Parcourir le registre

Toutes les entrées, par ordre alphabétique — 56 437 au total. Page 194 sur 226.

• shipping-artifactsThe durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core
• shipping-changesEnd-to-end change-shipping closed loop for non-trivial work — research → proposal doc → phased guarded impleme
• shipping-methodologyUse when running claudikins-kernel:ship, preparing PRs, writing changelogs, deciding merge strategy, or handli
• shipping-page-generatorWhen the user wants to create or optimize a shipping or delivery information page. Also use when the user ment
• shipping-productsPlan product launch/release: rollout/rollback plan, comms, monitoring, post-launch review. See also: launch-ma
• shipping-velocityHelp users accelerate their product development cycles by implementing high-intensity rituals, ruthless scopin
• shipshitdev-advanced-evaluationDesign and operate LLM-as-a-Judge evaluation systems using direct scoring, pairwise comparison, rubric calibra
• shipshitdev-agent-browserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the u
• shipshitdev-auditRun technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns.
• shipshitdev-clarifyImprove unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to unde
• shipshitdev-code-reviewCorrectness, security, and spec-fidelity gate for incoming pull requests. Auto-invoked when reviewing a diff,
• shipshitdev-codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interfac
• shipshitdev-critiqueEvaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonan
• shipshitdev-debugSystematic debugging guidance for bugs, failures, unexpected behavior, and performance regressions. Emphasizes
• shipshitdev-docsCreates clear, concise technical documentation for software projects, runbooks, and developer guides. Use when
• shipshitdev-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• shipshitdev-interviewRepo-grounded discovery interview that produces a handoff brief for PRD writing, feature intake, or planning.
• shipshitdev-mcp-builderCreates MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-
• shipshitdev-releaseCut a release from the trunk (default branch) and generate plain-English patch notes. Determines the next sema
• shipshitdev-skill-creatorGuide for creating effective skills. Use when creating a new skill or updating an existing one to extend agent
• shipshitdev-tech-debtInventory, quantify, and prioritize technical debt into a register ranked by interest (how often it hurts) ove
• shipshitdev-worktreeCreate an isolated git worktree from the correct base branch and check it out into a clean, gitignored directo
• shipwright-pipelineAutonomous app builder that converts plain-English descriptions into
• shirky-principleApply the Shirky Principle when analyzing why legacy systems persist, why incumbents resist disruptive solutio
• shitiesheng-perspective史铁生生死哲思思维——轮椅上的哲思、苦难中的超越、地坛的沉思、生死之问。 触发词：「史铁生视角」「像史铁生那样写」「我与地坛」「死是一件不必急于求成的事」。 擅长：生死哲思、苦难超越、内省散文、地坛意象、轮椅上的思考。
• Shiv33ndu/songgenerationa2aAn A2A wrapper for tencent/SongGeneration on HuggingFace Space
• shobcoder-brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or
• shobcoder-deep-researchGOD MODE deep research skill. Multi-phase autonomous research loop: query decomposition → multi-source crawlin
• shobcoder-frontend-designCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the use
• shobcoder-ponytailForces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who h
• shockrock2004-handoffUse when the user invokes /handoff, and ALWAYS when starting work in a repo that already contains a HANDOFF.md
• shop.theothers/theothersThe Others — an agentic t-shirt shop. Browse products and buy t-shirts via AI agents.
• shopifyProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• shopify-ab-testingE-commerce skills for AI agents — product research, marketing automation, supply chain optimization, and busin
• shopify-admin-apiA directory that holds all skills md files for OpenClaw and Claude Code
• shopify-alt-textUse when backfilling missing image alt text on a Shopify store: images with no alt attribute, accessibility al
• shopify-analytics-guideE-commerce skills for AI agents — product research, marketing automation, supply chain optimization, and busin
• shopify-app-recommendationsApp stack advisor — essential apps by business stage, cost optimization, performance impact analysis
• shopify-blog-strategyContent marketing via Shopify blog — SEO content, product education, buying guides, internal linking
• shopify-catalog-auditUse when someone wants to find product-data problems across a Shopify catalog: "audit my catalog", "find PDP p
• shopify-catalog-cleanupUse when fixing the debris an audit found in a Shopify catalog: bulk-archive dead/discontinued/zero-inventory
• shopify-category-taxonomyUse when you assign the Shopify Standard Product Taxonomy category, "set the product category", "categorize th
• shopify-contentCreate and manage Shopify pages, blog posts, navigation menus, redirects, and SEO metadata via the Admin API o
• shopify-devShopify Developer. Activate when a user is building or modifying a Shopify theme, app, or integration. Trigger
• shopify-developerComplete Shopify development reference covering Liquid templating, OS 2.0 themes, GraphQL APIs, Hydrogen, Func
• shopify-expertBuilds and debugs Shopify themes (.liquid files, theme.json, sections), develops custom Shopify apps (shopify.
• shopify-hydrogenCore Shopify Hydrogen APIs — createHydrogenContext, cart handler, CartForm, caching strategies, pagination, SE
• shopify-json-ldUse when adding structured data / JSON-LD / schema markup to a Shopify store: recipe, FAQ, Article/BlogPosting
• shopify-listing-optimizerGenerate SEO-optimized Shopify product listings from basic product details. Creates title, description, meta t
• shopify-matrixifyUse when a store owner is doing bulk data work through the Matrixify (formerly Excelify) app: bulk import/expo
• shopify-productsCreate and manage Shopify products via the Admin GraphQL API or CSV import. Workflow: gather data, choose meth
• shopify-redirect-mappingUse when you need to map a pile of old URLs to live pages and turn them into 301 redirects on a Shopify store:
• shopify-seo-metadataUse when a store has missing SEO titles or meta descriptions and you want to backfill them: "backfill missing
• shopify-setupSet up Shopify CLI auth and Admin API access for a store. Install CLI, authenticate, create custom app, store
• shopify-storeShopify Store Auditor. Activate when a user wants to improve, audit, or optimize a Shopify store. Triggers on:
• shopify-store-auditComprehensive audit of a Shopify store — SEO, performance, product listings, and conversion optimization. Outp
• shopify-theme-builderBuild a complete, clean, Online Store 2.0 Shopify theme from a guided requirements interview. Use when a user
• shopify-ui-skillsShopify's UI design system. Use when building interfaces inspired by Shopify's aesthetic - light mode, Inter f
• shopify-yourskillUse when [the specific situations, symptoms, and phrases someone would type or think when they hit this proble
• shopping-assistantAn intelligent shopping research assistant that helps users find the best product to buy through systematic co
• shopping-campaign-auditGoogle Ads Shopping / retail audit — product feed coverage, listing-group granularity, zero-impression product
• shoppingscraperFetch product data, prices, offers, buy-box winners, variants, and reviews from Google Shopping, Amazon, Bol.c
• shorebird-patchShorebird OTA パッチの作成・配布（staging → promote → stable）
• shortIntentionally short name so usage confidence flips to low (names under six characters or without a separator a
• short-descToo short.
