'kernel' 검색 결과

Review and adapt vllm_metax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs. Verify registration, inherited state, weight layouts and actual backend selection. Use for registry compatibility work, not standalone attention algorithms or monkey patches.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels. Establish quantization and cache differences, preserve upstream structure, and distinguish shared upstream bugs from adaptation defects. Use for model support work, not standalone monkey-patch or registry audits.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Audit and adapt monkey patches in vllm_metax/patch/ against a target upstream revision. Decide whether to retain, update, migrate, or remove each patch; maintain patch headers and explanations; validate changes and record evidence. Use only for compatibility work on this directory, not standalone attention backend, model, kernel, or other adaptations elsewhere in vllm_metax.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

/aegisops-ai — Autonomous Governance Orchestrator workflow skill. Use this skill when the user needs Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

/aegisops-ai — Autonomous Governance Orchestrator workflow skill. Use this skill when the user needs Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this when creating, editing, executing, or reviewing Jupyter notebooks — including cell structure, kernel management, extracting reusable logic to src/, and ensuring notebooks are restartable.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: one kernel file plus supporting files that downstream skills build from. Also updates and validates existing specs. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec"

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert guide for modern web shaders: Three Shading Language (TSL), WebGPU WGSL, Compute Shaders, and WebGL GLSL in Three.js and Babylon.js. Covers procedural generation, compute kernels, and post-processing / Panduan ahli shader web modern: TSL, WGSL, Compute Shader, dan GLSL.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Zephyr RTOS development — boards and devicetree, the build system (west, Kconfig, CMake, sysbuild), drivers and peripherals, BLE and networking, the kernel, storage, power, testing and debugging, security and OTA. Use this for ANY Zephyr RTOS or embedded-firmware task on a Zephyr project; it routes you to the right specialized skill via the zephyr-cli registry.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

GTM prospecting, enrichment, outreach, and Deepline Play work/audits. Providers: adyntel,affinity,ai_ark,akta,allegrow,amplemarket,apify,attention,attio,aviato,bettercontact,bigquery,bluesky,bounceban,brave,browserbase,builtwith,cbinsights,clay,clickhouse,cloudflare,contactout,contextdev,crunchbase,crustdata-v3,customer_db,databricks,dataforseo,datagma,dealroom,deepline_ip_to_company,deepline_native,deeplineagent,discolike,dropleads,edges,emailbison,emailguard,enformion,enigma,exa,findymail,firecrawl,fireflies,firmable,forager,fullenrich,fundable,generic_http,getleads,gong,google_ads_audiences,google_workspace,govfiles,grain,hackernews,harvestapi,heyreach,hubspot,hunter,icypeas,instantly,intercom,ipqs,kaspr,kernel,leadmagic,lemlist,limadata,linkedin_ads_audiences,luma,lusha,meta_audiences,millionverifier,nooks,notion,openmart,opensosdata,openwebninja,outreach,parallel,peopledatalabs,pitchbook,podscan,polymarket,postgres,predictleads,prospeo,quickenrich,rapidapi,redshift,rocketreach,salesforce,salesforge,….

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Windows local privilege escalation from a low-privilege shell to Administrator or SYSTEM. Covers quiet vs loud enumeration, SeImpersonate/Potato family including LocalPotato, token privileges (SeBackup/SeRestore/SeManageVolume/SeLoadDriver/SeDebug), service/DLL/COM/scheduled-task abuse, AlwaysInstallElevated and UAC boundary, KrbRelayUp-style domain-joined local admin, and version-gated kernel LPE. Use when the operator already has a Windows foothold and needs local SYSTEM. Endpoint blocks hand off to /edr-bypass then return here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Linux local privilege escalation from a low-privilege shell to root. Covers quiet vs loud enumeration, sudo/GTFOBins, CVE-2025-32463 chwoot and CVE-2025-32462 host bypass, polkit/udisks CVE-2025-6018/6019, SUID/capabilities, systemd timers/units, cron/PATH/LD_PRELOAD, dangerous groups and docker.sock, host-local container escape, and version-gated kernel LPE including Copy Fail CVE-2026-31431. Use when the operator has a Linux foothold and needs root. Kubernetes RBAC stays in /k8s. Endpoint blocks hand off to /edr-bypass then return here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Endpoint defense evasion after an operator-selected chain already has a valid execution path but AV/EDR/AMSI/WDAC/PPL/memory/kernel telemetry blocks the intended action. Originating modules include /web-attack /ad-attack /cloud-attack /k8s /cicd /service-attack /phishing /privesc-win /privesc-linux /creds /post /shell. Success is the blocked action becoming executable, then resume the originating module — not obtaining a shell here.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

