调试
定位并修复问题，分析错误
dry-refactoring
YYH211
Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY principle, or mentions code smells like copy-paste, magic numbers, or repeated logic. Implements a 4-step workflow from identifying repetition to verified refactoring.
investigate
incidentfox
Systematic incident investigation methodology. Use when investigating production issues, service degradation, errors, latency spikes, or outages.
aws-troubleshoot
incidentfox
AWS service troubleshooting patterns. Use for EC2, ECS, Lambda, CloudWatch, RDS issues.
log-analysis
incidentfox
Partition-first log analysis methodology. Use for log searches, error analysis, pattern finding across Datadog, CloudWatch, or Kubernetes logs.
sre-principles
incidentfox
Core SRE behavioral principles for incident response. Guides intellectual honesty, evidence-based reasoning, and communication standards.
moltbook-interact
oyi77
Automate interactions on Moltbook - post content, engage with threads, and manage account
code-review
VladimirBrejcha
Review pull requests, commits, or diffs for high-signal engineering issues and merge risk. Use when asked to review code, audit a patch, find bugs, or provide merge readiness feedback. Focus on defects introduced by the proposed changes (correctness, security, performance, reliability, and maintainability) and report actionable findings with severity, confidence, and precise code locations.
revenuecat
VladimirBrejcha
Comprehensive assistance with RevenueCat in-app subscriptions and purchases
swiftui-performance-audit
VladimirBrejcha
Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient.
swift-testing
VladimirBrejcha
Use when writing tests with Swift Testing (@Test, #expect, #require), migrating from XCTest, implementing async tests, or parameterizing tests.
swift-concurrency
VladimirBrejcha
Guide for building, auditing, and refactoring Swift code using modern concurrency patterns (Swift 6+). This skill should be used when working with async/await, Tasks, actors, MainActor, Sendable types, isolation domains, or when migrating legacy callback/Combine code to structured concurrency. Covers Approachable Concurrency settings, isolated parameters, and common pitfalls.
silent-pushes-setup
VladimirBrejcha
Setup, debug, or validate iOS silent (background) push notifications with APNs, including entitlements, device token registration, backend APNs sending, and widget refresh. Use for silent push setup or troubleshooting (aps-environment errors, token registration, background delivery, APNs headers).
SKILL.md — AI Skill Definition
ricardodantas
Source: https://github.com/ricardodantas/ratatui-themes
tauri
johnlarkin1
"Comprehensive Tauri v2 development skill for building cross-platform desktop applications with Rust backends and web frontends. This skill should be used when creating new Tauri apps, adding commands and IPC communication, developing plugins, managing application state, or integrating Rust with JavaScript/TypeScript frontends. Triggers on tasks involving #[tauri::command], invoke(), Tauri plugins, desktop app development, or Rust-WebView integration."
process-modeling
melodic-software
Process modeling using BPMN notation and flowchart patterns. Creates process diagrams with activities, gateways, events, swimlanes, and decision points for workflow documentation.
loop
saadshahd
Start autonomous iteration loop. Triggers on "loop", "keep going", "continue until done", "implement feature", "fix all", "loop status", "cancel loop".
verify
saadshahd
Fast parallel verification before PR. Use when "verify", "review my changes", "is this ready", "pre-review", "check before PR", or after loop completes.
watch
saadshahd
Monitored development with dev3000 (d3k). Use when debugging web apps, needing full-stack visibility, reading error context, or capturing browser + server logs. Triggers on "watch", "d3k", "dev3000", "monitor app", "capture logs", "what went wrong", "error context".
intent
saadshahd
Turn rough ideas into iron-clad work orders. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests.
commit
Casper-Studios
Generate commit messages following conventional commits and commit staged changes. Use when creating commits or when user invokes /commit.
pr-comments
Casper-Studios
Triage unresolved PR review comments, produce a severity-ordered fix plan, then resolve or fix each issue with subagents. Use when addressing PR feedback before merge.
tcp-ip
chaterm
TCP/IP 网络诊断与排查
investigate-bug
doodledood
Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.
optimize-prompt-token-efficiency
doodledood
'Iteratively optimizes prompts for token efficiency by maximizing information density - reduces verbosity, removes redundancy, tightens phrasing while preserving semantic content. Use when asked to compress, shorten, reduce tokens, tighten, maximize density, increase information density, or make a prompt more concise.'