• short-drama基于文件系统初始化、继续、恢复和交付短剧或漫剧项目，并提供面向创作者的本地 Dashboard；也负责组织项目级 Look Development / 风格帧方向与授权生产观察校准。面向编剧、漫剧工作室与编导。用户提出“
• short-drama-assets从短剧剧本拆解并统筹角色/造型、场景/视图、道具/状态、可选的角色声音方向和跨场连续性。用户说‘拆角色/场景/道具’、‘做资产表/角色表/场景表/道具表’、‘判断复用还是新变体’、‘更新造型/道具状态’、‘给角色定声音/
• short-drama-develop将中文小说、短剧或漫剧想法、梗概、改编材料、已有系列笔记或多集完整剧本发展成可追溯的改编方案、戏剧方向、创作简报、导演阐述、故事引擎与分集地图，并按题材与制作形态（画风）选择写法。用户提出“导入小说做短剧”“从多集整稿生
• short-drama-image-prompts为已确认的短剧角色、造型、场景、视角、道具和状态编写或修改可复制的通用资产图片提示词，并把已接受视觉方向投影成 Look Development 人物、地点或高压力风格帧。用户提到角色设定图、三视图、人物参考图、场景设定
• short-drama-knowhow维护者专用的短剧 know-how 学习、验证与生命周期治理。仅在维护者明确要求从其当前会话提供的授权只读文本源学习完整短剧项目链，并把私有观察逐步转成去标识、去复刻、经盲测与独立审查的公共 reference、rubr
• short-drama-novel-analyze把长篇小说、连载网文或多集散稿拆成可追溯的原著分析：章节索引、改编价值快评、逐章功能提取、剧情单元与节奏聚合、人物与设定归并，最后给出改编价值判定与分集候选，交给 $short-drama-develop 立契约。用户说
• short-drama-review独立校验与审查文件系统短剧项目中的原著分析层、故事、剧本、资产、连续性、资产图片提示词、分镜、关键帧和视频提示词，并消费有界授权生产观察做当前项目校准。用户提出“审稿/检查剧本”“检查资产或连续性”“检查图片/视频提示词
• short-drama-storyboard把已接受的中文短剧剧本和资产转成原文落实表、有戏剧动机的镜头、连续性边界与冻结关键帧提示词；关键场次可先做场次视觉计划或 Coverage Audition 比较真正不同的导演方案。用户提出“拆分镜/设计镜头/做镜头表”
• short-drama-video-prompts为已接受的短剧镜头和关键帧编写或修改可复制的通用视频提示词与运动规格。用户提到视频提示词、文生视频、图生视频动作、人物表演过程、运镜、对白口型、环境运动、镜头时长、起止状态或把分镜转成视频提示词时直接使用；只描述单个已编
• short-drama-write编剧环节：创作或修订中文短剧、漫剧单集卡、因果节拍与可拍摄的 Markdown 剧本，也负责把现有中文剧本以保留原文、预览语义差异、创作者接受后发布的方式规范化。用户提出“写/改一集短剧”“把大纲写成剧本”“优化场景/对
• short-formRepurpose a long-form YouTube video into short-form clips for Reels, Shorts, and TikTok. Identifies clip-worth
• short-form-videoThis skill should be used when the user asks to "make a Reels/TikTok/YouTube Shorts video", "build a short-for
• short-form-video-scriptThe master craft of scripting short-form vertical video (Reels, TikTok, Shorts) for watch-through. Use when so
• short-term-investing-recommendationUse when generating short-term swing-trade recommendations from this investing workspace. Runs the short-term
• shortcut-ui-skillsShortcut's UI design system. Use when building interfaces inspired by Shortcut's aesthetic - light mode, Inter
• shortenEdits and improves English business and professional writing using principles of information style — a reader-
• shortfilm-promptGenerate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using
• shortlist-deck-builderTurn shortlisted candidates into a client-ready narrative with positioning, strengths mapped to client priorit
• shorts-from-takesAssemble several raw clips — multiple takes, separate shots, or existing reels — into ONE finished, on-brand v
• shot-compositionThis skill should be used when the user asks to "compose a frame", "set up a grid", "plan shot composition", "
• shot-list-skillAI历史故事视频创作
• should-i-careSingle-CVE applicability triage that evaluates whether a CVE actually applies to the user's environment by rea
• show-and-shareSchreibt einen fertigen Show-&-Share-Post für die SKAILE Community. Nutzen wenn der User sagt "schreib mir ein
• show-hn-writerDraft a Show HN post backed by real HN performance data. Uses observed patterns from 250 top HN posts to maxim
• show-jira-issueUse this skill when the user asks about a specific Jira issue by key (e.g. PROJ-123, ENG-456) — for viewing th
• show-linear-issueUse this skill when the user asks about a specific Linear issue by identifier (e.g. BLA-123, ENG-456) — for vi
• show-meUse when the answer is a picture rather than prose: the user says "show me" or "diagram this" about the curren
• show-your-work-kleonApply Austin Kleon''s sharing framework. Trigger on: "what should I share?", "build an audience", "document my
• showcase-page-generatorWhen the user wants to create, optimize, or audit a showcase or gallery page for user-generated content. Also
• shubhranshu03-accessibility-checkerA curated open-source library of reusable SKILL.md files for Claude. Learn, use, and build powerful AI skills
• shubhranshu03-code-reviewerA curated open-source library of reusable SKILL.md files for Claude. Learn, use, and build powerful AI skills
• shubhranshu03-database-schema-reviewerA curated open-source library of reusable SKILL.md files for Claude. Learn, use, and build powerful AI skills
