288 skills · sorted by relevance
Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.
The English summary is being prepared. Showing the original description.
当用户直接要求进行数据集压缩测评，或在量化调优过程中需要使用 AISBench 评测工具输出数据集精度等场景时使用。 本 Skill 负责：使用 AISBench 数据集压缩代码、用 RBF Kernel Herding 算法生成压缩后的数据子集（coreset），并按用户目标交付两种产物之一： ① 接入量化调优主流程：产出独立的 coreset 数据集配置（不覆盖原始数据），回传「全集 config_name + coreset config_name」给编排层，供 evaluation.yaml 切换； ② 仅数据集压缩测评（不做量化调优）：基于 example 模板生成「全集测试脚本」和「子集测试脚本」两份 shell 脚本。 暂时支持 AIME 2025 和 GPQA，其他数据集需要再结合 aisbench tools目录下 herding_coreset_selector 源码进行分析。
The English summary is being prepared. Showing the original description.
Use when the user asks about NixOS, Nix language, flakes, nixpkgs, configuration.nix, nixos-rebuild, modules, options, overlays, derivations, mkDerivation, callPackage, home-manager, nix-darwin, devenv, packaging, cross-compilation, binary caches, garbage collection, NixOS containers, networking, firewall, systemd services, filesystems, LUKS, Wayland, X11, kernel, profiles, NixOS testing or VM tests, ISO images, Docker images, Raspberry Pi, Terraform, distributed builds, remote machines, pinning nixpkgs, rollback, generations, Nix Pills, or any topic related to configuring, packaging, deploying, or troubleshooting NixOS and the Nix ecosystem.
The English summary is being prepared. Showing the original description.
Perform forensic analysis of the macOS Unified Logging System (ULS) to investigate system events, application crashes, kernel panics, and potential indicators of compromise (IoCs) such as persistence mechanisms or unauthorized access.
The English summary is being prepared. Showing the original description.
Linux privilege escalation playbook. Use when you have low-privilege shell access and need to escalate to root via SUID/SGID binaries, capabilities, cron abuse, kernel exploits, misconfigurations, or credential harvesting on Linux systems.
The English summary is being prepared. Showing the original description.
Identify and exploit misconfigured Linux Capabilities. This skill covers how attackers escalate privileges to root without relying on SUID binaries or kernel exploits by abusing excessive capabilities like cap_dac_read_search, cap_sys_ptrace, or cap_setuid assigned to ordinary files.
The English summary is being prepared. Showing the original description.
Escape from Docker containers to the host system using container misconfigurations, mounted sockets, privileged mode, capabilities abuse, and kernel exploits. Use this skill when testing containerized environments for breakout vulnerabilities during penetration tests. Covers Docker socket mounting, cgroup escapes, nsenter techniques, and Kubernetes pod escapes.
The English summary is being prepared. Showing the original description.
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless build. No Playwright or SDK code to write. Use when an agent should operate a site itself, when a computer-use / browser-use setup needs a captured real fingerprint rather than a synthetic one, when agent sessions keep losing their login, or when comparing hosted agent-browser services. Also for 'MCP browser', 'browser MCP server', 'let my agent browse the web', 'agent browser control', 'browser-use MCP', 'computer use browser', 'Browserbase alternative', 'Steel browser alternative', 'headless browser detected'. Node (npx) or Python; Windows x64, macOS Intel + Apple Silicon, Linux x64 / arm64. SDK and REST reference is anti-detect-browser; account isolation is multi-account-isolation.
The English summary is being prepared. Showing the original description.
Drive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per identity, and a per-profile proxy whose exit IP sets timezone and WebRTC - JavaScript (npm 'anti-detect-browser') or Python (PyPI 'antibrow'). Use when sessions must stay logged in across runs and stay separate, when a scraper or agent is blocked by an incoherent headless fingerprint, when checking ads or pricing from another region, when a page must be reached as a phone rather than a desktop, when automation mints a profile per task, when running several of your own accounts from one machine, or when testing how your own bot detection scores a real device. Also for 'antibrow', 'fingerprint browser', 'multi-account browser', '防关联', '多账号', '安卓模拟', 'Android profile', 'mobile fingerprint', 'temporary profile', 'CreepJS', 'residential proxy', 'browser-use', 'crawl4ai'. MCP control is browser-mcp-agent; isolation is multi-account-isolation.
The English summary is being prepared. Showing the original description.
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
The English summary is being prepared. Showing the original description.
Own goal-first engineering outcomes: investigate, find root cause, design, plan, then delegate implementation unit-by-unit to cursor-implementation-loop, this plugin's kernel skill, with verification and honest reporting. Use to fix, build, or own an outcome end to end; investigate-and-fix; "make X work"; or plan-then-execute in one request. A request with an approved plan or equivalently precise spec that needs nothing beyond implementation belongs directly to cursor-implementation-loop. Requires this plugin's cursor-implementation-loop skill; they ship together.
The English summary is being prepared. Showing the original description.
16-phase feature orchestration workflow. Runs in the main thread as Kernel Mode. Coordinates the Lead→Developer→Reviewer→TestLead→Tester assembly line.
The English summary is being prepared. Showing the original description.