为任意 Agent Skill 设计、实现、接入或精简 Verifier 与 State；当用户希望给目标 skill 配置验证器/状态机、落实已有设计，或仅规划和审查架构时使用，尤其适合需要避免过度设计、硬编码并符合 Kernel 契约的任务。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when writing, moving or auditing any .md in imp - deciding which file a paragraph belongs in, adding a doc, fixing a stale claim, or when docs_lint.py fails in CI. Covers the four reader layers (L0 README / L1 operators / L2 kernel devs / L3 agents), the HTML-comment metadata header, [PROV:] provenance, the single-source-of-truth map, generated perf blocks, which numbers may appear in prose, plan-doc closure. Triggers on "which doc does this go in", "docs lint failed", "add a doc", "this claim is stale", "update the README", "PROV block", "layer", "STALE.md". Do NOT use for the CHANGELOG or a release body (shipping-prs), or for code-comment accuracy (codebase-audit).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working on or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when verifying that a model in the imp inference engine produces coherent output without repetition loops, token-stuck states, or state corruption across turns or streams. Triggers on "degenerates", "check degeneration", "repetition loop", "own own own", "stuck token", "empty content", "multi-turn regression", "does it still work", "NIAH", and after enabling CUDA graphs / changing forward pass / MoE routing / KV cache or KV dtype / GDN state or scan / sparse attention / PDL / speculation (MTP, n-gram) / ragged prefill / batched-decode kernels (smallm, producer quantize) / FA2 softmax.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when adding support for a new model architecture to imp, porting a model family, or debugging a model that loads but produces wrong output - "add support for <model>", "new arch", loader detection, chat template, tokenizer parity, RoPE variant, "outputs garbage", "prompt-blind", "digits scrambled", "NaN logits", "describes a different picture", "does it fit in VRAM". Do NOT use for kernel performance (sm120-cuda-expert) or quant-format questions (quant-formats).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when auditing the imp codebase for structural debt, dead code, god-objects/files, duplication, flag sprawl, or deciding whether a cleanup is worth shipping - "structure audit", "tech debt", "is this still used", "dead code", "refactor for clarity", "should we split this file", "remove this flag", "file size gate red", "alloc sites gate red". Do NOT use for build/test mechanics (building-and-testing), perf/kernel work (benchmark-cuda / sm120-cuda-expert), or output quality (check-degeneration).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when imp outputs differ between two paths that should agree - chunk sizes, prefill vs decode, prefix-cache resend, two engines (imp vs llama.cpp vs HF), two builds or kernels - "output changes with chunk size", "first token differs", "logprobs moved", "which layer diverges", "who is right, imp or llama.cpp", "near-tie". Do NOT use for repetition loops or garbage output (check-degeneration), a new arch that loads wrong (add-model-arch), or perf (benchmark-cuda).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Consolidated Symfony conventions (Symfony 6.4 / 7.x): attribute routing, controllers as services, autowiring/DI, Form types, Validation constraints, Voters for authorization, the Serializer/DTO contract, and Messenger. Apply when writing or reviewing Symfony backend code. Activated automatically by symfony-plugin/stack.md as a convention skill for the development phase. Apply when: writing or reviewing Symfony controllers, services, forms, validators, voters, and serialization. Do NOT use this skill for: - PHP language idioms (strict_types, enums, readonly) — see php-foundation:php-conventions. - Doctrine queries / entities — see symfony-plugin:doctrine-patterns. - Testing — injected by the QA phase (WebTestCase/KernelTestCase) + php-foundation:php-testing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

PHPUnit and Pest patterns for any PHP project: test structure, naming, data providers, test doubles (mocks/stubs/fakes), fixtures, and coverage targets. Stack-agnostic — referenced by every PHP plugin in the marketplace. Use this skill to: - Structure unit and integration tests with PHPUnit or Pest consistently. - Drive cases with data providers / datasets instead of copy-pasted test bodies. - Use test doubles with discipline — mock collaborators, not the system under test. - Set up and tear down fixtures cleanly and aim for a meaningful coverage target. Do NOT use this skill for: - PHP language idioms — see php-foundation:php-conventions. - Composer / autoloading — see php-foundation:composer-tooling. - Framework-specific test helpers (Laravel RefreshDatabase/actingAs, Symfony WebTestCase/KernelTestCase) — those are injected by the framework plugin's QA phase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.