Debugging
Find and fix bugs, error analysis
fiftyone-dataset-inference
by voxel51
Run ML model inference (YOLO, YOLOv8, CLIP, SAM, Detectron2, etc.) on FiftyOne datasets. Use when running models, applying detection, classification, segmentation, embeddings, or any model prediction task. Also use for end-to-end workflows that include importing data then running inference.
thinking-second-order
by tjboudreaux
When a change has effects past the immediate fix—incentives, scale, feedback—trace consequence chains with timing and probability before committing.
thinking-thought-experiment
by tjboudreaux
'When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.'
thinking-socratic
by tjboudreaux
When a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden requirements before building or committing.
thinking-systems
by tjboudreaux
When behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.
github-contributor
by daymade
Strategic guide for becoming an effective GitHub contributor. Covers opportunity discovery, project selection, high-quality PR creation, and reputation building. Use when looking to contribute to open-source projects, building GitHub presence, or learning contribution best practices.
windows-remote-desktop-connection-doctor
by daymade
Diagnose Windows App (Microsoft Remote Desktop / Azure Virtual Desktop / W365) connection quality issues on macOS. Analyze transport protocol selection (UDP Shortpath vs WebSocket), detect VPN/proxy interference with STUN/TURN negotiation, and parse Windows App logs for Shortpath failures. This skill should be used when VDI connections are slow, when transport shows WebSocket instead of UDP, when RDP Shortpath fails to establish, or when RTT is unexpectedly high.
debugging-network-issues
by daymade
Evidence-driven investigation for network, streaming, and protocol-layer bugs. Use when debugging connection resets (ECONNRESET, HTTP/2 RST_STREAM, INTERNAL_ERROR), SSE or long-polling stalls, fixed-time connection drops, CDN/proxy/CGNAT idle timeouts, or any incident where symptoms do not match the obvious cause. Applies falsification-first methodology — layered isolation experiments to pin down the responsible network layer, env-gated runtime instrumentation for non-invasive observation, and counter-review agent teams to challenge single-cause assumptions. Strongly trigger on "socket closed unexpectedly", "stream interrupted", "ECONNRESET", "HTTP/2 INTERNAL_ERROR", "fails after N seconds", "works sometimes but not always", "upstream silent for X seconds", or any scenario where the investigator might jump to conclusions before evidence. Generalizes to any multi-layer system investigation where assumption-first thinking is the failure mode.
test-gap-analysis
by dotnet
Find or close verified gaps in existing tests. USE FOR: "add missing edge cases", "would tests catch this bug?", weak tests, survived boundaries/guards/ errors, or pseudo-mutation analysis. Polyglot. DO NOT USE FOR: a new suite (code-testing-agent), smells/assertion audits, or an actual mutation tool.
build-perf-baseline
by dotnet
"Establish build performance baselines and apply systematic optimization techniques. USE FOR: diagnosing slow builds, establishing before/after measurements (cold, warm, no-op scenarios), applying optimization strategies like MSBuild Server, static graph builds, artifacts output, and dependency graph trimming. Start here before diving into build-perf-diagnostics, incremental-build, or build-parallelism. DO NOT USE FOR: non-MSBuild build systems, detailed bottleneck analysis (use build-perf-diagnostics after baselining)."
clr-activation-debugging
by dotnet
Diagnoses .NET Framework CLR activation issues using CLR activation logs (CLRLoad logs) produced by mscoree.dll. Use when: the shim picks the wrong runtime, fails to load any runtime, shows unexpected .NET 3.5 Feature-on-Demand (FOD) dialogs, unexpectedly does NOT show FOD dialogs, loads both v2 and v4 into the same process causing failures, or any time someone is wondering "what is happening with .NET Framework activation?"
msbuild-antipatterns
by dotnet
"Detect and fix MSBuild anti-patterns in project and build files. USE WHEN asked to review, audit, lint, clean up, or code-review a .csproj/.vbproj/.fsproj/.props/.targets/.proj (or Directory.Build.props/.targets) file, when asked 'is this project file correct?' or 'what's wrong with my build file?', or when hunting subtle build bugs caused by how a project is authored. Each anti-pattern has a symptom and a concrete BAD→GOOD fix. DO NOT USE FOR: non-MSBuild build systems (npm, Maven, CMake), or migrating a project to SDK-style (use msbuild-modernization)."
migrate-mstest-v1v2-to-v3
by dotnet
Migrate MSTest v1/v2 projects to MSTest v3, and fix v1/v2-to-v3 breaking changes that surface after the packages are already at 3.x. USE FOR: removing v1 Microsoft.VisualStudio.QualityTools.UnitTestFramework assembly references; moving MSTest.TestFramework/TestAdapter 1.x-2.x to 3.x, the MSTest metapackage, or MSTest.Sdk; tests that broke after a 2.x-to-3.x bump -- CS0411/CS1503 on Assert.AreEqual/AreNotEqual/AreSame once the object overloads became generic, and DataRow strict type matching (1L vs 1) that builds with MSTEST0014 but fails at run time; .testsettings/LegacySettings to .runsettings (DeploymentEnabled, per-test MSTest TestTimeout); v3 timeout behavior; TFMs v3 dropped (net5.0, .NET Fx below 4.6.2, netstandard1.0). Applies even when the project already references MSTest 3.x, if a v1/v2-era setting or error remains. Keeps the current runner. DO NOT USE FOR: MSTest v4 (use migrate-mstest-v3-to-v4 next), clean v3 projects with no v1/v2 leftovers, other test frameworks, or VSTest-to-MTP.
maui-app-lifecycle
by dotnet
.NET MAUI app lifecycle guidance — the four app states, cross-platform Window lifecycle events (Created, Activated, Deactivated, Stopped, Resumed, Destroying), platform-specific lifecycle mapping, backgrounding and resume behavior, and state-preservation patterns. USE FOR: "app lifecycle", "window lifecycle events", "save state on background", "resume app", "OnStopped", "OnResumed", "backgrounding", "deactivated event", "ConfigureLifecycleEvents", "platform lifecycle hooks". DO NOT USE FOR: navigation events (use maui-shell-navigation), dependency injection setup (use maui-dependency-injection), platform API invocation (use conditional compilation and partial classes).
frontend-patterns
by WorldFlowAI
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
developing-ios-apps
by daymade
Develops iOS applications with XcodeGen, SwiftUI, and SPM. Triggers on XcodeGen project.yml configuration, SPM dependency issues, device deployment problems, code signing errors, camera/AVFoundation debugging, iOS version compatibility, or "Library not loaded @rpath" framework errors. Use when building iOS apps, fixing Xcode build failures, or deploying to real devices.
claude-md-progressive-disclosurer
by daymade
Optimize CLAUDE.md files using progressive disclosure. Goal: Maximize information efficiency, readability, and maintainability. Use when: User wants to optimize CLAUDE.md, information is duplicated across files, or LLM repeatedly fails to follow rules.
humanize-writing
by jpeggdev
Remove signs of AI-generated writing from text. Use when the user mentions 'sounds like AI,' 'too robotic,' 'humanize this,' 'make it sound human,' 'de-AI this,' 'sounds like ChatGPT,' 'make it natural,' or 'doesn't sound like a person wrote it.' Detects and fixes AI writing patterns including inflated significance, promotional language, formulaic structure, AI vocabulary, superficial analyses, vague attributions, hedging, robotic rhythm, em dash and boldface overuse, chatbot artifacts, and missing personality. Based on Wikipedia's "Signs of AI writing" guide and editorial best practices.
autonomous-loops
by codewithmukesh
Autonomous iteration loops for .NET development: build-fix, test-fix, refactor, and scaffold loops. Each loop has bounded iterations, progress detection, and fail-safe guards that prevent infinite retries and wasted tokens. Load this skill when Claude needs to fix build errors, fix failing tests, perform multi-step refactoring, scaffold a new feature, or when the user says "fix the build", "make the tests pass", "refactor this", "scaffold", "generate and verify", "keep going until it works", "autonomous", or "loop".
verification-loop
by codewithmukesh
7-phase .NET verification pipeline with structured PASS/FAIL reporting. Ensures every change is build-verified, diagnostics-clean, anti-pattern-free, test-passing, security-scanned, format-compliant, and diff-reviewed before marking work as complete. Load this skill when: "verify", "check everything", "run verification", "pre-PR check", "is this ready", "validate changes", "build and test", "quality gate", "pipeline check", "ready to merge".
code-review-workflow
by codewithmukesh
Structured code review workflow for .NET projects using Roslyn MCP tools. Multi-dimensional review covering correctness, security, performance, architecture compliance, and test coverage. Load when: "review PR", "review code", "code review", "PR review", "review changes", "review my code", "check code quality".
error-handling
by codewithmukesh
Error handling strategy for .NET 10 applications. Covers the Result pattern, ProblemDetails (RFC 9457), global exception handling, FluentValidation, and structured error responses. Load this skill when implementing error handling, validation, or designing API error contracts, or when the user mentions "error handling", "Result pattern", "ProblemDetails", "exception", "validation", "FluentValidation", "error response", "global exception handler", or "RFC 9457".
model-selection
by codewithmukesh
Strategic Claude model selection for .NET development workflows. Guides when to use Opus 4.6 (deep reasoning, architecture, ambiguous problems) vs Sonnet 4.6 (throughput, large context, routine implementation) vs Haiku 4.5 (fast, cheap subagent tasks). Covers model switching workflows, subagent model assignment, and cost-effective task routing. Load this skill when choosing models for tasks, optimizing costs, working with subagents, or when the user mentions "model", "Opus", "Sonnet", "Haiku", "which model", "cost", "switch model", or "fast mode".
learning-log
by codewithmukesh
Auto-document insights and discoveries during development sessions. Unlike MEMORY.md (corrective rules from the self-correction-loop skill), the learning log captures organic discoveries: non-obvious bugs, undocumented architecture decisions, performance findings, workarounds, and gotchas. Stored at .claude/learning-log.md. Load this skill when Claude discovers something non-obvious, finds a workaround, uncovers an undocumented decision, or when the user asks about "learnings", "discoveries", "gotchas", "what did we learn", or "document this finding".