调试
定位并修复问题，分析错误
candid-loop
ron-myers
Run candid-review in a loop until all issues are resolved, with configurable auto, review-each, or interactive modes and support for ignored issues
webgl-expert
ronnycoding
Expert guide for WebGL API development including 3D graphics, shaders (GLSL), rendering pipeline, textures, buffers, performance optimization, and canvas rendering. Use when working with WebGL, 3D graphics, canvas rendering, shaders, GPU programming, or when user mentions WebGL, OpenGL ES, GLSL, vertex shaders, fragment shaders, texture mapping, or 3D web graphics.
candid-validate-standards
ron-myers
Validate Technical.md for vague rules, linter overlaps, and effectiveness issues
salvo-error-handling
salvo-rs
Handle errors gracefully with custom error types, status codes, and error pages. Use for building robust APIs with proper error responses.
copilot
dangeles
Use when reviewing code for correctness, efficiency, edge cases, or potential bugs in an adversarial but collaborative manner, or when bioinformatician/developer needs a second opinion.
adversarial-review
whynowlab
Devil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth. Use for high-stakes review, stress-testing choices, or when the user wants problems found deliberately. NOT for routine code review (use engineering:code-review). Triggers on "스트레스 테스트", "stress test", "devil's advocate", "반론", "이거 괜찮아", "문제 없을까", "깊은 리뷰", "critical review", "adversarial".
security-audit
ils15
"Security audit and vulnerability detection - OWASP Top 10, input validation, injection attacks"
code-review-checklist
ils15
Systematic code review using quality gates, SOLID principles, error handling patterns, and test coverage analysis. Provides structured feedback with severity levels and actionable improvements.
observability-patterns
vanman2024
Comprehensive observability setup patterns for Google ADK agents including logging configuration, Cloud Trace integration, BigQuery Agent Analytics, and third-party observability tools (AgentOps, Phoenix, Weave). Use when implementing monitoring, debugging agent behavior, analyzing agent performance, setting up tracing, or when user mentions observability, logging, tracing, BigQuery analytics, AgentOps, Phoenix, Arize, or Weave.
a2a-executor-patterns
vanman2024
Agent-to-Agent (A2A) executor implementation patterns for task handling, execution management, and agent coordination. Use when building A2A executors, implementing task handlers, creating agent execution flows, or when user mentions A2A protocol, task execution, agent executors, task handlers, or agent coordination.
production-deployment
vanman2024
Production deployment patterns for ElevenLabs API including rate limiting, error handling, monitoring, and testing. Use when deploying to production, implementing rate limiting, setting up monitoring, handling errors, testing concurrency, or when user mentions production deployment, rate limits, error handling, monitoring, ElevenLabs production.
api-design-patterns
ils15
Design RESTful APIs with proper HTTP methods, status codes, pagination, filtering, error responses, and OpenAPI documentation. Follows FastAPI best practices with Pydantic validation.
workflow-canvas
vanman2024
Celery canvas patterns for workflow composition including chains, groups, chords, signatures, error handling, and nested workflows. Use when building complex task workflows, parallel execution patterns, task synchronization, callback handling, or when user mentions canvas primitives, workflow composition, task chains, parallel processing, or chord patterns.
zig-sdl3-bindings
rudedogg
Zig bindings for SDL3 multimedia library. Use for cross-platform game
zig
rudedogg
Up-to-date Zig programming language patterns for version 0.15.x. Use when writing, reviewing, or debugging Zig code, working with build.zig and build.zig.zon files, or using comptime metaprogramming. Critical for avoiding outdated patterns from training data - especially build system APIs (root_module instead of root_source_file), I/O APIs (buffered writer pattern), container initialization (.empty/.init), allocator selection (DebugAllocator), and removed language features (async/await, usingnamespace).
review-pr
richtabor
Reviews PR comments from GitHub (Copilot, reviewers), evaluates against actual code, replies with reasoning, and resolves threads. Triggers on "review pr comments", "address pr feedback", "fix pr comments", or "review copilot suggestions".
fresh-eyes
richtabor
Re-reads code you just wrote with fresh perspective to catch bugs, errors, and issues. Use after completing a feature, fixing a bug, or any code changes. Triggers on "review my code", "fresh eyes", "check for bugs", "did I miss anything", or "sanity check".
accessibility-review
richtabor
Reviews UI for accessibility issues against WCAG 2.1/2.2 AA. Triggers on "is this accessible?", "check accessibility", or contrast/a11y review requests.
bug-blitz
ArjenSchwarz
Batch-fix all open bugs in parallel using git worktrees. Fetches bug-type tasks in "idea" status from Transit, creates an isolated worktree per bug, and spawns parallel subagents each running the fix-bug workflow. Use when you want to tackle all open bugs at once, e.g. "fix all open bugs", "bug blitz", "resolve all Transit bugs".
effect-best-practices
betalyra
Enforces Effect-TS patterns for services, errors, layers, and atoms. Use when writing code with Effect.Service, Schema.TaggedError, Layer composition, or effect-atom React components.
use-typescript-sdk
iskysun96
"Guides usage of @aptos-labs/ts-sdk for interacting with the Aptos blockchain from TypeScript/JavaScript applications.
re-frame-pair
day8
Pair-program with a live re-frame application via shadow-cljs nREPL. Inspect app-db, dispatch events, hot-swap handlers, trace dispatches, read epoch data, time-travel, and perform post-mortems without source edits when probing. Use whenever the user asks about their running re-frame app or mentions: re-frame, app-db, dispatch, subscribe, reg-event, reg-sub, reg-fx, epoch, interceptor, re-frame-10x, re-com, shadow-cljs.
troubleshoot-errors
iskysun96
"Diagnoses and fixes Aptos Move compilation, runtime, and deployment errors. Triggers on: 'error', 'fix this',
transit
ArjenSchwarz
Route Transit tickets to the appropriate workflow based on task type. Use when a user mentions a T-[number] ticket reference and wants to work on it. Fetches task details and dispatches to the correct skill (fix-bug, creating-spec, planning mode, or asks for clarification).