Browse Secure Claude Skills
Search verified agent skills and review security grades before installing · full A–Z index
- Vllm Multimodal Open Issue AnalyzerFetch and organize multimodal-related open issues from vllm-project/vllm. Categorizes issues by problem type (Bug, Feature Request, Performance, CUDA Graph, EPD disaggregation, Prefix Caching, ViT/visual encoder, Video, Audio/Speech, specific VL models, etc.) and generates a structured Markdown report saved to the skill's ./outputs directory. Use when the user wants to collect, search, analyze, or summarize open issues related to multimodal features or models in the vllm repository. Triggered...Votes: 0GitHub stars: 19
- Vllm Model TutorialGenerate comprehensive Chinese technical tutorial documents for specific vLLM models (e.g., Qwen3-VL, DeepSeek-V3, Llama 4, InternVL3, etc.). Produces deep-dive model walkthrough documents with Mermaid architecture diagrams, comparison tables, input preprocessing flows, forward pass analysis, ViT computation (for VLMs), vLLM code implementation analysis, and technical principle explanations (MoE, MLA, Gated Attention, ViT, DiT, etc.). Output is saved as Markdown to the skill's outputs/ direct...Votes: 0GitHub stars: 19
- Vllm Feature TutorialGenerate comprehensive Chinese technical tutorial documents for vLLM features and modules. Produces deep-dive code walkthrough documents with Mermaid architecture/flow diagrams, comparison tables, code snippets, and performance analysis. Output is saved as Markdown to the skill's outputs/ directory. TRIGGER when: user asks to learn about a vLLM feature, module, or subsystem (e.g., "我想了解 vllm 中的 xxx", "帮我生成 vllm xxx 的教程", "generate a tutorial for vllm's xxx feature", "vllm xxx 特性分析"). DO NOT T...Votes: 0GitHub stars: 19
- Vllm Feature DesignDesign and implement vLLM features. Given user requirements (feature description, related PRs, reference materials), produces (1) core code implementation — NO test cases — and (2) a rich Markdown design document saved to the current project root. Use when the user asks to design a vLLM feature, implement a vLLM feature, architect a component for vLLM, generate a design doc for vLLM, or requests a feature design for ML inference systems. Triggered by phrases like "帮我设计vLLM的xxx功能", "design a v...Votes: 0GitHub stars: 19
- Vllm Dev Task DiscoveryAnalyze contribution opportunities in the vllm-project/vllm repository for community developers. Given a module, feature, or model area, this skill collects information from open issues, recent PRs, GitHub discussions, code TODOs/FIXMEs, roadmap labels, and maintainer activity to generate a structured Markdown report of actionable tasks (feature development, model support, performance optimization, bug fixes, documentation, refactoring). Each task includes difficulty, prerequisite knowledge, ...Votes: 0GitHub stars: 19
- Vllm Benchmark Result AnalysisCompare vLLM serving benchmark outputs before and after a code change. Parses plain-text vLLM benchmark output (the "Serving Benchmark Result" block), computes per-metric percentage changes with improvement/regression markers, generates a Markdown report with a full metrics table and a key-changes summary, and saves it to ./outputs/. Use when the user pastes or provides vLLM benchmark output and asks to compare, summarize, or analyze performance differences between two runs (e.g., "before thi...Votes: 0GitHub stars: 19