• shubhranshu03-migration-plannerA curated open-source library of reusable SKILL.md files for Claude. Learn, use, and build powerful AI skills
• shuffleShuffle — pick a completely random genre and station
• 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。
• shut-up-and-codeLoad-bearing comments only. Use when writing or editing code in any language, or when the user asks about comm
• shut-up-and-driveCuts fluff and leads with what matters. Applies Parkinson's Law, Pareto, and Goodhart's Law so every word earn
• shuzishengmingkazike-skill数字生命卡兹克（前UI/交互设计师→AI自媒体人→虚实传媒CEO→AIFUT大会发起人）的AI科技自媒体创作思维——平实直接、数据碾压、自嘲幽默、硬核输出。 触发词：「数字生命卡兹克视角」「像卡兹克那样写」「AI产品实测
• Shy-Plus/openclaw-a2a-bridgeCross-device Agent-to-Agent communication bridge for OpenClaw, powered by Google A2A Protocol
• siExecute structured TDD implementation following task documents or bug fixing in ETNA_TRADER. Use when starting
• si-coderZero human involvement full-stack deployment. Umbrella skill that points to modular sc-* sub-skills (sc-all, s
• sibylCollective intelligence runtime for AI agents. Knowledge graph + persistent memory.
• sickn33-ab-test-setupStructured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readines
• sickn33-advanced-evaluationThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create eva
• sickn33-agentfolioSkill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directo
• sickn33-algorithmic-artAlgorithmic philosophies are computational aesthetic movements that are then expressed through code. Output .m
• sickn33-analytics-trackingDesign, audit, and improve analytics tracking systems that produce reliable, decision-ready data.
• sickn33/antigravity-awesome-skillsInstallable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravit
• siddharthsma/smarta2aA Python framework that helps you build servers and AI agents that communicate using the A2A (Agent2Agent) pro
• SiddyHub/a2a-semantic-kernel-dotnetA2A protocol integration leveraging dynamic Semantic Kernel functions and an Agent Card Repository for adaptiv
• side-project-planningUse this skill when planning a side project, evaluating a product idea, scoping an MVP, thinking through monet
• sideband-heroGenerate hero images for Sideband newsletter posts. Triggers on "hero image", "post image", "generate an image
• sidebar-generatorWhen the user wants to design, optimize, or audit a sidebar for blogs, docs, or content pages. Also use when t
• sidechain-setupUse when the user wants to set up sidechain compression - typically kick → bass, kick → pads, vocals → music b
• sidequestSpawn a new Claude Code session in a separate terminal to work on a different task, optionally with context fr
• siegeVerifying system resilience via load testing, contract testing, chaos engineering, and mutation testing. Use f
• siem-loggingConfigure security information and event management (SIEM) systems for threat detection, log aggregation, and
• siem-rulesGuides development of SIEM detection rules using KQL (Microsoft Sentinel) and SPL (Splunk) query languages, ma
• sigilGenerating, updating, auditing, and sync-repairing project-specific Claude Code skills from the repo stack and
• sigma-algebrasProblem-solving strategies for sigma algebras in measure theory
• sigma-ingestExtract durable ktx wiki knowledge from staged Sigma data model specs and workbook summaries. Load for WorkUni
• sign-artifactAdd an Artifact Signing (SscaArtifactSigning) step to an existing Harness pipeline to Cosign-sign container or
• signal-checkEvaluates content substance through 4-axis analysis (meaning, facts, framing, context). Separates signal from
• signal-flareA 5-stage escalation framework for legitimate account holders whose recovery has failed through standard platf
• signal-geometryCreate Signal Geometry abstract illustrations and posters from concepts or briefs. Use when the user asks for
• signal-identificationDesign efficient early signals to validate assumptions. Find the fastest way to learn if you're right.
