Agent Skills Index

Agent skills index, page 49

Browse this index of public skills, or use search to access the full library.

Open search

No.: 4,801
stitch-design-tasteSemantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
Repository: nexu-io/open-design
GitHub stars: 106,688Updated: Jun 2, 2026
No.: 4,802
google-whatsapp-prospectingFind B2B buyers' WhatsApp contacts at scale by Google-dorking product + region + WhatsApp signals, then validate, enrich, and run a compliant cold outreach sequence. Use when a foreign-trade / cross-border / DTC seller wants to build a targeted outbound list of importers, distributors, wholesalers, or end-buyers reachable on WhatsApp — without relying on paid B2B databases (Alibaba, IndiaMART, Kompass). Trigger phrases include "find WhatsApp leads", "Google reverse-lookup WhatsApp", "外贸 WhatsApp 开发客户", "Google 反查 WhatsApp", "外贸找客户公式", "海外采购商 WhatsApp", "拓客 WhatsApp 群发".
Repository: noique/cross-border-ecommerce-skills
GitHub stars: 91Updated: Jul 26, 2026
No.: 4,803
document-to-action-itemsExtract cited obligations, deadlines, tasks from documents.
Repository: NousResearch/hermes-agent
GitHub stars: 261,860Updated: Nov 3, 2026
No.: 4,804
douyin抖音内容创作全套。包括短视频文案（前3秒定生死）、竖屏格式规范、话题标签策略、严格审核规避（机审+人审）、完播率优化、五级流量池机制。建议配合 copywriting-base 使用以获取通用文案能力。触发词：抖音、Douyin、TikTok、短视频、抖音运营。
Skill content language: Chinese
Repository: npc-live/clawfirm
GitHub stars: 156Updated: Jun 14, 2026
No.: 4,805
wireframeProduce low-fidelity black-and-white UI wireframes as SVGs or viewer pages. Use when asked to wireframe, sketch a screen, draft a layout, make a low-fi mockup, or publish wireframes.
Repository: paperclipai/paperclip
GitHub stars: 112,381Updated: Jul 10, 2026
No.: 4,806
value-prop-statementsGenerate value proposition statements for marketing, sales, and onboarding from existing value propositions. Use when writing marketing copy, creating sales messaging, or crafting onboarding messages.
Repository: phuryn/pm-skills
GitHub stars: 27,783Updated: Mar 3, 2026
No.: 4,807
testUse when you need to run tests for React core. Supports source, www, stable, and experimental channels.
Repository: react/react
GitHub stars: 252,430Updated: Jan 24, 2026
No.: 4,808
project-managerProject management expert for Agile, estimation, risk management, and stakeholder communication
Repository: RightNow-AI/openfang
GitHub stars: 18,242Updated: Feb 25, 2026
No.: 4,809
music-midiExtract MIDI/score from an existing production
Repository: ruvnet/ruflo
GitHub stars: 81,304Updated: Aug 27, 2026
No.: 4,810
ruview-hardware-setupESP32-S3 / ESP32-C6 firmware build, flash, WiFi provisioning, and serial monitoring for RuView CSI sensing nodes. Use when setting up physical hardware, reflashing a node, or debugging a device that isn't streaming CSI.
Repository: ruvnet/RuView
GitHub stars: 103,115Updated: Jul 18, 2026
No.: 4,811
exhibition-layout-planner展览/展厅空间规划出图工具。当用户上传展厅平面图纸（CAD导出图、建筑平面图、毛坯/精装平面、手绘草图等）并希望生成展陈规划方案图时使用。能基于图纸生成四类专业出图：①分区规划平面图（不同功能区/展区用不同色块表示，带区域编号与名称）②参观动线图（带方向箭头的参观流线，区分主动线/次动线/疏散动线）③情绪/体验节奏曲线图（按参观顺序映射观众情绪起伏）④图例与区域内容说明图（色块图例+各区域展项点位说明）。只要用户提到"展厅平面图""展陈规划""分区图""参观动线""观展动线""布展方案""展区划分""色块分区""展览规划图"或上传了任何展馆/展厅/博物馆/展览空间的平面图纸并想要规划方案，就应使用本skill，即使用户没有明确说"出规划图"三个字。输出为可缩放、清晰、便于截图的HTML网页图。
Skill content language: Chinese
Repository: Siri2026-design/exhibition-layout-planner
GitHub stars: 1Updated: Jun 1, 2026
No.: 4,812
java-coding-standardsJava/Spring Boot 编码规范：用于编写、审查、重构和讲解 Java 代码。适用于 Java 风格、Spring Boot 架构、Controller/Service/Manager/DAO 分层、API 边界、Entity/VO/Form/DTO/BO 设计、MyBatis/MyBatis-Plus 持久化、事务、异常、日志、安全、性能、测试和 Java 代码评审等场景。默认结合 Google Java Style 与 Spring Boot 最佳实践，同时允许仓库内的 AGENTS.md、CLAUDE.md、Checkstyle、Spotless 以及相邻代码风格覆盖这些通用规则。
Skill content language: Chinese
Repository: Snailclimb/AIGuide
GitHub stars: 714Updated: Jul 2, 2026
No.: 4,813
space-video-script视频口播脚本撰写，两大特色——(1) 去 AI 味，把书面/AI 腔改成能念出口的真人口语；(2) 把模糊想法逼成一份精确到秒的分镜脚本（每个镜头讲什么、怎么呈现、停多久、怎么切）。当用户说「写口播脚本」「这段太 AI 了改成人话」「口播稿」「分镜脚本」「精确到秒」「script」「改成能念的」时触发。输入可以是选题正文、一段草稿，或一句模糊描述。
Skill content language: Chinese
Repository: SpaceZephyr/creator-buddy
GitHub stars: 1,857Updated: Aug 4, 2026
No.: 4,814
biological-oceanographerExpert-thinking profile for Biological Oceanographer (sea-going / plankton ecology / production & export rates / omics + microscopy / fisheries oceanography): Reasons from light-nutrient-grazing coupling, the microbial loop, and size-structured export through CTD/MOCNESS sampling, 14C and O2/Ar production with 234Th export flux, imaging and flow cytometry enumeration, and SILVA/PR2 metabarcoding while treating spatial patchiness, diel-migration tow aliasing, CDOM-biased...
