Chargement du README du dépôt…
Affichage de 22 skills collectés sur 22.
Continue NeverD x64 PE/COFF C-quality work: HighC structured C, LLVMC (llvm-to-C / `neverd decompile --llvm`) for obfuscated executables, Windows SEH/C++ EH readability, unnamed globals, local declarations, and Win64 ABI. Use when the user asks to improve x64…
Langue du texte source : anglais
Diagnose NeverD runtime tests that fail only or intermittently on GitHub Actions. Use for runner-specific crashes, signals, timeouts, or semantic mismatches; not ordinary local failures or workflow configuration errors.
Langue du texte source : anglais
Analyze anti-cheat architecture and detection tradeoffs across client, kernel, hypervisor, and backend layers. Use for system-level defense design; use narrower skills for PCIe DMA or Windows kernel details.
Langue du texte source : anglais
Maintain the awesome-game-security resource index. Use when adding or reclassifying links, organizing categories, or checking README format; use topic skills for security research itself.
Langue du texte source : anglais
Build compiler frontends, IR generation, optimization pipelines, or code generation with LLVM. Use for language and DSL compiler work; use narrower LLVM skills for isolated tooling or analysis tasks.
Langue du texte source : anglais
Analyze PCIe DMA threats, FPGA device behavior, and IOMMU defenses. Use for DMA-specific threat modeling or detection; use windows-kernel-security for kernel mechanisms without a DMA boundary.
Langue du texte source : anglais
Build dynamic instrumentation, runtime tracing, coverage, profiling, or monitoring with LLVM-related tooling. Use static-analysis when execution is not part of the analysis.
Langue du texte source : anglais
Research game-engine internals, source trees, SDK extraction, plugins, and engine-specific security surfaces. Use for Unreal, Unity, Source, Godot, or custom-engine structure rather than generic cheat techniques.
Langue du texte source : anglais
Classify game-cheat implementation surfaces and their defensive implications. Use for authorized threat modeling of memory access, injection, overlays, input, or engine attack surfaces.
Langue du texte source : anglais
Analyze graphics API interception, overlays, and render pipelines across DirectX, OpenGL, and Vulkan. Use for swap-chain, Present, SwapBuffers, shader, draw-call, or capture interactions.
Langue du texte source : anglais
Teach LLVM, Clang, and compiler concepts or assemble a learning path. Use for explanations and educational resources, not implementation work covered by a specialized LLVM skill.
Langue du texte source : anglais
Implement or analyze LLVM optimization passes, pipelines, and generated-code quality. Use for IR transformation and pass behavior, not general application performance tuning.
Langue du texte source : anglais
Apply or develop LLVM sanitizers, compiler hardening, and exploit mitigations. Use when secure compilation is central, not for general vulnerability analysis unrelated to the toolchain.
Langue du texte source : anglais
Build Clang plugins, LibTooling tools, LLDB extensions, or clangd/LSP integrations. Use for developer tooling around LLVM, not compiler pipeline implementation.
Langue du texte source : anglais
Build MLIR or CIR dialects, conversions, passes, and multi-level compiler pipelines. Use when MLIR/CIR is the implementation substrate, including ML and domain-specific compilers.
Langue du texte source : anglais
Analyze Android or iOS game security and platform protections. Use for APK/IPA, mobile IL2CPP, Frida, root or jailbreak, emulator, mobile kernel, or mobile anti-cheat research.
Langue du texte source : anglais
Diagnose NeverD lifting bugs caused by duplicated or divergent semantic decisions across pipeline surfaces. Use for cross-architecture, cross-format, order-dependent, verifier, PHI, ABI, or provenance inconsistencies; not isolated feature work.
Langue du texte source : anglais
Design or audit UI for Qt/QML, Qt projects, web, or embedded MPU or MCU targets. Use when creating screens, layouts, navigation, or auditing UX.
Langue du texte source : anglais
Select and use reverse-engineering workflows for protected game or anti-cheat binaries. Use for disassembly, decompilation, debugging, memory artifacts, anti-analysis, and tool choice; use narrower skills for lifting or kernel internals.
Langue du texte source : anglais
Implement LLVM-based dataflow, pointer, taint, dependency, or verification analyses. Use for static program-analysis algorithms and tools, not runtime instrumentation.
Langue du texte source : anglais
Analyze Windows kernel security mechanisms used by drivers and game protection. Use for callbacks, IRQL, kernel memory, PatchGuard, DSE, HVCI, or driver trust; use dma-attack-techniques for PCIe DMA.
Langue du texte source : anglais
Diagnose reproducible bugs and test failures by gathering evidence, isolating the failing boundary, and testing a root-cause hypothesis. Use when the cause is unclear or an attempted fix did not work.
Langue du texte source : anglais
Copiez ce prompt dans l’assistant IA que vous utilisez.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/NeverSight/NeverD.Le README n’a pas pu être chargé. Vous pouvez toujours consulter les Skills du dépôt ci-dessous.