调试
定位并修复问题，分析错误
k8s-diagnostics
rohitg00
Kubernetes diagnostics for metrics, health checks, resource comparisons, and cluster analysis. Use when analyzing cluster health, comparing environments, or gathering diagnostic data.
k8s-troubleshoot
rohitg00
Debug Kubernetes pods, nodes, and workloads. Use when pods are failing, containers crash, nodes are unhealthy, or users mention debugging, troubleshooting, or diagnosing Kubernetes issues.
k8s-core
rohitg00
Core Kubernetes resource management for pods, namespaces, configmaps, secrets, and nodes. Use when listing, inspecting, or managing fundamental K8s objects.
k8s-multicluster
rohitg00
Manage multiple Kubernetes clusters, switch contexts, and perform cross-cluster operations. Use when working with multiple clusters, comparing environments, or managing cluster lifecycle.
effect-ts
sablier-labs
This skill should be used when the user asks about Effect-TS patterns, services, layers, error handling, service composition, or writing/refactoring code that imports from 'effect'. Also covers Effect + Next.js integration with @prb/effect-next.
error-handling
cosmix
Comprehensive error handling patterns and strategies including Rust Result/Option, API error responses, data pipeline error handling, and security-aware error handling. Use when implementing exception handling, error recovery, retry logic, circuit breakers, fallback mechanisms, graceful degradation, or designing error hierarchies. Triggers: error, exception, try, catch, throw, raise, Result, Option, panic, recover, retry, fallback, graceful degradation, circuit breaker, error boundary, 500, 4xx, 5xx, thiserror, anyhow, RFC 7807, error propagation, error messages, stack trace.
code-flow-tracer
lis186
Trace code execution paths and data flow. Use when user asks "how does X work", "what happens when X", "trace the flow of X", "where does data come from", or needs to understand feature implementation.
flow
lis186
Extract business logic flow from code, trace execution path from entry point
qodo-pr-resolver
qodo-ai
Review and resolve PR issues with Qodo - get AI-powered code review issues and fix them interactively (GitHub, GitLab, Bitbucket, Azure DevOps)
trace
ReinaMacCredy
Show agent execution timeline and performance summary
setup-check
ReinaMacCredy
Verify Maestro plugin prerequisites — Agent Teams flag, jq, trace MCP, PSM tools, directories, and hooks.
ultraqa
ReinaMacCredy
Iterative fix-and-verify loop for tests, build, lint, or typecheck. Diagnoses failures, applies fixes, re-verifies — up to 5 cycles.
review
ReinaMacCredy
Code review with auto-fix — plan-vs-implementation comparison or structured git-diff review. Automatically fixes issues found during review.
doctor
ReinaMacCredy
Diagnose and fix Maestro installation issues
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.
qodo-get-rules
qodo-ai
"Loads org- and repo-level coding rules from Qodo before code tasks begin, ensuring all generation and modification follows team standards. Use before any code generation or modification task when rules are not already loaded. Invoke when user asks to write, edit, refactor, or review code, or when starting implementation planning."
handoff
petekp
Generate a smart bootstrap prompt to continue the current conversation in a fresh session. Use when (1) approaching context limits, (2) user says "handoff", "bootstrap", "continue later", "save session", or similar, (3) before closing a session with unfinished work, (4) user wants to resume in a different environment. Outputs a clipboard-ready prompt capturing essential context while minimizing tokens.
auth0-react-native
auth0
Use when adding authentication to React Native or Expo mobile apps (iOS/Android) with biometric support - integrates react-native-auth0 SDK with native deep linking
writing-go
alexei-led
Idiomatic Go 1.25+ development. Use when writing Go code, designing APIs, discussing Go patterns, or reviewing Go implementations. Emphasizes stdlib, concrete types, simple error handling, and minimal dependencies.
code-explore
sd0xdev
"Pure Claude code investigation. Use when: tracing execution paths, understanding architecture, diagnosing issues. Not for: dual-perspective review (use code-investigate), code review (use codex-code-review). Output: analysis report with findings."
bug-fix
sd0xdev
"Bug fix workflow. Use when: fixing bugs, resolving issues, regression fixes. Not for: new features (use feature-dev), understanding code (use code-explore). Output: fix + regression test + review gate."
codex-implement
sd0xdev
"Implement features via Codex MCP. Use when: writing new code from specs, implementing features, Codex-driven development. Not for: code review (use codex-code-review), architecture advice (use codex-architect). Output: implemented code + review loop."
issue-analyze
sd0xdev
"GitHub Issue deep analysis. Use when: analyzing issue root cause, classifying problems, investigation planning. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + investigation strategy."
skill-health-check
sd0xdev
"Validate skill quality against routing, progressive loading, and verification criteria. Use when: auditing skills, checking skill health, reviewing skill design. Not for: code review (use codex-code-review) or doc review (use doc-review). Output: health report with per-skill ratings + Gate."