Repository: stanfish06/skillquarium
GitHub stars: 12Updated: Aug 10, 2026
No.: 4,815
py-guiBuild and review cross-platform Python desktop applications with tkinter, ttk, CustomTkinter, PySide6, or PyQt6. Use for windows, widgets, layouts, dialogs, system tray, background jobs, event loops, model-view separation, accessibility, high-DPI behavior, settings, packaging with PyInstaller or Nuitka, and fixing unsafe worker-thread UI updates.
Skill content language: Chinese
Repository: stevenke1981/python_skills
GitHub stars: 1Updated: Jul 30, 2026
No.: 4,816
personal-trainer-master健身私教 — 为客户设计、指导和推进个性化训练方案的专业工艺, 有别于团课教练、物理治疗师或运动队教练: (a) 训练方案设计与周期化 (线性 / 波动 / 板块周期化 Bompa & Haff; NSCA《力量训练与体能训练精要》行业圣经; Schoenfeld 肌肥大机制; Helms/Valdez/Morgan 肌肉与力量金字塔; 共轭训练法 Simmons/Westside; Starting Strength 线性渐进 Rippetoe; Renaissance Periodization 训练量地标 Israetel); (b) 动作评估与筛查 (FMS 功能性动作筛查 Gray Cook; NASM CEx 纠正性训练连续体抑制-拉伸-激活-整合; 关节逐级方法 Cook/Boyle; 姿势与代偿模式识别; PAR-Q+ 与 ACSM 运动前筛查指南); (c) 教学与指令 (外部 vs 内部注意焦点 Wulf; 差异化学习 Schöllhorn; 约束导向方法 Davids/Renshaw; RIR/RPE 自动调节 Zourdos/Helms; 动机访谈在健身中的应用 Rollnick/Miller); (d) 营养指导的执业边界 (宏量营养素周期化; Precision Nutrition / ISSN 立场声明的循证建议; 边界: 私教提供一般性指导, 医学营养治疗需 RD/RDN 资质; 能量可用性与 RED-S Mountjoy IOC 共识); (e) 商业与客户管理 (客户留存与方案依从; 咨询与销售伦理; 线上教练平台与规模化 Goodman PTDC; 方案交付工具 TrueCoach/Trainerize/TrainHeroic; 课时定价模型; 独立教练 vs 健身房雇员); (f) 专项方向 (运动表现 CSCS; 纠正性训练 CES; 老年健身 SFN; 产前产后; 青少年 YSCA; 适应性 / 无障碍健身; 健美 / 形体; 力量举; 耐力运动 S&C)。诚实处理: 兄弟科学 vs 循证之争, 补剂行业利益冲突, 合成代谢激素使用现状 (诚实但不推广: 匿名调查约 30% 有经验男性健身者使用过 — 业内估, Kanayama/Pope/Hudson 记录健康风险, WADA 禁用清单用于竞技语境), 体型焦虑与进食障碍风险 (男性私教肌肉变形症, 正食症倾向, N
Skill content language: Mixed languages
Repository: swaylq/master-skill
GitHub stars: 174Updated: May 24, 2026
No.: 4,817
embedded-firmware-from-hardwareBuild and review maintainable embedded MCU firmware from schematic, PCB, netlist, pin-map, BOM, Keil/C51/MDK projects, vendor demo code, or hardware debug evidence. Use when Codex must convert hardware design knowledge into firmware architecture, BSP/HAL code, pin configuration, peripheral drivers, board diagnostics, touch-key/keypad/display/buzzer/WiFi bring-up, or investigate why firmware does not match schematic/PCB behavior.
Repository: Tansuo2021/ADtoKeil
GitHub stars: 193Updated: Jun 7, 2026
No.: 4,818
mem-searchSmart search (default). Search claude-mem's persistent cross-session memory database in three steps: search, timeline, then selected get_observations. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
Repository: thedotmack/claude-mem
GitHub stars: 114,994Updated: Oct 20, 2026
No.: 4,819
02-premeditated-murderผู้กระทำวางแผนฆ่าล่วงหน้าก่อนลงมือ เช่น เตรียมอาวุธไว้ล่วงหน้า ดักรอหรือนัดพบเหยื่อ มีมูลเหตุโกรธเคืองสะสมมานาน เคยข่มขู่หรือแสดงเจตนาว่าจะกำจัด เลือกเวลาและสถานที่เอื้อต่อผู้กระทำ กระทำอย่างมีระบบและรุนแรง หลบหนีอย่างมีแผน ทำลายหลักฐาน บาดแผลสอดคล้องกับการโจมตีที่มุ่งหวังผล ทั้งหมดนี้บ่งชี้ว่ามีการตัดสินใจก่อนกระทำ ไม่ใช่การกระทำชั่วแล่นหรือบันดาลโทสะ
Skill content language: Thai
Repository: ThomasMoreAI/legal-skills-open
GitHub stars: 78Updated: Jun 1, 2026
No.: 4,820
pr-walkthroughCreate a narrated video walkthrough of a pull request with code slides and audio narration. Use when asked to create a PR walkthrough, PR video, or walkthrough video.
Repository: tldraw/tldraw
GitHub stars: 51,429Updated: Sep 24, 2026
No.: 4,821
nature-proposal-writerBuild a research proposal before drafting a paper for RL, MARL, LLM, and LLM Agent projects. Use for topic selection, hypothesis design, contribution sharpening, experiment planning, thesis chapters, grant-style proposals, and SCI paper planning.
Repository: vcis-wangchenxu/agent_nature-skills
GitHub stars: 4Updated: Jul 1, 2026
No.: 4,822
arisUse ARIS, the Auto Research in Sleep skill-based research harness, for setup, workflow routing, reviewer backend integration, state recovery, experiment operations, and repository maintenance.