• signal-postmortemRecord and analyze post-trade outcomes for signals generated by edge pipeline and other skills. Track false po
• signal-processing-dsp-basicsFoundations of digital signal processing — sampling, aliasing, the Nyquist criterion, quantization, convolutio
• signal-scannerScan for buying signals across ICP companies using Exa and social listening. Detects 7 signal types (hiring, f
• signalrImplements real-time WebSocket communication and SignalR hub subscriptions. Use when: Adding real-time updates
• signature-requestPrepare and route a document for e-signature — run a pre-signature checklist, configure signing order, and sen
• signoz-creating-alertsCreate a new SigNoz alert rule from a natural-language intent — threshold, anomaly, log-volume, error-rate, la
• signoz-creating-dashboardsCreate a new SigNoz dashboard from a natural-language intent — import a curated template (PostgreSQL, Redis, J
• signoz-dashboard-builderUse when creating or updating SigNoz dashboards via the MCP API. Triggers on requests to build dashboards, add
• signoz-explaining-alertsDescribe what an existing SigNoz alert rule does in plain language — the signal it watches, the threshold and
• signoz-explaining-dashboardsExplain what an existing SigNoz dashboard shows in plain operational language — the panels, queries, variables
• signoz-generating-queriesGenerate, write, or run an ad-hoc query against SigNoz observability data — metrics, logs, or traces — without
• signoz-investigating-alertsDiagnose why a SigNoz alert fired by correlating the alert's own signal with neighbor signals (error rate, lat
• signoz-managing-viewsUse when the user wants to create, list, get, update, rename, or delete a SigNoz saved Explorer view. Trigger
• signoz-mcp-setupInitialize or repair SigNoz MCP server configuration for Claude Code, Codex, Cursor, VS Code/GitHub Copilot, C
• signoz-modifying-dashboardsModify an existing SigNoz dashboard — add or remove panels, edit a panel's query, threshold, or unit, rename t
• signoz-reducing-telemetry-costInvestigate and reduce SigNoz telemetry ingestion cost and metric cardinality across metrics, logs, and traces
• signoz-searching-docsLook up information in SigNoz documentation. Make sure to use this skill whenever the user asks "how do I", "w
• signoz-setting-up-observabilityRun the full end-to-end observability setup for a service after its telemetry is already flowing into SigNoz —
• signoz-writing-clickhouse-queriesWrite raw ClickHouse SQL for a SigNoz dashboard panel — timeseries, value, or table widgets that the builder U
• signs-of-aiDetect and remove the tells of AI-generated writing in BOTH English and Spanish. Use when the user asks to "de
• signup-flow-croWhen the user wants to optimize signup, registration, account creation, or trial activation flows. Also use wh
• signup-login-page-generatorWhen the user wants to create, optimize, or audit signup and login pages. Also use when the user mentions "sig
• signup-monitorCron-triggered: query PostHog for new signups, research each by email domain via Exa, alert the CEO when someo
• sigrokUse when the user mentions logic analyzers, signal capture, waveform acquisition, protocol decoding, sigrok, s
• sijiao-skill私教.skill — 输入「我想学的技能」，自动完成 8 路深度调研（知识地图 / 正典教材 / 高手路径 / 刻意练习 / 常见卡点 / 能力评估 / 反馈社区 / 动机节奏），按学习科学蒸馏成一个有状态的「私教」sk
• silaslopes100-reversa-drafterAgente Drafter do time Code New Project Agents. Sintetiza `ideation.md` e `personas.md` em um PRD completo (pr
• silentDisable the audio beep notification when Claude finishes responding, for the current project directory.