- Infx Bench Script GeneratorGenerate three local bash scripts (docker run / server start / AgentX client replay) to run an InferenceX srt-slurm recipe YAML benchmark manually on a local GPU server, without Slurm or srt-slurm. Given a recipe like dsv4/vllm/mi355x-fp4-mtp/agentic.yaml and an override variant (e.g. override_tp8_c56 or override_dep8_c64), optionally capture one complete torch profiler prefill or decode step via vllm serve --profiler-config, with configurable host paths for model weights, the InferenceX chec...Votes: 0GitHub stars: 19
- ScroogeKO-first pentalingual (KO/EN/JA/HI/ZH) LLM output-compression mode. Cuts output tokens by answering in a compressed register while keeping full technical accuracy. Persona = token miser ("Scrooge"). One dial (full) per language. Use when the user says "/scrooge", "scrooge mode", "압축 모드", "토큰 아껴", "スクルージモード", "स्क्रूज मोड", "斯克鲁奇模式", "be terse", or asks for fewer output tokens.Votes: 0GitHub stars: 6
- Scrooge StatsShow measured Scrooge session token usage and estimated savings when available. Use when the user invokes /scrooge-stats, $scrooge-stats, asks for Scrooge token stats, or asks how many output tokens Scrooge saved.Votes: 0GitHub stars: 6
- ZeusZero-interaction full pipeline skill. 사용자가 한 줄 설명만 제공하면 설계(zephermine) → 구현(agent-team) → 감리(argos) → Docker 구성 → 테스트(minos) 전체를 자동 완료. 인터랙티브 질문 도구 절대 호출 금지. /zeus로 실행. 제우스.Votes: 0GitHub stars: 6
- ZephermineCreates a persisted, sectionized implementation artifact suite through research, stakeholder interviews, domain analysis, database and API design, and multi-LLM review. Use for feature or product plans consumed by downstream implementation and QA. Prefer lightweight native plan/interview workflows for small tasks; on Antigravity those are /plan and /grill-me. /zephermine로 실행. Also known as 젭마인, 제퍼마인, 제퍼미네.Votes: 0GitHub stars: 6
- Youtube TranscriptYouTube 영상 자막을 추출하고 요약합니다. yt-dlp 기반으로 MCP 없이 로컬에서 안정적으로 동작합니다. /youtube-transcript 또는 "이 영상 자막 가져와"로 실행.Votes: 0GitHub stars: 6
- Writing Clearly And ConciselyUse when writing prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Applies Strunk's timeless rules for clearer, stronger, more professional writing.Votes: 0GitHub stars: 6
- WranglerUse Cloudflare Wrangler CLI for Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and secrets.Votes: 0GitHub stars: 6
- Wpf Coding Standards명시적 `/wpf-coding-standards` 호출 전용 WPF 참고서. 일반 C#/XAML 작성에는 자동 적용하지 않는다.Votes: 0GitHub stars: 6
- Workpm다이달로스(Daedalus) — 설계 없이 바로 구현할 때 사용하는 5단계 PM. 리서치, 제안, 도면, 구현, 검증을 자체 진행하며 Claude, Codex, Antigravity, Grok의 내장 탐색자·작업자를 우선 사용한다. Antigravity의 일반 장기 팀 작업은 /teamwork-preview를 우선하고, 이 스킬은 5단계 장부와 산출물이 필요할 때 사용한다. /workpm 또는 /daedalus로 실행한다.Votes: 0GitHub stars: 6
- Workplace ConversationsNavigate difficult workplace conversations and deliver constructive feedback using Preparation-Delivery-Followup framework and SBI (Situation-Behavior-Impact) model. Use when preparing for tough conversations, giving feedback, managing conflicts, or handling sensitive discussions.Votes: 0GitHub stars: 6
- Web To Markdown웹페이지를 깨끗한 마크다운으로 변환. JS 렌더링 페이지 지원 (Puppeteer + Readability). 단일/배치 변환, 로그인 필요 페이지, 선택적 콘텐츠 추출. "웹 to 마크다운", "페이지 저장", "web2md" 요청에 실행. /web2md로 실행.Votes: 0GitHub stars: 6
- Web Design GuidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".Votes: 0GitHub stars: 6
- Video Maker영상 요청의 진입점. Remotion 또는 HyperFrames 중 엔진 하나를 골라 스크립트→음성(TTS)→컴포지션→자막→렌더를 코드 기반으로 설계·구현·검증한다. 제품 소개 영상, 데모 비디오, SNS 숏폼, 데이터 시각화 영상, 나레이션·자막 영상, MP4 렌더링, Remotion, HyperFrames 요청에 /video-maker로 사용한다. 전역에 설치된 HyperFrames 스킬 번들의 라우터는 진입점으로 쓰지 않는다.Votes: 0GitHub stars: 6