Repository: VectorSpaceLab/AREX-Skill
GitHub stars: 12Updated: Aug 26, 2026
No.: 4,823
cpi-iflow-developmentSAP CPI iFlow development — integration flow design, Groovy scripting, XSLT/Message mappings, content modifier, router, ZIP packaging, deploy via MCP. Use when creating CPI iFlows, writing Groovy scripts for CPI, packaging iFlows as ZIP, deploying to SAP CPI tenant, or debugging CPI message processing failures.
Repository: williamcorrea23/sap-router-skill
GitHub stars: 2Updated: Oct 3, 2026
No.: 4,824
fabric-apparel-patternmakerUse when a task needs the judgment of a Fabric/Apparel Patternmaker — deriving grade rule increments from a size chart's actual (possibly non-uniform) measurement differences rather than applying one uniform rule across the whole range, preserving ease allowance proportion at graded extreme sizes, moving internal pattern details proportionally with their body point during grading, or deciding whether a new pattern needs fit-test sampling at range extremes.
Repository: wonsukchoi/domain-experts
GitHub stars: 24Updated: Jul 10, 2026
No.: 4,825
ielts-reading雅思阅读精读教练。同义替换提取 + T/F/NG 逻辑拆解 + 段落结构分析 + 错题诊断。触发方式：/ielts-reading、「分析阅读」「这道为什么错」「同义替换」「阅读训练」
Skill content language: Chinese
Repository: YANZHANLIN/ielts-claude-skills
GitHub stars: 331Updated: Apr 27, 2026
No.: 4,826
nano-banana-pro-prompts-recommend-skillRecommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts also work with Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E, Flux, Stable Diffusion, and any text-to-image AI model. Use this skill when users want to: - Generate images with AI (any model — Nano Banana Pro, Gemini, GPT Image, Seedream, etc.) - Find proven AI image generation prompts and prompt templates - Get prompt recommendations for specific use cases (portraits, products, social media, posters, etc.) - Create illustrations for articles, videos, podcasts, or marketing content - Browse a curated prompt library with sample images - Translate and understand prompt techniques Also available: "ai-image-prompts" skill — a model-agnostic version of this library for universal image generation.
Repository: YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill
GitHub stars: 1,900Updated: Nov 8, 2026
No.: 4,827
chuanzhang-fenjing-biaoqing将中文剧本同时加工为影视分镜、人物情绪表演和 Seedance 视频提示词或中文 HTML 分镜网页。Use when the user asks for 分镜、镜头表、视频提示词、Seedance提示词、分镜网页、人物表情、微表演、情绪弧线，或要求把 chuanzhang-fenjing 与 chuanzhangbiaoqing 合并使用。保留分镜六道确认，并在每个镜头的“动作”之后、“音效”之前固定输出完整“表情”字段，使最终交付直接成为分镜 + 情绪一体稿。
Skill content language: Chinese
Repository: zhangxiansheng-888/chuanzhangAIshijie
GitHub stars: 72Updated: Jul 27, 2026
No.: 4,828
spritesheet从视频中提取帧生成 spritesheet 和独立透明 PNG。当用户说"制作 spritesheet"、"视频转精灵图"、"提取动画帧"、"sprite sheet"、"循环动画"时使用。
Skill content language: Chinese
Repository: zrong/skills
GitHub stars: 13Updated: Jun 16, 2026
No.: 4,829
zinxtickBeginner-friendly generic sticker and meme-pack production workflow for AI agents. Use when turning a user-provided character, animal, mascot, product, food, drink, can, object, logo-like subject, or original visual concept into a cohesive platform-ready static or animated sticker/expression pack, including built-in style preset selection, theme preset selection or custom prompt handling, item planning, image-generation prompting, contact sheets, transparent cutouts, platform export assets, and visual QA.
Repository: zxzin/zinxtick
GitHub stars: 25Updated: May 31, 2026
No.: 4,830
she-love-meAcquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics and risk signals, and generating a structured Chinese HTML report. Use when the user asks to export, import, or analyze WeChat/QQ chats or requests relationship analysis from message history.
Skill content language: Chinese
Repository: 863401402/she-love-me
GitHub stars: 991Updated: Aug 13, 2026
No.: 4,831
corrosion-materials-selectorMaterials selection skill for corrosion resistance based on process conditions and industry standards
Repository: a5c-ai/babysitter
GitHub stars: 1,891Updated: Jun 1, 2026
No.: 4,832
cnc-programmingExpert skill for CNC programming and toolpath optimization using CAM software
Repository: a5c-ai/babysitter
GitHub stars: 1,891Updated: Jun 1, 2026
No.: 4,833
generative-media-promptingThe shared brief-to-prompt convention behind the media point tasks — parse the brief, select the model or tool, construct the prompt, then QA the output against the brief. Use when prompting for image, video, speech, or music generation or editing.
Repository: a5c-ai/babysitter
GitHub stars: 1,891Updated: Aug 3, 2026
No.: 4,834
unified-memoryShare durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
Repository: affaan-m/ECC
GitHub stars: 299,529Updated: Sep 12, 2026
No.: 4,835
customer-billing-opsStripeなどの接続された請求ツールを使用して、サブスクリプション、返金、チャーントリアージ、請求ポータルの回復、プラン分析などの顧客請求ワークフローを操作します。顧客を助けたい、サブスクリプション状態を検査したい、または収益に影響する請求操作を管理したい場合に使用します。
Skill content language: Japanese
Repository: affaan-m/ECC
GitHub stars: 299,529Updated: May 17, 2026
No.: 4,836
hookify-rules自動フック実装、イベントドリブン実行、およびルール駆動ワークフロー。
Repository: affaan-m/ECC
GitHub stars: 299,529Updated: May 17, 2026
No.: 4,837
autonomous-loopsPatterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Repository: affaan-m/ECC
GitHub stars: 299,529Updated: Jun 7, 2026
No.: 4,838
medical-research-literature-reader-proA medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental backgrounds. Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper — whether they provide a PDF, abstract, DOI, PMID, or just a title. Triggers include requests like \"analyze this paper\", \"critique this study\", \"is this a strong paper?\", \"give me similar studies\", \"prepare me for journal club\", \"help me understand this bioinformatics paper\", \"what are the weaknesses here?\", or \"turn this into a mind map\". Also activate for any downstream deliverables such as journal club kits, comparison tables, PI decision briefs, replication starters, or follow-up experiment designs. Do NOT treat as a generic summarizer — this skill performs structured evidence-type classification, track-specific critical appraisal, interpretation-boundary judgment, and research-grade follow-up generation.
