#SkillRepo stars
- 17665Mxl Project ScaffoldTaoELi/MaxwellLinkThis skill should be used when users ask to prepare MaxwellLink input files; it scaffolds a new `projects/YYYY-MM-DD-NAME/` folder from copy-ready templates and provides basic validation.9
- 17666Mxl SinglemodeTaoELi/MaxwellLinkThis skill should be used when users need the MaxwellLink single-mode cavity solver for fast prototyping and regression, in either socket or embedded mode.9
- 17667Mxl TroubleshootTaoELi/MaxwellLinkThis skill should be used when MaxwellLink simulations stall, diverge, or produce missing/incorrect observables; it provides a first-aid checklist for sockets, units, and driver configuration.9
- 17668Onboarding Teardownadaptyteam/adapty-skillsUse when someone wants to improve, fix, test or critique a mobile app's onboarding — "here's my onboarding", "roast my flow", "why do users drop off before the paywall", a competitor's signup flow, a welcome or activation flow, a quiz, or a flow described in one sentence. Also use whenever YOU are the one designing or generating an onboarding sequence and were given no design reference to follow — no reference screens, no existing flow to copy, no spelled-out sequence — as in "build me an onboarding", "add a quiz before the paywall", "make a flow that converts"; this library is the reference i9
- 17669Paper Tutorial Plasmon HeatingTaoELi/MaxwellLinkDual-purpose tutorial to reproduce manuscript Figure 5b, 5d, and 5e plasmonic flux and HCN heating maps (EM-only, TLS, and ASE/BOMD), and to transfer the workflow to related plasmon-molecule systems by adjusting geometry, molecular model, and run procedures.9
- 17670Paper Tutorial Vsc WaterTaoELi/MaxwellLinkDual-purpose tutorial to reproduce manuscript liquid-water vibrational strong-coupling spectra and CPU scaling (single-mode cavity plus Meep Bragg resonator), and to adapt the same procedure to related VSC systems by retuning cavity/resonator parameters, size ladders, and execution settings.9
- 17671Paywall Teardownadaptyteam/adapty-skillsUse when someone shares a mobile subscription or purchase screen and wants to know what to change, fix, test or improve — "here's my paywall", "roast this", "what should I test", a competitor screenshot, a design in progress, or an image with almost no text. Also use whenever YOU are the one designing or generating a paywall screen and were given no design reference to follow — no reference image, no existing screen to copy, no layout spec — as in "make me a paywall", "make one that converts", "will this convert?", "is this any good?"; this library is the reference in that case, and it evaluat9
- 17672Project BuildingHOWILLMAKEIT/skills建立和持续维护项目的工作方式与文档体系。用户要求创建 AGENTS.md、建立 docs、整理项目交接、沉淀开发或实验流程,或按已有项目规范推进工作时使用。编写或修改文档必须使用内置的 better-notes,核对来源、语言准确性和写作风格。适用于软件和研究项目;单纯概念问答、独立文件编辑或只读状态查询不因此自动触发项目文档写入。9
- 17673Prune Commentskr4chinin/skillsAudit code comments and plan which to delete, keep, rewrite or replace with a refactor. Use when asked to prune a codebase's comments, or to sort workaround comments into root-cause fixes and safe deletions.9
- 17674Purchase Testingadaptyteam/adapty-skillsUse when a sandbox or test purchase does not work, or when someone is about to make their first one. Triggers on "my sandbox purchase isn't going through", "the purchase sheet doesn't appear", "I bought it but nothing happened", "the paywall is blank on my phone", "no event in the Adapty dashboard", "how do I test purchases", "test on a real device", "restore doesn't work". Diagnoses first, so nobody is sent back to a console before the cheap checks have run. Complements `adapty-integration`, which owns writing the code and connecting the stores.9
- 17675Recover Semantic Modelkr4chinin/skillsRecover a program's minimal semantic model (the state that changes what users see, how its transitions repeat and reorder, what each effect requires). Use when asked to recover or audit that model, to check what is idempotent or order-dependent, or to split a refactor into provably equivalent and "trust me" changes.9
- 17676Revolut X Authrevolut-engineering/revolut-agent-skillsRevolut X API authentication setup, Ed25519 keypair generation, and request signing. Use when the user asks to set up Revolut X API access, configure API keys, generate an Ed25519 keypair, sign requests manually, or debug 401/403/409 authentication errors.9
- 17677Revolut X Balancerevolut-engineering/revolut-agent-skillsRevolut X account balance queries — available, reserved, staked, and total funds per currency. Use when the user asks to check their balance, view their portfolio, or verify they have sufficient funds before placing an order on Revolut X.9
- 17678Revolut X Configurationrevolut-engineering/revolut-agent-skillsRevolut X exchange configuration — available currencies, trading pairs, and pair constraints (min/max order size, step, status). Use when checking supported assets, validating a symbol, or looking up order size constraints before placing a trade.9
- 17679Revolut X Market Datarevolut-engineering/revolut-agent-skillsRevolut X authenticated market data — ticker prices (bid/ask/mid/last), OHLCV candles at multiple intervals, and order book depth up to 20 levels. Use when the user asks for the price of a crypto asset, candlestick data, order book depth, or bid/ask spread on Revolut X.9
- 17680Revolut X Ordersrevolut-engineering/revolut-agent-skillsRevolut X order management — place market or limit orders, view active and historical orders, and cancel orders. Use when the user asks to buy or sell crypto, place a market or limit order, check open orders, cancel an order, or anything related to trading on Revolut X.9
- 17681Revolut X Public Market Datarevolut-engineering/revolut-agent-skillsRevolut X public market data — public order book (5 price levels) and latest 100 trades across all pairs. No authentication required. Use when the user wants a quick price check or recent trade data and has not configured API keys, or asks about public market data.9
- 17682Revolut X Tradesrevolut-engineering/revolut-agent-skillsRevolut X trade data — market trade history, private fills, and execution details for completed orders, with pagination and date filtering. Use when the user asks to view trade history, check fills, see recent trades, or analyse order execution on Revolut X.9
- 17683Robodk AddinRoboDK/RoboDK-Agent-SkillsCreate, edit, validate, package, inspect and extract RoboDK Add-ins (also called RoboDK Apps) — a folder of Python action scripts plus AppConfig.ini that adds menus, toolbar buttons, context-menu entries and settings dialogs to RoboDK, distributed as an .rdkp package. Use this skill whenever the user mentions RoboDK add-ins, RoboDK apps, .rdkp files, AppConfig.ini, the AppLoader or Add-in Manager, roboapps/AppSettings, or wants to add a button, menu, toolbar action, right-click action or custom UI to RoboDK, package/unpack an .rdkp, inspect an existing Add-in, or automate a RoboDK workflow tha9
- 17684Robodk APIRoboDK/RoboDK-Agent-SkillsReference for writing, porting, or debugging application code against the RoboDK API — the Robolink/Item/Mat SDK for driving RoboDK from Python, TypeScript, C++, C#, MATLAB, C, or Visual Basic. Use when a user wants to write a script that connects to RoboDK, reads/writes item poses and joints, runs MoveJ/MoveL/MoveC, builds targets/frames/tools/programs, converts between Euler/pose conventions, or ports RoboDK API code from one language to another.9
- 17685Robodk Driver BuilderRoboDK/RoboDK-Agent-SkillsWrite, port, or debug a RoboDK robot driver — the standalone console program (Python script or compiled executable) that lets RoboDK move a real robot live over its own stdin/stdout protocol ("Online Programming"), as opposed to a post processor generating an offline program file. Use when asked to "write/add a driver for <robot>", "port this driver to another language", "the robot driver doesn't respond to <command>", "support live/online programming for a new robot", or when handed an existing driver file to fix or extend. Distinct from robodk-real-robot-control, which operates an already-wo9
- 17686Robodk Post Processor BuilderRoboDK/RoboDK-Agent-SkillsRead, write, debug, and extend RoboDK post processors — the Python files defining a `RobotPost` class (MoveJ/MoveL/MoveC/setFrame/setTool/setSpeed/setZoneData/setDO/waitDI/RunCode/RunMessage/ProgSave...) that translate a RoboDK simulation program into a real robot controller program. Use this skill whenever the user mentions RoboDK, post processors, "the post", a Posts folder, or generating/fixing robot controller code in any dialect (KRL .src, RAPID .mod, Fanuc .ls, Motoman .jbi, Siasun .spf, URScript, Kawasaki .as, G-code) — including indirect asks like "my robot program comes out wrong", "a9
- 17687Robodk Real Robot ControlRoboDK/RoboDK-Agent-SkillsThe ONLY skill in this repo allowed to move a real, physical robot — via robot.Connect() and RUNMODE_RUN_ROBOT/PROGRAM_RUN_ON_ROBOT, using RoboDK's robot drivers (Online Programming). Every other RoboDK skill here is simulation-only by design; redirect here the moment a request is unambiguously about the real robot moving, not the simulated one — phrasings like "move the real robot", "run this on the actual/physical robot", "connect to the robot and jog it", "online programming", "drive the robot live". Do not use for anything that stays in simulation, for generating a program to transfer late9
- 17688Robodk Shape BuilderRoboDK/RoboDK-Agent-SkillsBuild parametric RoboDK visual components — primitives (box, sphere, cone), fixtures (table, pedestal, fence), and mechanisms (conveyor, linear rail, T-bot/H-bot gantry, 1/2/3-axis turntable/positioner) — using RoboDK's own bundled Components Add-in library instead of hand-rolled mesh geometry. Use whenever a station needs one of these shapes; prefer this over generating raw triangle meshes for anything it covers.9
- 17689Robodk Station AuditRoboDK/RoboDK-Agent-SkillsAudit RoboDK stations for common structural mistakes.9
- 17690ShipreeltheBstar/shipreelTurn a pull request into a short narrated walkthrough video (about two and a half minutes) with animated diagrams, code panels, optional screen recordings of the real app, captions, crossfade cuts and an ambient music bed. Runs locally with no paid services by default. Use when asked for a PR video, PR walkthrough, demo video of a change, or "make a shipreel".3
- 17691Speech to Text Apisbleakbelladonnals/asr-transcription-skills多平台录音转写(Gemini / 阿里百炼 / 火山方舟)API 调用与对比评测。触发场景:课程/会议录音转文字、多引擎转写质量对比、公众号文章数据采集。包含三家 API 的调用方式、已踩过的坑、现成脚本位置和锚点对比方法。9
- 17692Srt to Review Blueprintbleakbelladonnals/asr-transcription-skills把课程录音转写 SRT(含转写错误、碎片块、无说话人标签)+ 课堂笔记 + 面试旁听笔记,加工成课后复习蓝本:一份整体版 + 一份笔记补丁版(含术语表、行内纠错标注、存疑清单)。触发词:录音转写整理、srt 转蓝本、复习文档、转写纠错、笔记补充、课程录音整理。9
- 17693Storyblok Build Frontendstoryblok/agent-pluginUse when generating frontend components for Storyblok blocks — writing, registering and validating the framework code that renders a space's content. E.g. "generate components for my blocks", "build an Astro + Storyblok landing page".9
- 17694Storyblok Build Pluginstoryblok/agent-pluginUse when extending Storyblok with plugins to enhance what editors can do — custom field inputs, Visual Editor panels, pages inside a space, integrations with external systems — including choosing, building, or deploying one. E.g. "editors need a map location picker", "build a field plugin", "deploy our plugin".9
- 17695Storyblok Implement Figmastoryblok/agent-pluginUse when turning a Figma design into frontend components backed by Storyblok blocks. E.g. "figma to storyblok", "build this Figma design".9
- 17696Storyblok Model Contentstoryblok/agent-pluginUse when creating or modifying Storyblok components/blocks, content types, or fields, or modeling a content schema from multi-modal input. E.g. "model content for a blog", "add an image field to the teaser", "set up blocks for this landing page design".9
- 17697Storyblok Use CLIstoryblok/agent-pluginUse when driving Storyblok through the Storyblok CLI — code-driven schema, content migrations, bulk pull/push of stories, components, assets or datasources, or scaffolding a project.9
- 17698Storyblok Use MCPstoryblok/agent-pluginUse when interacting with Storyblok through the MCP server — the tool model, operation names and payload shapes for stories, assets, components, datasources and every other resource. Load it before calling `mcp__storyblok__` tools, alongside the skill that owns the task.9
- 17699Storyblok Use Storyblokstoryblok/agent-pluginUse when a request touches Storyblok at all, including advice or a plan that changes nothing yet. You MUST load it first — before any other Storyblok skill and before any `mcp__storyblok__` tool — to pick the right skill and the right tool for the job. E.g. "add an FAQ section to the pricing page", "model content for a blog", "set up Storyblok in this project".9
- 17700Transcription Quality Evaluationbleakbelladonnals/asr-transcription-skills对比评测录音转写产品/引擎(录音硬件端到端 vs 云转写模型):控制变量测试设计(2×2 音频×引擎)、ffmpeg 音频质量客观指标(响度/动态/底噪/削波/声道)、SRT 变体解析与统计、关键术语识别对照、内容锚点时间轴对齐、幻觉检测,输出对比矩阵。触发词:转写对比、转写质量、录音质量对比、ASR 评测、哪个转写好、录音笔对比、转写引擎对比。9
- 17701UndressHOWILLMAKEIT/skills去除论文、开源项目、技术博客、简历项目和产品介绍中的包装性语言,基于论文、代码、实验与原始材料,简单说明作者实际复用了什么、修改了什么、实现了什么、验证了什么。用于用户询问“这个工作到底做了什么”“是不是过度包装”“创新点本质是什么”“去掉术语重新解释”或需要审视技术工作的真实含金量时。9
- 17702Video SummaryHOWILLMAKEIT/skillsBibiGPT 风格视频总结:输入 Bilibili / YouTube 视频链接,快速抓取字幕/转写文本,并生成结构化总结(TL;DR、核心要点、章节时间线、金句,支持中英文)。Use when the user shares a video link (bilibili.com, b23.tv, youtube.com, youtu.be) and asks to summarize it, extract key points, get subtitles/transcript, 总结视频, 提炼要点, 视频笔记.9
- 17703Academic Writing RefinerZihan-Zhu/academic-writing-refinerRefine academic writing for computer science research papers targeting top-tier venues (NeurIPS, ICLR, ICML, AAAI, IJCAI, ACL, EMNLP, NAACL, CVPR, WWW, KDD, SIGIR, CIKM, and similar). Use this skill whenever a user asks to improve, polish, refine, edit, or proofread academic or research writing — including paper drafts, abstracts, introductions, related work sections, methodology descriptions, experiment write-ups, or conclusion sections. Also trigger when users paste LaTeX content and ask for writing help, mention "camera-ready", "rebuttal", "paper revision", or reference any academic venue o5
- 17704Agent BuilderNikolasMarkou/agent-builderBuild, review, troubleshoot, optimize, and extend AI agents — single-agent, multi-agent, RAG, and production systems. Covers framework selection, pattern selection (topology, behavioral, data flow), agent orchestration, state design, and tool design. Defaults to Python with LangChain/LangGraph; also supports CrewAI, Strands, OpenAI Agents SDK, Google ADK, and Mastra. Use whenever the user wants to build, design, scaffold, review, debug, optimize, extend, or migrate an agent or agentic system.5
- 17705Agent Design FundamentalsArchive228/lab-skillsDecision rules for whether to build an LLM agent and how to architect it, distilled from OpenAI's "A Practical Guide to Building Agents": build/no-build criteria, model selection, tool design, single-agent vs multi-agent orchestration (manager pattern vs decentralized handoffs), layered guardrails, and human-in-the-loop triggers. Use when designing, reviewing, or refactoring an agent system — before choosing an architecture, adding more agents, defining tools, or shipping an agent to production without guardrails.10
- 17706Agent EvalsArchive228/lab-skillsBuild and maintain evaluation suites for AI agents: bootstrap 20-50 tasks from real failures, pick code-based vs model-based vs human graders by agent architecture (coding, conversational, research, computer-use), write unambiguous tasks with reference solutions, and keep suites alive via ownership and transcript reading. Use when creating evals from zero, adding graders or eval cases, debugging suspicious eval scores, or deciding pass@k vs pass^k metrics for an agent product.10
- 17707Agent Failure PreflightArchive228/lab-skillsPre-deployment failure-mode gate for agentic AI systems, distilled from Microsoft AI Red Team's Taxonomy of Failure Modes in Agentic AI Systems v2.0 (grounded in 12 months of red-team engagements). Run it before shipping or materially changing an agent — adding tools/MCP servers/plugins, enabling persistent memory, adding sub-agents or orchestration, enabling computer use, or expanding permissions — to verify concrete controls against memory poisoning, HitL bypass, goal hijacking, supply-chain compromise, session context contamination, capability disclosure, and multi-agent cascade failures.10
- 17708Agent Improvement LoopArchive228/lab-skillsOperate a trace-driven improvement loop for a deployed agent: capture execution traces, convert human and model feedback into Promptfoo evals, gate the current harness against them, rank harness changes with HALO, and hand off a Codex-ready change set. Use when an agent is live and you need a repeatable cadence for diagnosing failures and shipping harness fixes — not for pre-launch prompt tinkering without traces.10
- 17709Agent SandboxingArchive228/lab-skillsContainment architecture for agent products that execute code, browse, or call tools, distilled from Anthropic's "How we contain Claude across products". Use when designing or reviewing sandboxing, isolation, permission systems, egress controls, or untrusted-content handling for an agent, or when choosing between container, OS-sandbox, and VM isolation patterns; provides a threat-model checklist covering user misuse, model misbehavior, and external attacks.10
- 17710Agent Sessionsvladmdgolam/agent-skillsSearch, list, and resume AI agent sessions across Claude Code, Codex CLI, Gemini CLI, opencode, Hermes Agent, and Cline CLI. Use when the user asks to find a past conversation, search session history, resume a previous session, list recent agent activity, or check what was discussed in a prior session. Also use when asked to "find that conversation where I...", "resume my last codex session", "read latest convo", "read last messages", "what did I work on yesterday", "search my claude history for X", or gives an agent session id such as `ses_...`, a UUID, or a Cline id like `1782988565588_qqrxi9
- 17711Agentic Coding DisciplineArchive228/lab-skillsWorking discipline for agentic coding sessions, distilled from Claude Code's official best-practices doc: close the loop with runnable verification (tests, /goal, Stop hooks, adversarial review subagents), separate explore/plan/code phases, keep CLAUDE.md lean, choose permissions/sandboxing deliberately, manage context aggressively (/clear, /compact, checkpoints), and scale with fan-out and agent teams. Use at the start of any non-trivial coding-agent session, when configuring an agent environment, or when a session shows drift, bloat, or unverified "done" claims.10
- 17712Agentic VulnerabilitiesJasonTheDeveloper/owasp-skillsOWASP Top 10 for Agentic Applications (2026) vulnerability knowledge base for identifying, assessing, and remediating security risks in AI agent systems.9