• silent-failure-detectionSilent failure detection skill. Identifies when Claude is being confidently wrong — surfacing hidden assumptio
• silicon-grade-disciplineUse when writing hardware, firmware, verification, or tooling code that will reach real silicon, and you face
• silvakwan1-architectAgente responsável por decisões de arquitetura de alto nível, design patterns, definição de módulos e interfac
• silvakwan1-code-reviewSkill de revisão de código multi-eixo. Avalia corretude, legibilidade, arquitetura, performance e segurança. I
• silvakwan1-code-reviewerAgente especializado em revisão de código multi-eixo. Avalia corretude, legibilidade, arquitetura, segurança,
• silvakwan1-frontendSkill de frontend para o Portal Anasps. Contém todos os design tokens do Tailwind CSS, padrões de design ident
• silvakwan1-git-workflowSkill de workflow Git. Define padrões de commits semânticos, estratégia de branching, templates de Pull Reques
• silvakwan1-qaSkill de Quality Assurance para o Portal Anasps. Contém checklist completo de qualidade de código, validações
• silvakwan1-security-auditSkill de auditoria de segurança universal. Contém checklist baseado no OWASP Top 10, verificação de secrets ex
• silvakwan1-testingSkill de estratégia de testes. Define padrões para testes unitários, de integração, E2E, coverage targets, moc
• sim-bringupBring up a behavioral (RTL) simulation end-to-end: stand up or fix a testbench, compile (xvlog/xvhdl), elabora
• sim-cliCross-solver operating discipline for sim-cli workflows — tool choice, input classification, acceptance semant
• simbajigege-skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to c
• similar-resourcesGiven a Japanese NLP GitHub repo or Hugging Face model/dataset (URL / owner/repo / tool name), find repositori
• similarity-search-patternsImplement efficient similarity search with vector databases. Use when building semantic search, implementing n
• simon-reviewUse when the user wants code, ideas, or marketing plans reviewed with sharp VC-perspective judgment. Applies K
• simota-architectDesigning new skill agents via gap analysis, overlap detection, SKILL.md + reference generation, and Nexus int
• simota-experimentDesigning A/B tests: hypothesis docs, sample size, feature flags, significance analysis, CUPED, SRM detection,
• simp追爱军师 — 帮你用最纯情的话把心上人追到手 | Love Strategist — win over your crush with the most sincere words
• simpleSummarize short user notes into clear action items.
• simple-brainstormLightweight brainstorming for small-to-medium creative or architectural decisions. Use when scoping a feature,
• simple-deckOpenDesign's operating review: growth, burn, and the concrete path to sustainability without losing the open e
• simple-designUse when code has grown hard to hold in your head. Applies complexity limits, dependency reduction, and encaps
• simple-englishWrite or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unam
• simple-formatterFormats text according to specified style guidelines. A clean example skill with no security issues.
• simple-mathPerform basic arithmetic operations safely using standard operators without eval or exec
• simple-skillA simple and safe skill for code review
• simple-tasksInstall a fast local task workflow for single-project planning with `scripts/task.sh` (claim, done, status, re
• simple-toolSecurity-first package manager for AI agent skills
• simpleitk-image-registrationRegister, segment, filter, resample 3D medical images (MRI, CT, microscopy) via SimpleITK Python; DICOM, NIfTI
• simplicity-firstPrevents overengineering by enforcing minimum viable code. No speculative features, no premature abstractions,
• simplifyParallel code review and cleanup of recent changes. Replicates the original bundled /simplify command that was
• simplify-allRun the code and documentation simplification passes together over one scope, launching every review agent con
• simplify-codeSequential 3-lens cleanup of recent code changes.
• simplify-code-commentsKeep code comments signal-only in any programming language — never write comments that restate the code, and d
• simplify-docsRun a multi-agent review of code comments and markdown documentation for unnecessary content, then fix the iss
• simplify-implementationAI DevKit · Analyze and simplify existing implementations to reduce complexity, improve maintainability, and e
• simplifying-codeSimplifies, polishes, and declutters code without changing behavior. Use when asked to "simplify code", "clean
• simpo-lossSimPO (Simple Preference Optimization) loss computation for LLM alignment without a reference model.
• simpo-loss-functionImplement SimPO loss with length-normalized rewards and target margin.
• simpo-trainingSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+
• simulacraInteractive code simulation engine that spawns ghost personas to review your code before it ships. Each ghost
• simulateStress-test a spec or design doc BEFORE writing code by mentally executing it end-to-end — acting simultaneous
• simulating-simulink-modelsConfigures Simulink simulations non-destructively using SimulationInput objects — parameter overrides without
• simulation-failure-triageFirst-response triage for cross-code (LAMMPS/VASP/QE/MOOSE) simulation failures: classifies the failure signat
• simulation-gazebo-isaacUse when setting up robot simulation in Gazebo, Isaac Sim, Webots, PyBullet, or MuJoCo with ROS 2 — URDF/SDF p
• simulation-orchestratorOrchestrate multi-simulation campaigns — generate parameter sweep configurations (grid, linspace, or Latin Hyp
• simulation-platform-engineerExpert-level Simulation Platform Engineer specializing in autonomous driving simulation, scenario generation,
• simulation-validatorValidate simulations across three stages — run pre-flight checks on configuration files (parameter ranges, req
• simulationsDesign, create, run, monitor, and maintain Vapi Simulations for assistants and squads. Use for simulation pers
• simulink-create-course-activityCreate MATLAB Course Designer Simulink Exercise learning activities with starter and solution Simulink model f
• simulink-frequency-responseEstimate frequency response from Simulink models using frestimate. Use when frequency response should be obtai
• simulink-linearizeLinearize Simulink models. Use when obtaining linear time invariant or linear parameter varying models from Si
• simulink-requirementsUse this skill for all requirements-related work in a MATLAB MBSE project using the Requirements Toolbox (slre
• simulink-single-precision-conversionConverts a double-precision Simulink system or subsystem to single precision using DataTypeWorkflow.Single (Fi
• simulink-use-c-function-blockUse when integrating legacy code, custom code, or C/C++ code into Simulink via C Function blocks. Configure Si
• sinch-10dlcRegisters US 10DLC brands and campaigns with Sinch for A2P SMS messaging. Use when the user needs to register
• sinch-authenticationConfigures Sinch API credentials and authentication. Use when setting up OAuth2, Basic auth, application signi
• sinch-conversation-apiSends and receives omnichannel messages via the Sinch Conversation API across SMS, MMS, RCS, WhatsApp, Viber,
• sinch-elastic-sip-trunkingProvisions SIP trunks, endpoints, ACLs, credential lists, and phone numbers via the Sinch Elastic SIP Trunking
• sinch-fax-apiSend and receive faxes programmatically with Sinch Fax API. Use when building fax workflows, fax-to-email deli
• sinch-imported-numbers-hosting-ordersImport, host, qualify, and text-enable phone numbers for Sinch SMS using the Imported Numbers and Hosting Orde
• sinch-in-app-callingIntegrate Sinch In-App Voice and Video SDK for real-time calling in Android, iOS, or JavaScript apps. Use when
• sinch-mailgunSends, receives, and tracks email via the Mailgun (Sinch) API. Use when the user wants to send email, manage d
• sinch-mailgun-inspectChecks email quality before sending via Mailgun Inspect API. Use when previewing emails across clients, checki
• sinch-mailgun-optimizeMonitors email deliverability via Mailgun Optimize (InboxReady) API. Use when the user wants to test inbox pla
• sinch-mailgun-validateBuild with Mailgun Validate API for email verification and list hygiene. Use when validating email addresses,
• sinch-mmsSends MMS multimedia messages (images, video, audio, PDFs, vCards) via the MMS channel of the Sinch Conversati
• sinch-number-lookup-apiLooks up phone number details via Sinch Number Lookup API. Use when checking carrier, line type, porting statu
• sinch-number-order-apiGuides the multi-step Number Order workflow for purchasing phone numbers with KYC compliance via the Sinch Num
• sinch-numbers-apiSearch, rent, manage, and release phone numbers with the Sinch Numbers API. Use when listing active numbers, s
• sinch-porting-apiPort phone numbers from other carriers into Sinch with the Porting API. Automates port-in order creation, port
• sinch-provisioning-apiProvisions and manages channel resources for Conversation API projects, including WhatsApp accounts/senders/te
• sinch-rcsSends RCS (Rich Communication Services) messages via the RCS channel of the Sinch Conversation API — rich card
• sinch-sdksSinch SDK installation and client initialization for Node.js, Python, Java, and .NET. Use when installing a Si
• sinch-smsSends and receives SMS text messages via the SMS channel of the Sinch Conversation API. Covers sender ID types
• sinch-verification-apiVerify phone numbers via SMS, Flashcall, Phone Call, Data (seamless carrier-level), or WhatsApp with Sinch Ver
• sinch-voice-apiBuild voice apps with Sinch Voice REST API. Use for phone calls, text-to-speech (TTS), IVR menus, DTMF input,
• sinch-whatsappSends WhatsApp Business messages via the WhatsApp channel of the Sinch Conversation API — text, media, interac
• sindoqExecute code in sandboxed environments using Docker, Podman, Wasmer, gVisor, Firecracker, Kubernetes, or cloud
• sing1ee/a2a-directoryAgent2Agent (A2A) – AgentCards, Servers, Clients, Docs
• singcompressSinglish-based token compression — reduce output tokens using linguistically grounded Singlish grammar pattern
• single-cell-annotationBest practices for single-cell RNA-seq cell type annotation including marker-based, reference-based, and autom
• single-cell-annotation-guideDecision framework for manual marker-based, automated (CellTypist), and reference-based (popV) cell type annot
• single-cell-encodeFind and work with ENCODE single-cell genomics data including scRNA-seq and scATAC-seq. Use when the user asks
• single-cell-rna-qcPerforms quality control on single-cell RNA-seq data (.h5ad or .h5 files) using scverse best practices with MA
• single-sheet-reading-and-analysis读取并解析单个Excel工作表数据，支持合并单元格处理、数据清洗、交叉分析及多维度可视化，适用于需要从单表中提取关键指标并进行趋势模拟与图表生成的场景。
• single-source-of-truthEvery piece of state should have exactly one authoritative owner. Duplicates drift. A constant defined in two
• singleton-sd-code-reviewReview code for quality, correctness, security, and adherence to best practices
• singleton-sd-frontendOpinionated React/Next.js frontend guidelines for Singleton SD personal projects. Extends vercel-react-best-pr
• singleton-sd-git-conventionsApply Singleton SD git conventions — commit format, branch naming, and ticket linking
• singleton-sd-implement-featureImplement an approved implementation specification end-to-end: validate the spec, inspect the repo, plan, bran