Repository: aipoch/medical-research-skills
GitHub stars: 2,032Updated: May 18, 2026
No.: 4,839
three-body-video-creator影片与视频编辑和内容创作者必备！当需要制作《三体》主题视频时，自动化完成选题策划、视觉设计、音频生成到成片合成，多智能体协作流程，3小时搞定72小时工作量。
Skill content language: Chinese
Repository: anbeime/skill
GitHub stars: 9,320Updated: Aug 26, 2026
No.: 4,840
antd-component-lookupLook up Ant Design React component documentation, props, and usage examples. Use when working with Ant Design (antd) components and needing API details, default values, or usage patterns.
Repository: ant-design/ant-design
GitHub stars: 100,119Updated: May 13, 2026
No.: 4,841
director-staging多角色调度方法论——3 人以上同框的站位设计/视线网络/注意力引导/前后景分层/AI 生成中的多角色一致性控制；Nomi 写多人 shot 的 prompt（谁站哪/朝向/视线/谁是焦点）时参考，走应用内 Seedance/可灵生成。
Skill content language: Chinese
Repository: aqm857886159/Nomi
GitHub stars: 620Updated: Sep 9, 2026
No.: 4,842
generate-assets统一资产生成 skill：接受 `--type=character|scene|prop|product`，或不传自动扫所有 pending（缺 sheet）资源并按类型分发。当用户说“生成角色图”/“生成场景图”/“生成道具图”/“生成商品图”、想为新资产创建参考图、或有资产缺少 *_sheet 时使用。
Skill content language: Chinese
Repository: ArcReel/ArcReel
GitHub stars: 6,341Updated: Oct 26, 2026
No.: 4,843
maps-geographyAccurate maps from real geo data — use for any map, or whenever geography would make a good graphic for a deliverable
Repository: asgeirtj/system_prompts_leaks
GitHub stars: 71,048Updated: Aug 19, 2026
No.: 4,844
meteorology-driver-classificationClassify environmental and meteorological variables into driver categories for attribution analysis. Use when you need to group multiple variables into meaningful factor categories.
Repository: benchflow-ai/skillsbench
GitHub stars: 1,906Updated: Jan 23, 2026
No.: 4,845
ebay-sold-listings-searcheBay sold-listings scraper across 8 marketplaces (ebay.com/.co.uk/.de/.fr/.it/.es/.ca/.com.au). Takes keyword plus filters (category, price range, item condition, item location, sort order, completed toggle) and returns paginated real-sale records with itemId, url, title, condition, conditionId, endedAt, soldPrice, soldCurrency, listingType (best_offer_accepted / buy_it_now / auction), isBestOfferAccepted, buyingFormat, bidCount, shipping, totalPrice, thumbnails, seller info, sellerType. Use when user mentions ebay sold, ebay sold listings, ebay sold prices, ebay completed listings, ebay comps, ebay resale prices, ebay auction sold results, ebay best offer accepted, scrape ebay sold, ebay market research, ebay pricing intelligence, ebay flipping research, real sold prices ebay, get sold prices from ebay. Also applies to price benchmarking, sold-price analytics, resale valuation, cross-marketplace price arbitrage, appraisal for collectibles, brand demand tracking on ebay.
Repository: browser-act/skills
GitHub stars: 6,339Updated: Jul 20, 2026
No.: 4,846
stata-runRun arbitrary Stata code or a .do file and display the result.
Repository: brycewang-stanford/Auto-Empirical-Research-Skills
GitHub stars: 4,955Updated: Jun 4, 2026
No.: 4,847
code-reviewReviews code changes for bugs, security issues, and quality problems. Use for a single-pass review of a PR, branch, or local diff; for large PRs that span several subsystems, use deep-review (`.agents/skills/deep-review/`).
Repository: coder/coder
GitHub stars: 17,332Updated: Sep 26, 2026
No.: 4,848
agent-evalBenchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo.
Repository: colbymchenry/codegraph
GitHub stars: 77,134Updated: Aug 5, 2026
No.: 4,849
video-downloaderDownloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Repository: davila7/claude-code-templates
GitHub stars: 33,223Updated: Dec 5, 2025
No.: 4,850
ponytail-helpQuick reference for ponytail levels, skills and commands. One-shot display. Use for /ponytail-help, "ponytail help", "how do I use ponytail".
Repository: DietrichGebert/ponytail
GitHub stars: 187,001Updated: Oct 16, 2026
No.: 4,851
xiaohongshu-writer小红书笔记写作助手 - 标题优化、emoji策略、话题标签、封面文案、笔记结构
Skill content language: Chinese
Repository: dongsheng123132/u-claw
GitHub stars: 1,760Updated: Mar 12, 2026
No.: 4,852
humanizeAI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로 실행하고 `--strict`면 heavy 고정. 트리거 — "/humanize".
Skill content language: Korean
Repository: epoko77-ai/im-not-ai
GitHub stars: 6,467Updated: Sep 1, 2026
No.: 4,853
code-security-reviewScans source code for security vulnerabilities — injection flaws, authentication bypasses, hardcoded secrets, XSS, and more — then filters false positives and ranks findings by severity and confidence. Supports all programming languages. Uses a three-phase audit-filter-report workflow with customizable scan categories and filtering rules. Use when the user asks for a security review, vulnerability scan, security audit, code security check, or wants to find security bugs in their code.
Repository: ez-lbz/claude-code-security-skills
GitHub stars: 23Updated: Apr 16, 2026
No.: 4,854
actuarial-analysisGuide actuarial analysis for insurance pricing. TRIGGERS - Use when user needs help with actuarial-analysis related tasks.
