A lead research agent that receives a user's question, breaks it into smaller research tasks, coordinates six research groups, and combines their results. The source describes the groups and workflow in Chinese.
Use when: evaluating range/IL/exposure risk before a rebalance or deposit. Analyzes concentrated liquidity positions for impermanent loss, fee APR, range width, capital efficiency, and cross-DEX yield comparison. Triggers on keywords: IL, impermanent loss, range risk, rebalance risk, deposit risk, exposure, fee APR…
Generate a migration report from workspace artifacts. Reads status.md, visual reports, and screenshot directories to build report-data.json, then runs the HTML report generator.
Especialista em metricas de lancamento digital — diagnostico de funil completo (impressoes -> cliques -> leads -> aquecidos -> visitantes PV -> checkout -> compra), calculo CPL/CAC/LTV/ROAS/ROI/ticket medio/conversao por etapa, comparacao com benchmarks Brasil 2026 por nicho, identificacao de gargalos CIMA pra BAIXO…
Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and…
Generates the final pull-request title and body after a 4CO-OP run is approved. Uses the plan, diff, builder notes, reviewer notes, and gatekeeper verdict to produce a clear PR description.
Designs a concrete implementation blueprint for a new feature and writes the six plan documents directly — slices, files to create/modify, frozen per-slice API contracts, and data model changes. Slices the work vertically into contract-bounded work-units decomposed for maximum parallelism (BE/FE halves parallelise…
Teach and explain existing codebases at project, module, and deep source-reading scopes, with source-grounded call paths, tensor shapes, formulas, and persistent learning plans when useful.
Use this agent to gather codebase context for prompt transformation. Explores relevant files, finds similar implementations, identifies patterns to reference, and discovers tech stack constraints. Returns actionable context that makes transformed prompts specific to THIS codebase, not generic advice. Context: User…
A specialized helper for analyzing performance profiles from Ascend NPU tools, using local paths to profiling files such as ascendpt, ascendms, or PROF data.
Use this agent when a major project step has been completed and needs to be reviewed against the original plan and coding standards. Examples: After sub-phase implementation, after major feature completion, before merging to verify work meets requirements.
Reviews user-facing Angular changes for UX quality: every state exists (loading, empty, error, success), accessibility basics hold, components follow the codebase's existing patterns, and the flow works end-to-end. Angular-aware — also catches the framework's own failure modes. Use PROACTIVELY when a change adds or…
Use this agent when you need to refactor code for better organization, cleaner architecture, or improved maintainability. This includes reorganizing file structures, breaking down large components into smaller ones, updating import paths after file moves, fixing loading indicator patterns, and ensuring adherence to…
Read-only audit invocation for a claims-verifier pass. Carries Read, Grep, and Bash (recomputation only) and no network or write tools, so it can recompute hashes/figures over its sanctioned read set while an out-of-set write or fetch stays impossible by tool set. Spawned cold, per pass, by the claims-verifier…
Main-session orchestrator for multi-step work. Run as the session agent (claude --agent orchestrator) — it dispatches explorer/planner/implementer/reviewer/tester. Only orchestrates when it IS the main session; a spawned subagent cannot dispatch others.
Level 2 orchestrator. Coordinates comprehensive code reviews across all dimensions by routing PR changes to appropriate specialist reviewers. Select when PR analysis and specialist coordination required.
Runs and explains the @aziontech/webkit adoption flow — npx @aziontech/webkit init. Sets up deps, lint configs, pre-commit, the webkit MCP, and the Claude Code bundle in this project, idempotently.
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples: Context: User wants to create a code review agent user: "Create an agent…
★not rated 2 5mo agoA254 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: