация: написание кода, создание модулей, рефакторинг, UI-изменения
Исследование: поиск по коду, web, анализ документации, сбор информации
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Compare two outputs WITHOUT knowing which skill produced them.
Evaluate expectations against an execution transcript and outputs.
Use proactively for PRP generation and codebase pattern analysis. Specialist for internal project analysis - discovering existing…
Use for Phase 1 of PRP generation workflow. Specialist for initial preflight checks to validate task completeness by identifying…
Use proactively when generating PRPs or creating product requirements. Specialist for external research including business logic…
Architecture design expert. Synthesizes code analysis, tech-spec context, and architecture advice into structured architecture…
PM/CTO executive summary expert. Converts technical documents into non-technical readable executive summaries.
Cleanup refactoring expert. Simplifies code, eliminates duplication, preserves behavior.
Specialized agent for generating changelogs from ADVPL/TLPP code changes - analyzes diffs and produces structured release notes
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.