Repository: FDU-INS/Insurance-Skills
GitHub stars: 82Updated: May 18, 2026
No.: 4,855
prd-writer撰写产品需求文档(PRD)并生成可交互原型。触发条件：用户提到"需求文档"、"PRD"、"产品需求"、"写需求"、"原型"、"feature list"等关键词。集成 UI-UX-Pro-Max 设计系统，支持 Cloudflare Pages 部署。
Skill content language: Chinese
Repository: FinStep-AI/prd-writer-skill
GitHub stars: 94Updated: Mar 4, 2026
No.: 4,856
java-architectUse when building, configuring, or debugging enterprise Java applications with Spring Boot 3.x, microservices, or reactive programming. Invoke to implement WebFlux endpoints, optimize JPA queries and database performance, configure Spring Security with OAuth2/JWT, or resolve authentication issues and async processing challenges in cloud-native Spring applications.
Repository: Jeffallan/claude-skills
GitHub stars: 12,279Updated: Oct 15, 2026
No.: 4,857
wealth-structure当用户问「怎么赚钱/如何致富/该不该要期权/如何判断一个生意的结构」时调用。核心理念: 财富=睡觉时仍在赚钱的资产; 靠「责任(押上声誉)→产权(股权/知识产权)→杠杆(无需许可的代码媒体)→避免出局」构建, 无法靠出租时间致富。不适用于: 具体投资标的分析、理财产品的选股建议。 Triggers: 致富/赚钱/股权/期权/杠杆/被动收入/ownership/leverage/equity
Skill content language: Chinese
Repository: kangarooking/cangjie-skill
GitHub stars: 12,390Updated: Aug 30, 2026
No.: 4,858
act-combat-design二次元 / 动作游戏(ACT)战斗设计专家方法论 + 行业知识库。用户说"设计 XXX 角色"/"做 XXX 战斗设计"/"配 XXX 角色玩法"/"设计 XXX boss"/"设计 XXX 怪物"/"战斗策划专家"时触发。产出可给策划 / 美术审阅的战斗设计文档(markdown 或 HTML)，覆盖玩家角色与怪物 Boss。本方法论**不预设任何具体战斗体系**——招式集 / 分类轴 / 视觉预警 / 受击状态 / 配队 / 养成等由你的项目自己定义(见 conventions/TEMPLATE.md)；内置角色原型库、Boss 范式库、46 条元规则、跨游戏借鉴库(70+ 游戏)、打击感 / 数值 / Boss AI 工程基线。Anime/action-game combat design expert: methodology + industry knowledge base, project-agnostic.
Skill content language: Mixed languages
Repository: koisama0411/act-combat-design
GitHub stars: 92Updated: Jul 14, 2026
No.: 4,859
stm32STM32 系列单片机开发入口 skill。自动索引子 skill 完成环境部署、项目初始化、调试排错全流程。当用户进行 STM32 开发时调用。
Skill content language: Chinese
Repository: kukucaiCndy/embedded_ai_skills
GitHub stars: 60Updated: Jul 15, 2026
No.: 4,860
ppt-skill触发关键词：演示、PPT、幻灯片、slides、presentation、keynote、deck、汇报、展示; 使用场景：用户需要生成演示文稿、汇报材料或教学幻灯片。
Skill content language: Chinese
Repository: LeoYeAI/openclaw-master-skills
GitHub stars: 2,169Updated: May 5, 2026
No.: 4,861
character-possession将已蒸馏的角色人格档案"夺舍"为第一人称写作引擎。输入角色人格档案 + 场景设定，输出该角色在此场景中的第一人称叙述——感受、反应、内心独白。改编自 Marvis 夺舍.skill 概念，确保 POV 改写时角色声音不串线。
Skill content language: Chinese
Repository: liuxiaopeng1981/hermes-writing-skills
GitHub stars: 2Updated: Jun 8, 2026
No.: 4,862
shuorenhua检查和清理中英文文本里的 AI 套路，适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求；按场景控制力度，同时保留事实、术语、语域和责任主体。
Skill content language: Chinese
Repository: lornshrimp/Lorn.NovelWriteSkills
GitHub stars: 249Updated: Jul 12, 2026
No.: 4,863
image-to-3d-studio单图→3D场景→多风格渲染的全流程部署+创作引擎。覆盖 image-blaster 一键安装部署、World Labs 3D场景生成、fal/Hunyuan 单体模型提取、 Blender 精细调整与多风格渲染（纯3D、写实2D、三渲二赛璐珞/吉卜力/概念艺术/电影感）、以及 AI 视频控制信号输出（深度图/法线图/mask/参考帧/相机轨迹）的完整闭环。支持通过 Codex/Claude 远程手机一键部署和操控。强制触发词：image-blaster、World Labs、3D场景生成、单图转3D、图片转3D、三渲二、3D转2D、cel-shading、赛璐珞渲染、吉卜力风格渲染、toon shader、 NPR渲染、非真实感渲染、Blender渲染风格、场景一致性、AI视频片场、 3D场景部署、一键部署3D、Codex部署、远程建模、手机遥控建模、深度图导出、法线图导出、参考帧生成、相机轨迹、 glb、spz、obj、3D资产、场景重建、全景图生成、 fal.ai、Hunyuan 3D、腾讯混元3D、ElevenLabs音效、 "帮我把这张图变成3D""一键跑image-blaster""部署3D场景工具" "渲染成动画风格""三渲二怎么做""Blender里怎么出赛璐珞" "帮我装image-blaster""帮我配环境""生成深度图""导出法线图" 当用户想从一张图片生成可控3D场景时务必触发。当用户提到部署或安装 image-blaster、配置 API Key 时务必触发。当用户想在 Blender 里做三渲二（任何风格）渲染时务必触发。当用户需要为 AI 视频生成控制信号（深度图/法线图/mask/参考帧）时务必触发。当用户说"帮我远程跑一下""用手机操控""Codex跑这个"时也应触发。即使用户只是说"这张图能不能变成3D"或"怎么保持AI视频场景一致"也应触发。
Skill content language: Chinese
Repository: lujiaheng-artpivot/image-to-3d-studio
GitHub stars: 7Updated: May 17, 2026
No.: 4,864
cinematic-scroll-storytellingCreate cinematic scroll-driven landing pages with Lenis smooth scrolling, GSAP ScrollTrigger, scroll-linked progression, staggered text reveals, sticky card stacks, parallax backgrounds, scroll-scrubbed transitions, footer reveals, and immersive preloaders. Use when analyzing or building premium editorial scroll experiences, sticky project stacks, kinetic typography, or section-by-section storytelling.
Repository: MengTo/Skills
GitHub stars: 7,330Updated: Jul 18, 2026
No.: 4,865
n8n-spec-driven-developmentKeeps implementation and specs in sync. Use when working on a feature that has a spec in .agents/specs/, when the user says /spec, or when starting implementation of a documented feature. Also use when the user asks to verify implementation against a spec or update a spec after changes.
Repository: n8n-io/n8n
GitHub stars: 209,572Updated: Jun 16, 2026
No.: 4,866
inkos-translation长文任意语言互译、术语一致性、分段续跑与章节审校方法。Used by InkOS translation workers.
Repository: Narcooo/inkos
GitHub stars: 11,064Updated: Sep 25, 2026
No.: 4,867
amazon-review-analyzerDeep Amazon review analysis for competitive intelligence and product improvement. Extract sentiment patterns, recurring complaints, feature requests, and competitive insights from customer feedback. Turn reviews into actionable product development and marketing strategies. Use when the user asks about review analysis, customer feedback, product complaints, sentiment analysis, or what customers think about products.
Repository: nexscope-ai/Amazon-Skills
GitHub stars: 820Updated: Jun 5, 2026
No.: 4,868
modular-film-prompt-bibleUse for high-control film and video prompting that must combine a stable world bible, reference placeholders, real-photography fidelity, sound policy, genre fusion, and shot-level execution into one reusable creative template.
Repository: nolanx-ai/nolanx.ai
GitHub stars: 2,028Updated: May 15, 2026
No.: 4,869
release-openclaw-macRun or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.
Repository: openclaw/openclaw
GitHub stars: 394,204Updated: Jul 23, 2026
No.: 4,870
sn-md-to-html-report将 Markdown 报告、研究笔记、行业分析、战略备忘录、技术白皮书、复盘、周报等长文档，重组并创作为有编辑判断、网页美感和证据秩序的自包含 HTML 专题页。用户要求“转成 HTML”“网页化报告”“美化报告”“做成专题页”“便于分享”“提升可读性/设计感”“把报告做成网页”时使用。必须先写 plan.md 再写 HTML，保留原文事实断言和结论强度，不套模板，不做机械 Markdown 转换。
Skill content language: Chinese
Repository: OpenSenseNova/SenseNova-Skills
GitHub stars: 6,054Updated: Jun 30, 2026
No.: 4,871
game-object-componentsUse this skill when working with Phaser 4 game object components and the mixin system. Covers Transform, Alpha, Tint, Origin, Depth, Flip, Mask, GetBounds, Lighting, and other shared component behaviors. Triggers on: component, mixin, transform, mask, bounds, lighting.
Repository: phaserjs/phaser
GitHub stars: 40,673Updated: Apr 10, 2026
No.: 4,872
ideal-customer-profileIdentify the Ideal Customer Profile (ICP) from research data with demographics, behaviors, JTBD, and needs. Use when defining your ICP, analyzing PMF survey data, or understanding who your best customers are.
Repository: phuryn/pm-skills
GitHub stars: 27,783Updated: Mar 3, 2026
No.: 4,873
pixijs-mathUse this skill when working with coordinates, vectors, matrices, shapes, hit testing, or layout rectangles in PixiJS v8. Covers Point/ObservablePoint, Matrix (2D affine, decompose (including mirrored/negative-scale matrices), apply, applyInverse), shapes (Rectangle, Circle, Ellipse, Polygon, RoundedRectangle, Triangle), Rectangle layout helpers (pad, fit, enlarge, ceil, scale, getBounds), strokeContains hit tests, Polygon isClockwise/containsPolygon, toGlobal/toLocal, PointData/PointLike/Size types, DEG_TO_RAD, and pixi.js/math-extras vector and intersection helpers. Triggers on: Point, ObservablePoint, Matrix, Rectangle, Circle, Polygon, Triangle, RoundedRectangle, toGlobal, toLocal, hitArea, strokeContains, pad, fit, enlarge, ceil, getBounds, containsRect, intersects, isClockwise, math-extras, lineIntersection, segmentIntersection, DEG_TO_RAD, PointData, decompose, mirror, flip, negative scale, setFromMatrix.
Repository: pixijs/pixijs
GitHub stars: 48,655Updated: Sep 16, 2026
No.: 4,874
github-project-managementComprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Repository: ruvnet/ruflo
GitHub stars: 81,304Updated: Oct 28, 2026
No.: 4,875
juristeDroit français des affaires et de la vie courante — statuts et objet social, contrats de prestation et CGV, clients étrangers et loi applicable, propriété intellectuelle et propriété du code, activités réglementées et agréments, droit de la consommation, RGPD, mise en demeure, injonction de payer, référé et procédure. Utilisez ce skill dès qu'une question touche à un contrat, un engagement, une clause, un litige, un statut, une obligation légale ou un risque juridique — même si l'utilisateur ne dit jamais le mot « juridique », et notamment quand il s'apprête à signer, publier ou lancer une activité. Le bon moment pour poser une question juridique est avant, et c'est presque toujours à ce moment-là qu'on ne la pose pas. Also use this skill for any question about French business or civil law asked in English or any other language — company formation and articles of association, service agreements and terms of sale, freelance contracts, regulated or licensed activities, GDPR, intellectual property and code owner
Skill content language: French
Repository: Sjrazaviebra/le-cabinet
GitHub stars: 3Updated: Aug 18, 2026
No.: 4,876
deck-studioPPT 生产 Agent：理解场景 → 推荐风格 → 先出大纲 → 定义页面 → 双通路交付（PPT 内容稿 / 逐页视觉图 / 信息图组图）。当用户要做汇报、路演、培训课件、提案、咨询报告的演示文稿，或要把大纲/文章做成 slides、deck、PPT、信息图、小红书图文、可视化传播图时使用。支持指定风格或从风格库推荐，支持 image 模型逐页出视觉稿。前身为 notion-infographic（v2）并吸收 ppt-designer 的设计原则。不用于：pptx 文件的纯技术操作（拆分/合并/提取，用宿主 pptx skill）、演讲稿或文章本体的写作（用 wechat-article-writer）、需要先做研究的内容调研（先走 deep-research 再回来）、单张海报或 logo 设计。
Skill content language: Chinese
Repository: staruhub/ClaudeSkills
GitHub stars: 731Updated: Jul 30, 2026
No.: 4,877
poker-strategy-master德州扑克策略 (德州扑克策略 (Texas Hold'em) — solver/GTO 时代的无限注德州扑克竞技打法，牌手/职业视角。覆盖: (a) 理论两极 — GTO 博弈论均衡 (不可剥削的基线策略) vs Exploitative 剥削打法 (针对对手漏洞偏离均衡最大化 EV)，以及二者的实战取舍; (b) solver 时代工作流 — PioSOLVER/GTO Wizard 跑解、范围构建、节点锁定 (node-locking) 做剥削、用 HUD+数据库 (Hold'em Manager/PokerTracker/Hand2Note) 复盘找漏洞 (leak finding); (c) 牌型分层 — 现金局 (cash game) vs 锦标赛 (MTT) 的根本差异，后者叠加 ICM (独立筹码模型) 与跳台/泡沫期博弈; (d) 核心概念栈 — 范围 (range)/权益 (equity)/EV/位置 (position)/翻前开池与 3-bet/4-bet/翻后下注理论 (c-bet、极化 vs 浓缩范围、MDF 最小防守频率、阻断牌 blockers、超池下注 overbet)、SPR、底池赔率; (e) 元层 — 资金管理 (bankroll management)、桌位选择 (table selection)、方差与心态 (mental game/tilt 控制)、抽水 (rake) 与场次选择对长期赢率 (winrate, bb/100) 的影响; (f) 智识演进 — 从 Sklansky 古典手牌价值 → Janda/Tipton 博弈论 → solver 普及 → GTO Wizard 民主化求解 → AI 超人 (Libratus/Pluribus) 对人类策略的反哺。学派分歧: GTO 派 vs 剥削派、现金局 vs 锦标赛、理论自上而下 vs 牌局自下而上、solver 纯学院派 vs 实战感觉派。不含: 线下牌场运营/发牌荷官、博彩合规与赌场管理、扑克之外的牌类 (桥牌/斗地主)、纯概率赌博 (老虎机/轮盘)。) Master OS — automated mastery of 德州扑克策略 (Texas Hold'em) — solver/GTO 时代的无限注德州扑克竞技打法，牌手/职业视角。覆盖: (a) 理论两极 — GTO 博弈论均衡 (不可剥削的基线策略) vs
Skill content language: Chinese
Repository: swaylq/master-skill
GitHub stars: 174Updated: Jun 5, 2026
No.: 4,878
hdf5-pde-data-loadingPatterns for loading PDE simulation datasets (PDEBench, PhiFlow, JAX-CFD) from HDF5 files. Handles layout detection (single tensor vs separate variables), spatial/temporal downsampling, multi-variable systems, HuggingFace and DaRUS data sources, and efficient PyTorch DataLoader creation. Use when preparing PDE data for neural operator training.
Repository: synthetic-sciences/openscience
GitHub stars: 4,358Updated: Jul 4, 2026
No.: 4,879
proof-checkerRigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
Repository: wanshuiyin/Auto-claude-code-research-in-sleep
GitHub stars: 18,891Updated: Oct 24, 2026
No.: 4,880
k8s-security-policiesImplement Kubernetes security policies including NetworkPolicy, PodSecurityPolicy, and RBAC for production-grade security. Use when securing Kubernetes clusters, implementing network isolation, or enforcing pod security standards.
Repository: wshobson/agents
GitHub stars: 42,334Updated: Mar 7, 2026
No.: 4,881
pptx-quality-gatesUse when validating or repairing an editable PPTX deck for geometry, accessibility, native editability, source lineage, and OOXML package integrity.
Repository: wshobson/agents
GitHub stars: 42,334Updated: Jul 18, 2026
No.: 4,882
seedance2即梦 Seedance 视频创意工作台。用户发图+文案时自主完成看图分析→文案扩写→运镜匹配→质量验证→API生成。触发词：即梦、Seedance、seedance、视频生成、视频提示词、AI视频、运镜、短剧、广告视频、视频延长、图生视频。
Skill content language: Chinese
Repository: zhanghaonan777/Seedance2-skill
GitHub stars: 137Updated: Feb 21, 2026
No.: 4,883
character-asset根据剧本与人物身份设计角色资产，固定三视图加中景；支持女性角色魅力、气质与肖像设计。用于人物、角色设计、人物设定、人物资产、女性魅力、character、角色图；输出静态参考图任务说明与资产合同，本 Skill 独立完成静态参考图任务说明、资产锁定、审核字段、负向约束和可供后续制作直接读取的资产合同。
Skill content language: Chinese
Repository: 62656456/ai-film-skills
GitHub stars: 105Updated: Sep 28, 2026
No.: 4,884
epidemiology-guideEpidemiological study designs, measures of association, and public health ana...
Repository: brycewang-stanford/Auto-Empirical-Research-Skills
GitHub stars: 4,955Updated: Apr 3, 2026
No.: 4,885
gs-searchSearch Google Scholar for academic papers by keywords. Returns results with title, authors, journal, year, citation count, and full-text links. Use when the user wants to search Google Scholar.
Repository: cookjohn/gs-skills
GitHub stars: 541Updated: Mar 4, 2026
No.: 4,886
ai面向AI企业的专业合规文档生成工具。覆盖算法备案、数据安全评估、个人信息保护影响评估（PIA/DPIA）、AI伦理审查、等保2.0、数据安全法、个人信息保护法、生成式AI服务管理暂行办法等20+类合规场景。提供标准化文档模板、智能风险识别、合规建议生成、整改方案输出等一站式服务，帮助企业快速建立AI合规体系，降低合规风险和成本。
Skill content language: Chinese
Repository: CSlawyer1985/legal-skillhub
GitHub stars: 32Updated: Aug 4, 2026
No.: 4,887
pydicomPython library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
Repository: davila7/claude-code-templates
GitHub stars: 33,223Updated: Dec 20, 2025
No.: 4,888
playwright-skillComplete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
Repository: davila7/claude-code-templates
GitHub stars: 33,223Updated: Jan 25, 2026
No.: 4,889
tanstack-query-expertExpert in TanStack Query (React Query) — asynchronous state management. Covers data fetching, stale time configuration, mutations, optimistic updates, and Next.js App Router (SSR) integration.
Repository: davila7/claude-code-templates
GitHub stars: 33,223Updated: Oct 24, 2026
No.: 4,890
autotestreport自動化驗收測試 (Auto-Acceptance-Test) - 執行網站功能驗收並產生報告
Skill content language: Chinese
Repository: elfhermit/AutoTest
GitHub stars: 1Updated: Feb 26, 2026
No.: 4,891
hackernews-frontpageScrape the Hacker News front page (titles, points, comment counts).
Repository: garrytan/gstack
GitHub stars: 140,824Updated: Nov 2, 2026
No.: 4,892
timesfm-forecastingZero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Supports both basic forecasting and advanced covariate forecasting (XReg) with dynamic and static exogenous variables. Automatically checks system RAM/GPU before loading the model, validates dataset fit before processing, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model and handle your specific dataset.
Repository: google-research/timesfm
GitHub stars: 35,331Updated: Jun 8, 2026
No.: 4,893
workrallyWorkRally CLI (workrally) — 面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集。支持 AI 生图、AI 生视频、项目管理、资产库、媒资管理、无限画布、文件上传下载等。 Use when user asks to generate images, generate videos, manage projects, upload files, download assets, manage materials, or interact with WorkRally platform via command line.
Skill content language: Chinese
Repository: infometa/workbuddyskills
GitHub stars: 424Updated: Jul 21, 2026
No.: 4,894
review-analysis对亚马逊商品评论进行深度分析，自动识别产品痛点、分析退货原因，生成改进建议和客服回复模板。Invoke when user uses /review-analysis command with a product ASIN.
Skill content language: Chinese
Repository: liangdabiao/amazon-sorftime-research-MCP-skill
GitHub stars: 1,100Updated: Jul 8, 2026
No.: 4,895
linkfox-temu-compliance-globalTemu 全球站电商合规（Compliance）API，经 LinkFox 网关转发 Partner Global 合规相关 OpenAPI（bg.compliance.*、bg.arbok.open.*、bg.flash.open.* 等，共 9 个接口）。当用户提到 Temu Global 合规、商品资质、GPSR、治理属性、实拍图、资质上传、bg.compliance.edit、arbok cert、site=global 合规时触发。
Skill content language: Chinese
Repository: linkfox-ai/linkfox-skills
GitHub stars: 115Updated: Oct 14, 2026
No.: 4,896
arc42-documentationAuthor an arc42 architecture document with the project's cross-section traceability rules. Use when producing or extending an arc42 document — it carries the procedure the "Architecture Documentation" contract deliberately leaves out: scaffolding the with-help template, the five traceability rules arc42 does not enforce, the Chapter 11 Risks-vs-Technical-Debt structure, the ADR-to-risk-ID wiring, the Chapter 1.2-vs-10 quality-goal marking, and the six-part Quality Attribute Scenario form. The contract pins the vocabulary (arc42, C4/PlantUML, Nygard ADRs, Pugh); this skill is the how-to.
Repository: LLM-Coding/Semantic-Anchors
GitHub stars: 528Updated: Sep 24, 2026
No.: 4,897
hatch-petCreate, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references. Use when a user wants to hatch a Codex pet, create a custom animated pet, or build a built-in pet asset with an 8x9 atlas, transparent unused cells, row-by-row animation prompts, QA contact sheets, preview videos, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.
Repository: nexu-io/open-design
GitHub stars: 106,688Updated: Aug 18, 2026
No.: 4,898
publish-siteVersioned site deploys to GitHub/Cloudflare/Netlify Pages.
Repository: NousResearch/hermes-agent
GitHub stars: 261,860Updated: Aug 27, 2026
No.: 4,899
autosar-bswAUTOSAR BSW expert. Defaults to Classic AUTOSAR (BSW/MCAL/RTE, static config, C, AUTOSAR OS) and operates in six modes: (1) BSW configuration — Com, NvM, Dem, Dcm, Os, MemIf with dependency chain and EB Tresos / DaVinci container paths; (2) ARXML debugging — classify, locate, and fix consistency errors with a corrected fragment and prevention rule; (3) RTE generation troubleshooting — diagnose generator failures across pre-gen, contract, implementation, and post-gen build phases; (4) COM stack debugging — layer-walk CanDrv → CanIf → PduR → Com → RTE for missing, wrong, stale, or intermittent CAN signals; (5) Boot, NVM & power — EcuM/BswM startup and shutdown, bootloader / UDS reprogramming, NvM/Fee/Ea storage, sleep/wakeup, partial networking; (6) Communication protocol — CAN / CAN FD, LIN, CanTp, PduR gateway, ComM/Nm, UDS (ISO 14229), SOME/IP, DoIP. Handles Adaptive AUTOSAR (ara:: clusters) when the input names ara::com, ara::exec, POSIX, or manifests, plus legacy bring-up behind MCAL/CDD interfaces.
Repository: ptsilivis/autonomousguy
GitHub stars: 38Updated: Jul 4, 2026
No.: 4,900
stock-research个股深度研究（多 Agent 编排版）— 多角色分析师并行编排（技术/新闻/资金情绪/基本面/市场 5 分析师并行 → 多空辩论 → 研究经理汇总），数据全部走 QuantMind 本地（QuantDB + PG 新闻富集 + Huntly），新闻双通道（自家 FinBERT 量化情绪 + 实时搜索补充）。用户说「深度研究」「个股深度研究」「研究某只股票」「多角度分析」时使用：跑 research_data.py 取数 → 并行分析师 → 辩论 → 汇总报告 → PDF → 落盘深度分析目录。触发词：深度研究、个股研究、研究600519、多角度分析、全面分析某股
Skill content language: Chinese
Repository: qusong0627/QuantMind
GitHub stars: 1,895Updated: Oct 31, 2026