PyTorch Inductor pattern matcher 机制开发：扩展本仓 compile 能力（default/Inductor 后端）， 或扩展三方框架自带的类似能力——Pattern 创建/注册/调试、GraphPatternEntry 手动改图、 Copy 算子（InplaceCopy/ViewCopy）消减的机制与全生命周期，含 Phase 1–7 出口证据纪律。 当用户需要写/改/调试 pattern、处理融合不命中、做 Copy/InplaceCopy 消减或注册 replacement 时 使用；即使用户只说"pattern 不生效""copy 算子变多了""compile 没融合"而未说全称，也应触发 （触发词：pattern / pattern matcher / register_replacement / GraphPatternEntry / compile 融合 / Copy 消减）。 边界：批量下发（图 capture/replay）见 aclgraph-dev；算子本体开发见 operator-dev； 框架侧特性使能/补齐见 framework-integration。 由 dev-workflow 的 pattern/compile 开发场景路由触发，亦由 model-auto-optimization 的 S1 kernel 融合（接入/compile）替换场景指向（框架侧使能不支持、需新增/适配 pattern 时）。
The English summary is being prepared. Showing the original description.
多模态模型自动优化流程总入口（编排层）：把一个三方框架托管的扩散模型从环境准备到无损/有损 优化自动跑完。任务判定后按 S0 环境准备、S1 kernel 融合优化（原 S1/S2 合并）、S3 并行通信、 S4 有损优化、S5 训练感知（预留，少步蒸馏 + SLA/QAT）、闭环复验路由到能力技能（env-install / framework-integration / profiling-collect / profiling-analyze / performance-optimization / dit-parallel-opt / dummy-run 等），检查各阶段产物与验收并回填经验槽位。 当用户需要对具体模型做框架接入、无损/有损加速、并行调优或确认收益时使用本入口；即使用户只提 模型名加"优化/加速/跑通/采profile"而未说框架或阶段，也应由本入口判定路由。仓库代码开发类任务 请走 dev-workflow。流程执行/验收按 workflows/optimization-flow.md，run-state + stage_gate 门禁。
The English summary is being prepared. Showing the original description.
量化格式契约与位级对齐：从设备字节反推量化器的**编码公式、舍入模式、scale 粒度、退化块规则**， 并据此重实现/融合量化器（MXFP8 e8m0、int8 perblock、fp8 perchannel 等）， 用「同进程同数据 + 独立参考实现 + 中点与退化输入全覆盖」做到**逐字节精确**。 当自研量化 kernel 与框架算子**对不上**、需要逆向某个量化器的数值契约、需要判断 「量化残差算不算可接受」、或要在融合内核里复现 aclnn 量化语义时使用此 skill。 即使用户只说「量化结果和参考不一致」「这个 scale 怎么算出来的」「融合量化器精度对不上」 而未提"契约"，也应触发。**注意**：单纯选量化档位/配置（该不该开量化、开哪一档）走 dit-perf-opt；算子级性能调优与 DSL 选型走 operator-dev； 并行作用域导致的静默失效（DiT 侧「改了并行但不报错也没生效」的判定）走 dit-parallel-opt。
The English summary is being prepared. Showing the original description.
Detect single-nucleotide crosslink (CL) sites in CLIP-seq data using truncation patterns (iCLIP/eCLIP CITS), crosslink-induced mutations (HITS-CLIP CIMS deletions, PAR-CLIP T-to-C), or HMM/kernel-density methods (PureCLIP, PARalyzer, CTK). Use when single-nucleotide resolution is required for motif registration (mCross), allele-specific binding (BEAPR), variant-effect prediction, or comparing crosslink chemistry across CLIP variants.
The English summary is being prepared. Showing the original description.
Expert guide for Backend.AI distributed computing platform. Automatically activates when users ask about: - Backend.AI architecture, components (Manager, Agent, Storage Proxy, Webserver, App Proxy) - Features (session scheduling, Sokovan orchestrator, multi-tenancy, resource allocation) - APIs (REST, GraphQL), authentication, RBAC authorization - Container runtime (kernels, jail sandbox, hook library, virtual folders) - Accelerator support (CUDA, ROCm, TPU, NPU, Graphcore IPU) - Client SDKs (Python, Java, JavaScript, PHP) - Setup, requirements (Python 3.13+, Docker, PostgreSQL, Redis, etcd) - How WebUI connects to/interacts with Backend.AI backend - Plugin interfaces, development setup, infrastructure Use when user mentions "Backend.AI", "backend.ai", "Sokovan", component names, or asks about the backend platform this WebUI connects to. allowed-tools: WebFetch, Read
The English summary is being prepared. Showing the original description.
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.
The English summary is being prepared. Showing the original description.
Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.
The English summary is being prepared. Showing the original description.
Use for deep Symfony project analysis: kernel/bootstrap, container wiring, routing/request flow, Doctrine, security, Messenger, and Symfony-specific failure patterns.
The English summary is being prepared. Showing the original description.
Quantização de pesos consciente da ativação para compressão de LLM de 4-bit com aceleração 3x e perda mínima de acurácia. Use ao implantar modelos grandes (7B-70B) em memória GPU limitada, quando precisa de inferência mais rápida que GPTQ com melhor preservação de acurácia, ou para modelos com instruções ajustadas e multimodais. Vencedor do Prêmio Melhor Artigo MLSys 2024.
The English summary is being prepared. Showing the original description.
Compress review pressure into the right next action instead of more code by default. Classify findings, reject non-liabilities, and choose proof-only vs minimal-fix vs refactor-kernel, preventing one-patch-per-comment churn. Use after a code review — PR comments, reviewer suggestions, or audit findings — and especially when you are about to reflexively patch every comment.
The English summary is being prepared. Showing the original description.
Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.
The English summary is being prepared. Showing the original description.
Detect privilege escalation attempts including token manipulation, UAC bypass, unquoted service paths, kernel exploits, and sudo/doas abuse across Windows and Linux.
The English summary is being prepared. Showing the original description.