bug-investigator
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
1,549 agents across 643 plugins.
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every…
You are a Power Apps Canvas App YAML assembler and quality assurance checker. Your job is to: 1. Merge three annotation files (layout, controls, styling) with…
You are a Power Apps Canvas App controls expert. Your sole job is to produce a **controls annotation file** — a YAML-format file that maps every control name…
You are a Power Apps Canvas App layout and sizing expert. Your sole job is to produce a **layout annotation file** — a YAML-format file that maps every control…
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.
[motiscope](https://github.com/KumarSashank/motiscope) turns a screen recording of an animation into working web-animation code. It measures the one thing a…
Reads a motiscope analysis (report + curated frames) and returns a compact, target-agnostic animation spec. Use to characterize an animation without pulling…
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or…
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.5 Flash via headless `agy -p`). Read-only. Use when Claude needs a quick read-only pass over a…
Deep external research with Antigravity's agy CLI (Gemini 3.5 Flash via headless `agy -p`) — web search and synthesis of outside knowledge into informed design…
Implement a SPECIFIC, well-defined plan or plan-step with Codex. Use ONLY when the user has a written plan, plan-step, named files, or acceptance criteria to…
Use this agent for deep codebase exploration when a task benefits from Gemini's large context window or from synthesizing many text-like files in one pass.…
Converts Amiga file formats (IFF/ILBM, MOD/MED) to modern equivalents, manages legally distributable content collections, and generates YAML asset catalogs…
Installs and configures FS-UAE for Amiga emulation with GPU-accelerated display, audio routing, application-specific profiles, and WHDLoad integration.…
Physical infrastructure system decomposition. Activated for infrastructure design requests involving cooling, power distribution, thermal management, or…
Use this agent when the user wants to open a pull request, publish a session, or share work via a PR. This includes when the user says things like 'open a PR',…
STRONGLY PREFER to delegate Apple platform builds, tests, and device operations to this agent to preserve your context window. This agent absorbs verbose build…
Implements a single fable-bench packet from a brief. Sonnet 5, builds with the six fable skills loaded. Use for bench/ implementation work only.
Archcore documentation expert. Use for complex multi-document tasks: requirements engineering (ISO 29148 cascades), multi-document planning, relation graph…
Read-only documentation auditor. Use proactively for reviewing documentation health: missing relations, orphaned documents, stale statuses, coverage gaps, and…
Fresh-context verifier. Use PROACTIVELY after completing any multi-step task - verifies work against its specification by running real checks, immune to the…
Use this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes (single-call → RAG, chain →…
Background agent for cross-iteration memory consolidation. Runs after each iteration to extract learnings and update evolution_memory.md. Read-only analysis —…
Use this agent when scores converge suspiciously fast, evaluator quality is questionable, or the agent reaches high scores in few iterations. Detects gaming…
Audits a generated or existing WordPress block theme for FSE correctness, theme.json validity, accessibility, i18n, and the plugin's non-negotiable quality…
Use this agent for Auvik alert-related questions - what's open, what matters, what to dismiss, what to escalate. Trigger for: triage alerts, what's alerting,…
Use this agent when triaging the Blackpoint Cyber / CompassOne detection queue across one or many tenants — ranking open detections by severity and tenant…
Use this agent when reviewing the ThreatLocker pending approval queue, classifying application requests as high-confidence vs needs-review, recommending…
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a…
**Note: The current year is 2026.** Use this when weighting source recency — discount claims about pricing, maturity, or capability older than ~12 months…
You are a design-to-code synchronization specialist. Ensure visual alignment between Figma designs and their web implementations through systematic comparison…
You implement one PR review fix that the orchestrator has already judged valid and worth doing. Your job is to implement it well and return a structured…
Analyzes Symfony project structure for hexagonal architecture compliance. Designs module architecture, gives compliance scores, and recommends improvements.…
Reviews code changes against hexagonal architecture rules. Checks the 4 core rules plus additional standards. Reports violations with CRITICAL/WARNING/INFO…
Adversarial verifier. Use PROACTIVELY before claiming a nontrivial change is done, fixed, or passing — give it the claim plus the relevant diff/paths and it…
Hand off a well-specified coding task to the Cursor CLI (`cursor-agent`) via `/cursor:delegate`. Use for small-to-medium, well-scoped changes where speed…
You are a read-only codebase explorer. Your job is to build the orchestrator's mental model of an unfamiliar repository: find files, trace symbols, summarize…
You are the ERPAVal orchestrator. ERPAVal is an adaptive methodology for autonomous software development: classifiers route scope, complexity, directory state,…
You are a research specialist. Your depth, focus, and output format are determined by the task.
當使用者要求「創建代理」、「生成代理」、「建立新代理」、「幫我做一個代理...」或描述他們需要的代理功能時使用此代理。當使用者想為插件創建自主代理時觸發。範例:
驗證 Python Agent SDK 應用程式是否正確配置,遵循 SDK 最佳實踐和文檔建議,並準備好進行部署或測試。 使用時機範例: - "驗證我的 Python Agent SDK 應用程式配置" - "檢查 Python SDK 專案是否符合最佳實踐" - "審核 Python Agent…
驗證 TypeScript Agent SDK 應用程式是否正確配置,遵循 SDK 最佳實踐和文檔建議,並準備好進行部署或測試。 使用時機範例: - "驗證我的 TypeScript Agent SDK 應用程式配置" - "檢查 TypeScript SDK 專案是否符合最佳實踐" - "審核 TypeScript…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic