Parcourir le registre

Toutes les entrées, par ordre alphabétique — 56 437 au total. Page 198 sur 226.

• solana-agent-kitComprehensive guide for building AI agents that interact with Solana blockchain using SendAI's Solana Agent Ki
• solana-best-practicesReviews Solana/Anchor programs for development best practices. Use when writing, reviewing, improving or audit
• solana-blinksBuild Solana Actions and Blinks for in-app transactions on X and other clients. Triggers on "Blinks", "Solana
• solana-compressLaunch ZK compressed tokens on Solana using Light Protocol for 99% cost reduction. Triggers on "compressed tok
• solana-cpi-safetyDetect and prevent Solana cross-program-invocation vulnerabilities — return-data spoofing, arbitrary CPI, stal
• solana-devUnified skill hub for Solana development. Routes to external submodule skills (solana-foundation, sendai, sola
• solana-developmentBuild, test, deploy, and audit Solana programs with Anchor or native Rust, and build with ZK Compression (Ligh
• solana-gameSolana game development with Unity, React Native, and web. Extends solana-dev-skill with gaming-specific patte
• solana-hackathonBootstrap a Solana hackathon project with current best practices and 2026 primitives. Triggers on "hackathon",
• solana-kitagent skills marketplace for mcp bundler(can be used with other ai tools with support of agent skills markepla
• solana-kit-migrationHelps developers understand when to use @solana/kit vs @solana/web3.js (v1), provides migration guidance, API
• solana-program-scaffoldScaffolds a Solana on-chain program with Anchor — workspace setup, PDA patterns, dual SOL/SPL token support, c
• solana-sdpBuild on the Solana Developer Platform (SDP) for enterprise payments, tokenization, and trading. Triggers on "
• solana-security-auditComprehensive Solana smart contract security auditor. Covers 50+ attack vectors across Anchor, native Rust, an
• solana-vulnerability-scannerScans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing
• solanabr-solana-devUnified skill hub for Solana development. Routes to external submodule skills (solana-foundation, sendai, sola
• sole-search🇰🇷 소상공인(운영 중인 가게·자영업자) 지원사업 조사 에이전트 스킬 [Claude Code·Codex·agy(Antigravity)·Cursor·Gemini CLI 지원] 소상공인24·기업마당
• solidSOLID principles for object-oriented design with multi-language examples (PHP, Java, Python, TypeScript, C++).
• solid-agents-project-scaffolderUse when creating a new SolidJS project, scaffolding a SolidStart application, or setting up project infrastru
• solid-agents-reviewUse when reviewing generated SolidJS code, validating a SolidJS project, or checking for React pattern contami
• solid-astroUse when applying SOLID principles to an Astro project — file-size limits, src/interfaces/ for types, JSDoc, m
• solid-core-overviewUse when starting a SolidJS project, checking API availability, or looking up import paths and version compati
• solid-core-reactivity-modelUse when reasoning about SolidJS reactivity, debugging tracking issues, or understanding why components run on
• solid-errors-error-handlingUse when implementing error boundaries, Suspense loading states, or error recovery in SolidJS components. Prev
• solid-errors-react-contaminationUse when reviewing SolidJS code for React anti-patterns or converting React components to SolidJS. Prevents de
• solid-errors-reactivity-debuggingUse when SolidJS reactivity is broken, effects are not firing, or store updates are not reflected in the UI. P
• solid-impl-routingUse when implementing client-side routing, navigation, or URL parameter handling in SolidJS applications. Prev
• solid-impl-solidstartUse when building SolidStart applications with SSR, file-based routing, or server functions. Prevents incorrec
• solid-impl-state-patternsUse when designing state architecture or choosing between signals, stores, and context in SolidJS. Prevents us
• solid-impl-testingUse when writing unit or integration tests for SolidJS components, signals, or stores. Prevents missing cleanu
• solid-js-expertDesign, build, debug, and review SolidJS and SolidStart applications. Use for Solid reactivity, signals, store
• solid-nextjsUse when applying SOLID principles to Next.js architecture — modular structure, file size limits, interface se
• solid-phpUse when applying SOLID principles to Laravel 13 / PHP 8.3+ code — file size limits, interface placement, or P
• solid-principlesApply the SOLID principles as design diagnostics when writing, reviewing, or refactoring code with classes, mo
• solid-reviewAudit any C#, TypeScript, or Angular code against the five SOLID principles and Clean Architecture layering ru
• solid-skillGenerate release notes from git history between two refs. Use when the user says "write release notes", "summa
• solid-syntax-componentsUse when creating components, handling props, working with children, refs, directives, or events in SolidJS. P
• solid-syntax-contextUse when sharing state between components, creating providers, or implementing dependency injection in SolidJS
• solid-syntax-jsxUse when writing JSX templates, rendering lists, conditional rendering, or using control flow components in So
• solid-syntax-signalsUse when creating signals, effects, memos, resources, or managing component lifecycle in SolidJS. Prevents Rea
• solid-syntax-storesUse when managing complex nested state, updating objects or arrays, or choosing between signals and stores in
• solidifierApply SOLID principles and design patterns to backend code with judgment and restraint. Use this skill wheneve
• solidity-auditSecurity audit and code review checklist. Covers 30+ vulnerability types with real-world exploit cases (2021-2
• solidity-auditorProfessional-grade Solidity smart contract security auditor. Performs comprehensive audits or targeted reviews
• solidity-coding[AUTO-INVOKE] MUST be invoked BEFORE writing or modifying any Solidity contract (.sol files). Covers pragma ve
• solidity-debug[AUTO-INVOKE] MUST be invoked when debugging failed on-chain transactions. Covers transaction receipt analysis
• solidity-defiDeFi プロトコル開発スキル。AMM・流動性プール、レンディング、 価格オラクル、Vault（ERC4626）の設計パターンを提供する。 ユーザーが "DeFi", "AMM", "DEX", "レンディング", "V
• solidity-deploy[AUTO-INVOKE] MUST be invoked BEFORE deploying contracts or writing deployment scripts (*.s.sol). Covers pre-f
• solidity-security[AUTO-INVOKE] MUST be invoked BEFORE writing or modifying any Solidity contract (.sol files). Covers private k
• solidity-security-auditComprehensive Solidity smart contract security auditing and vulnerability analysis skill. Based on methodologi
• solidity-testing[AUTO-INVOKE] MUST be invoked BEFORE writing or modifying any test files (*.t.sol). Covers test structure, nam
• solidjs-v2Answer SolidJS 2.0 API and beta-behavior questions, and write or edit SolidJS 2.0 code (solid-js 2.x / next /
• solidjs-v2-migrationMigrate a Solid 1.x codebase, file, or component to SolidJS 2.0 (solid-js 2.x / next / beta). Use when convert
• solidjs-v2-reviewerReview SolidJS 2.0 code for React-isms, Solid 1.x-isms, and reactivity bugs. Use when reviewing diffs, PRs, or
• solidstart-request-eventsSolidStart request events: getRequestEvent for server context, event.locals for typed data, nativeEvent for Vi
• solidworks-draw用自然语言驱动 SolidWorks 进行参数化机械零件建模。支持轴类、盘类、活塞等常见零件，内置工程设计规则和材料数据库。可从已有 SW 文件学习设计知识。使用 "画一个..." 或 "帮我建模..." 触发。
• solo-analyzeEvaluate a startup idea against real patterns from 101 founder interviews
• solo-failuresUnderstand why startups fail — the most common failure modes, anti-patterns, and how to avoid them, backed by
• solo-founder-gtmWhen the user is a solo founder building their GTM motion, wants to scale without hiring, or needs to design a
• solo-growthGet data-backed growth and marketing recommendations for your business
• solo-operator运用《单干》(陈欢) 的 49 个关键动作方法论,指导一人公司与超级个体的商业决策。适用于用户想把专业能力变现(定价/产品化/知识付费)、设计个人品牌定位与内容策略、评估要不要辞职单干或开启副业、以及单干路上纠结方向选择
• solo-patternsBrowse and search the startup pattern database (11 categories, 80+ patterns)
• solo-playbookGet a data-backed step-by-step playbook for any startup goal
• solo-roastGet your startup plan roasted with data — Garry Tan style
• solr-extendingTo build Solr plugins: SearchComponent, QParser, URP, DocTransformer.
• solr-queryTo build and debug Solr queries: eDisMax, block join, JSON facets, kNN, explain.
• solr-schemaTo design and audit Solr schemas: field types, analyzers, docValues, solrconfig.
• solr-semantic-searchTo build Solr phrase-tagging semantic search: concept tagging, taxonomy, graph paths.
• solublempnnSolubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli
• solutionUse when the user wants to write system architecture at docs/architecture/solution.md (stub or full arc42-lite
• solution-architect解决方案架构师助手。当用户要设计新系统架构、评审现有架构、做技术选型决策、诊断性能/可扩展性/可用性问题、规划架构演进或重构时使用。覆盖微服务、事件驱动、云原生等架构模式，技术趋势通过实时搜索获取而非依赖内置知识。不用于
• solution-designExplores ambiguous product or engineering intent before implementation, clarifies users, constraints, alternat
• solutions-page-generatorWhen the user wants to create, optimize, or audit solutions pages. Also use when the user mentions "solutions,
• solveSolve competitive programming and LeetCode-style problems with educational explanations. Use when asked to "so
• solve-challengeSolves CTF challenges by performing first-pass triage, identifying the dominant category, and routing executio
• solve-issuePick a GitHub issue, classify its domain, delegate to the right specialist, run quality gates, and create a PR
• somatic-pipelines-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• sonarqube-checkSonarQube quality gate, any language, no company server needed: run SonarQube Community Build locally (Docker)
• sonarrThis skill should be used when managing TV shows in Sonarr. Use when the user asks to "add a TV show", "search
• songseeGenerate spectrograms and feature-panel visualizations from audio with the songsee CLI.
• songwriting-and-ai-musicSongwriting craft and Suno AI music prompts.
• sonic-brandingBuild a complete audio identity for your brand using the 7-step methodology—from brand assessment through depl
• sonoscliControl Sonos speakers (discover/status/play/volume/group).
• soonjune-new-skillScaffold a new skill in this skills repository — copies the template, enforces Agent Skills spec conventions,
• sooperset/mcp-atlassianMCP server for Atlassian tools (Confluence, Jira)
• soothsayVerify agent instruction files against the actual repository. Use when the user says "check my agent docs", "i
• sop-authoring-assistantTurn rough notes on how a task is done into a clean, repeatable Standard Operating Procedure. Flags any step w
• sop-builderProduction-ready entrepreneurship skills for Claude Code — marketing, sales, operations, finance, and leadersh
• sop-designUse when starting a new feature or project, need to establish a spec→plan→task→code workflow, want AI to follo
• sop-writerTurn a messy process description into a clean Standard Operating Procedure (SOP) or playbook with numbered ste
• sop-writer-thSOP step-by-step + เงื่อนไข | สำหรับ HR ธุรการ หรือผู้จัดการที่ต้อง. Triggers when user says (Thai/EN): 'SOP',
• sopimuksen-laatiminenSopimuksen laatiminen Suomen oikeuden mukaan: rakenne, keskeiset lausekkeet ja sopimusoikeuden perusteet. Käyt
• sopimuksen-tarkistusSopimuksen lausekekohtainen riskiarvio Suomen oikeuden mukaan ja luokittelu (VIHREÄ / KELTAINEN / PUNAINEN). K
• soraUse when the user asks to generate, edit, extend, poll, list, download, or delete Sora videos, create reusable
• sora2Sora2 内容创作与作品分析 skill，通过 MaxHub API 查询作品、用户、评论、回复、二创/Remix、下载/媒体信息，并支持上传图片、创建视频等创作相关写操作。适合 AI 视频创作工作流、作品复盘、二创传
• soskill🔍 SoSkill - 开源 Skill 搜索与聚合 | Open-source Skill Search & Aggregation
• sotaMaster router for the SOTA engineering skills library. Use this skill whenever the user asks to build, design,
• sota-api-designState-of-the-art API design and audit guidance (2026) covering REST/HTTP, GraphQL, gRPC, WebSockets/SSE/realti
• sota-architectureState-of-the-art software and system architecture rules (2026) for both building and auditing. Use when design
• sota-async-concurrencyState-of-the-art rules for writing and auditing asynchronous and concurrent code across runtimes (Python async
• sota-c-cppState-of-the-art C and C++ engineering rules (2026 baseline) that Claude applies when writing or auditing C/C+
• sota-cli-uxState-of-the-art CLI and developer-tool UX guidance (2026) covering command and flag design, output and intera
• sota-cloud-infrastructureState-of-the-art cloud infrastructure architecture (2026). Applies when designing, building, or auditing cloud
• sota-code-securityState-of-the-art secure coding and security auditing rules (2026 baseline). Use whenever BUILDING or modifying
• sota-confidential-computingState-of-the-art confidential computing and cryptographic PETs (2026) for BUILDING and AUDITING systems that p
• sota-copywritingState-of-the-art marketing copywriting and content guidance (2026) covering positioning and value propositions
• sota-data-engineeringState-of-the-art data engineering rules (2026) for building and auditing data pipelines and analytics infrastr
• sota-databasesState-of-the-art database engineering rules (2026) for designing, building, and auditing data layers. Covers e
• sota-detection-engineeringState-of-the-art detection engineering, SOC, threat hunting, and incident response (2026). Use when BUILDING d
• sota-devsecopsState-of-the-art DevSecOps and software supply chain security (2026). Applies when building or auditing CI/CD
• sota-docs-workflowState-of-the-art documentation and engineering-collaboration guidance (2026) covering documentation architectu
• sota-dotnetState-of-the-art C# / .NET engineering rules (2026 baseline, .NET 10 LTS / C# 14) that Claude applies when wri
• sota-frontend-designState-of-the-art web design, UI/UX, and motion engineering standards (2026). Use when building OR auditing/rev
• sota-golangState-of-the-art Go engineering rules (2026 baseline, Go 1.25+) that Claude applies when writing new Go code o
• sota-identity-accessState-of-the-art identity and access management engineering (2026) for BUILDING/configuring identity infrastru
• sota-javascript-typescriptState-of-the-art JavaScript and TypeScript engineering (2026) for both writing and auditing code. Covers stric
• sota-jvmState-of-the-art JVM engineering rules (2026 baseline) for Java and Kotlin that Claude applies when writing or
• sota-kubernetesState-of-the-art Kubernetes platform security and operations (2026) for cloud-managed (EKS/GKE/AKS) and self-h
• sota-llm-engineeringState-of-the-art LLM application engineering rules (mid-2026 baseline) for BUILDING and AUDITING LLM-powered f
• sota-ml-engineeringState-of-the-art ML engineering / MLOps rules (2026) for BUILDING and AUDITING production machine-learning sys
• sota-mobileState-of-the-art mobile engineering for building and auditing iOS and Android applications. Use when the task
• sota-network-securityState-of-the-art network security as a discipline (2026) for BOTH designing/building secure networks AND audit
• sota-observabilityState-of-the-art observability and reliability engineering (2026). Use when instrumenting code (structured log
• sota-performanceState-of-the-art performance engineering for building fast systems and auditing existing code for bottlenecks.
• sota-phpState-of-the-art PHP engineering (2026 baseline, PHP 8.3+ floor, 8.5 current) for both writing new PHP and aud
• sota-privacy-complianceState-of-the-art privacy and compliance engineering guidance for building privacy-respecting systems and audit
• sota-pythonState-of-the-art Python engineering (2026 baseline) for both writing new Python and auditing existing Python c
• sota-rubyState-of-the-art Ruby engineering rules (2026 baseline, Ruby 3.4+ / 4.0) that Claude applies when writing or a
• sota-rustState-of-the-art Rust engineering (2026) for writing and auditing Rust code. Covers idiomatic ownership and AP
• sota-sandboxingState-of-the-art sandboxing and isolation engineering (2026). Use when designing isolation for untrusted code,
• sota-secrets-managementState-of-the-art secrets management for building and auditing software. Use whenever a task involves creating,
• sota-security-complianceState-of-the-art security & compliance engineering (2026) for the cybersecurity control frameworks and product
• sota-shell-scriptingState-of-the-art shell scripting (bash-focused, defensive) for writing and auditing shell scripts, CI scripts,
• sota-testingState-of-the-art software testing strategy and practice (2026) for designing test strategy, writing unit/integ
• sota-threat-modelingState-of-the-art threat modeling for both designing new systems and auditing existing ones. Use when designing
• sota-ux-writingState-of-the-art UX writing and product-copy guidance (2026) covering voice and tone systems, plain language (
• sota-web-frameworksState-of-the-art engineering rules (2026) for the JavaScript SSR meta-frameworks: React 19 + Next.js (App Rout
• soulEmbody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, v
• soul-graderUse when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide rese
• sound-design-filmApply Walter Murch's legendary film sound principles to marketing video, creating emotionally resonant audio t
• sound-designerUse when the user wants to design a synth patch from scratch or modify an existing one - lead, bass, pad, pluc
• sounding-board第三视角谈话型思考导师 - 当你带着一团模糊的困惑（工作/生活/学习/情感/某个想法）想理清时启动。它不急着帮你解决，而是先陪你把『真正的问题』讨论出来，再以苏格拉底式诘问抽丝剥茧，并把每次对话沉淀为可追溯、会演化的结构
• sourav15mukherjee-accessibility-auditorScan web application code for WCAG 2.1 accessibility violations. Use when the user asks to check accessibility
• sourav15mukherjee-code-reviewerReview code for bugs, security issues, performance problems, and best practice violations. Use when the user a
• sourav15mukherjee-prompt-engineerHelp users craft optimized AI prompts. Use when the user asks to write a prompt, improve a prompt, create a sy
• source-code-audit当拿到源码、代码片段、反编译产物，或用户要求代码审计时调用。负责输入点→传播链→危险函数Sink的静态审计，跨语言（PHP/Java/Python/Node/Go）危险函数速查，输出可疑调用链与缺陷触发条件。
• source-code-inspectionInvestigate application or repository source code with search_file and read_file to explain behavior, trace ro
• source-codingProblem-solving strategies for source coding in information theory
• source-drivenImplement features using official docs for exact dependency versions instead of training data. Use when user a
• source-driven-developmentGrounds every implementation decision in official documentation. Use when you want authoritative, source-cited
• source-evaluatorA curated open-source library of reusable SKILL.md files for Claude. Learn, use, and build powerful AI skills
• source-groundedGround framework- and library-specific code in official documentation, not training data. Detect the installed
• source-grounded-decisionsUse before a version- or spec-sensitive decision — framework or library code, a CLI flag, a config schema fiel
• source-groundingVerify version-sensitive facts against live authoritative sources before asserting them in code or answers. Tr
• source-ingestFetch and normalize supported source-tutorial inputs into local, traceable text artifacts. **Trigger**: source
• source-leakSource code leak detection via GitHub, Gitee, and search engine dorking. Uses tech stack fingerprints to const
• source-manifestBuild or validate the source manifest for the source-tutorial pipeline from user-provided URLs/files. **Trigge
• source-of-truthCreate epistemically honest Source of Truth documents that pass Clarity Gate verification. Use when consolidat
• source-part-segmentationSegment overlapping visual parts from source images, wireframes, texture atlases, and decals before mesh recon
• source-postLoad when turning an external article, blog, release note, interview, or report into a source-backed public po
• source-researchUse when the user wants research, source gathering, current-information lookups, cross-source synthesis, or ex
• source-reviewerReviews public source notes and produces a bounded summary.
• source-snapshotPlaybook for getting external data into the repo deterministically — fetch a web page, doc, or API/registry re
• source-tutorial-specUse when a `source-tutorial` workspace has ingested sources and needs a grounded tutorial contract before stru
• source-tutorial-writerUse when approved tutorial context packs exist and the run needs the final article-first tutorial deliverable.
• source-verification验证信源可信度的研究过程知识，指导 agent 在涉及事实声明时交叉核验信源
• sourcecode-analyzerMulti-agent deep source code analysis for architecture, coding style, design patterns, languages, frameworks,
• sourcesSources — add, edit, or remove streams and genres
• sourcing-conversation-trackerTracks every outbound sourcing conversation from email — who has been reached out to, who has responded, who i
• sourmash-signature-compare-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• sous-chefDinner-planning agent. Plans a short run of dinners (default 3) that fit the household's preferences, never re
• southwestSearch Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or
• soutien-academiqueAccompagne les étudiants (lycée, IUT, BUT, licence, master) dans la rédaction académique et le soutien scolair
• sow-pws-builderBuild Statements of Work (SOW) or Performance Work Statements (PWS) for federal contracts through a structured
• sow-reviewUse when reviewing a statement of work or work order to assess scope clarity, deliverables, acceptance criteri
• sox-testingGenerate SOX sample selections, testing workpapers, and control assessments. Use when planning quarterly or an
• soybeanjs/soybean-uiA powerful and elegant Vue 3 component system with headless primitives and ready-to-use styled wrappers.
• sozialauswahlDurchführung und Angriff der Sozialauswahl bei betriebsbedingter Kündigung nach § 1 Abs. 3 KSchG – Bildung der
• sp-apifetchHandle frontend-to-backend API communication with JWT authentication, error handling, and JSON parsing followi
• spa-routesLobeHub SPA route architecture. Use when editing src/routes, src/features delegation, desktop/mobile/popup rou
• space-environment-screeningScreen broadly shareable space-instrument concepts against orbit environment, thermal loading, radiation, cont
• space-funding-routerFind, compare, and route space-project funding opportunities across Horizon Europe, NASA NSPIRES/ROSES, ESA OS
• space-mission-plannerExpert-level Space Mission Planner specializing in orbital mechanics (Hohmann transfers, gravity assists, delt
• space-telescope-conceptDevelop broadly shareable space-telescope concept studies for AAO, including first-order optical prescriptions
• space.0/space0Give an AI agent a body in a Zero 3D voxel world: perceive, move, build, chat, remember.
• space.agentmemory/agentmemory-mcpPaid remote MCP for persistent AI agent memory, analytics, checkout, and search-readiness.
• space.customjs/customjs-mcpHost static HTML pages, generate PDFs, screenshots, scrape JS sites, run sandboxed JavaScript.
• space.mcploadbudgeter/mcploadbudgeter-mcpPaid remote MCP for context budgets, progressive loading, schema slimming, and readiness.
• space.promptguardscan/promptguardscan-mcpPaid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
• space.rally/mcp-serverTools for Go-to-market teams creating sales materials, product demos, and deal rooms for customers.
• space.servercardtrust/servercardtrust-mcpPaid remote MCP for server-card validation, auth checks, trust packets, and readiness.
• space.steady/steadyKeep teams & agents coordinated automatically
• space.studiosphere/pulsePrivacy-first audio intelligence: BPM, key, waveform. Audio never stored. Pay per second.
• space.syntheticuserlab/syntheticuserlab-mcpPaid remote MCP for synthetic user testing, UX validation, analytics, checkout, and readiness.
• spacing-systemCreate a spacing scale from a base unit with rules for when each step applies. Use when standardising padding
• spaciousGenerous whitespace, consistent padding, and grid-based layouts for clean, readable, and breathing interfaces.
• spacyspaCy NLP library with pipelines. Use for text processing.
• spanner-dataUse these skills when you need to explore the database structure, discover schema objects like tables and grap
• spar-actUse after the user has approved implementation. Execute the active plan sequentially, follow the plan's approa
• spar-initAfter install or on demand, complete the repo-local spar-kit setup by checking version freshness, AGENTS.md, .
• spar-planUse after the initial spec exists and the user is ready to turn it into an implementation plan. Complete the s
• spar-retainUse after implementation when the user approves closeout. Reconcile the active spec and plan with what shipped
• spar-specifyUse this skill when the user wants to define a new feature, bug fix, or significant change before planning or
• sparc-methodologySPARC (Specification, Pseudocode, Architecture, Refinement, Completion) development methodology with multi-age
• sparc-pipelineUse when you need to run the full 5-phase SPARC methodology (Specification→Pseudocode→Architecture→Refinement→
• sparc-specUse when you need to run SPARC Phase 1 (Specification) for a feature — produces phase_1_<slug>.md with Functio
• sparkApache Spark distributed computing. Use for big data processing.
• spark-engineerUse when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark ap
• spark-environment-setupSet up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when inst
• spark-memory-thermal-opsManage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory h
• spark-optimizationOptimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when impro
• spark-training-gotchasPreflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training ru
• sparringUse when the user says "sparring", "run sparring with Claude", "do sparring with Claude", "do sparring with GP
• sparring-partnerThis skill should be used whenever the user wants to develop, refine, or stress-test an idea, plan, design, re
• sparse-autoencoder-trainingProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural netw
• spartan-warriorEmbody the unbreakable Spartan ethos of discipline, courage, and relentless excellence through laconic wisdom
• spatial-interpolation-and-uncertainty-starterA framework for discovering, compiling, and validating reusable skills for scientific agents.
• spatial-join-sanityUse when performing a spatial join or location-based filter between two layers — joining attributes by locatio
• spatial-luminous-designSpatial depth systems, luminosity techniques, glassmorphism tiers, material surface reference (glass, metal, p
• spatial-thinkingUse when animation involves depth, perspective, volume, or three-dimensional awareness—camera moves, character
• spatial-transcriptomicsWorkflow for spatial transcriptomics preprocessing, domain detection, deconvolution, neighborhood analysis, an
• spawning-reviewersUse when dispatching one or more reviewer agents for an adversarial second opinion on any artifact — code, a d
• spdd-abstraction-firstUse during SPDD design review before generation to validate entities, responsibilities, interfaces, boundaries
• spdd-alignmentUse before SPDD analysis or implementation to lock business intent, domain language, scope boundaries, accepta
• spdd-analysisUse after SPDD alignment to analyze requirements against relevant code, domain concepts, risks, gaps, strategy
• spdd-api-testUse in SPDD when API or system-boundary behavior must be verified with executable scenarios covering normal, b
• spdd-generateUse when implementing code from an approved SPDD REASONS Canvas, following Operations in order and staying ins
• spdd-iterative-reviewUse after SPDD-generated changes to review behavior, prompt/code consistency, architecture boundaries, code qu
• spdd-prompt-updateUse in SPDD when requirements, behavior, acceptance criteria, business rules, or safeguards change; update the
• spdd-reasons-canvasUse to create or review a Structured-Prompt-Driven Development REASONS Canvas before code generation: Requirem
• spdd-storyUse when a large SPDD requirement needs to be split into independent, deliverable user stories before analysis
• spdd-syncUse after behavior-preserving refactors or implementation cleanup in SPDD to synchronize the REASONS Canvas ba
• speakUse when the user invokes /speak to hear the last response as natural spoken audio via TTS
• speak-human把满是专业术语、看不懂的内容重新讲成大白话 —— 一句话结论 + 生活化类比 + ASCII 图 + 落回原事 + 术语对照表，只换说法不换意思。用于用户说「说人话」「讲人话」「听不懂」「太专业了」「用大白话解释」「能不
• speak-human-tw「說人話」：繁體中文的去 AI 味改寫 skill。審查與改寫文字，去除 AI 味道、校正中國用語與半形標點，讓文字讀起來像真人寫的。 觸發時機：用戶說「去 AI 味」「說人話」「這段好 AI」「改自然一點」「幫我潤稿去
• speakeasy-contextSpeakeasy workflow: run 'agent context' FIRST, do task, run 'agent feedback' LAST. Triggers on speakeasy, SDK,
• specOpt into deliberate spec-first planning for the current change-unit. Dispatches the `spec` agent in interactiv
• spec-app-reviewReview an application-type spec for completeness against UI rendering requirements and golden-path structure.
• spec-approachAdd a refined `## Approach` section to an existing feature spec.md before TDD executes it. Reads the spec, exp
• spec-author49 production-grade AI agent skills (SKILL.md) for Claude Code, Codex & Antigravity — system design, DevOps, s
• spec-brainstormConversational design workshop for substantial work. Interviews the human one question at a time, explores 2-3
• spec-breakdownTurns an approved spec into ordered, independently mergeable implementation issues, and drafts the capability
• spec-compliance-validator驗證規格檔案的完整性與一致性，確保所有必要的規格元素都已定義且符合標準格式。
• spec-convergeIteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adve
• spec-correctnessTurn classified acceptance criteria into runnable property tests. Consumes
• spec-creationSpec creation with pattern references, acceptance criteria, and demo scripts. Use when creating implementation
• spec-debate让 Claude 与 Codex 对一份 spec 文档做匿名对抗辩论，由独立第三方裁判合成终稿。当用户想"辩论这份 spec"、"对抗评审 spec"、"让 Claude 和 Codex 辩论文档"、或输入 /spec
• spec-dependency-analysisAnalyze dependencies and separate enablement from feature work.
• spec-drivenPlanning and implementation with 4 adaptive phases — Specify, Design, Tasks, Execute. Auto-sizes depth by comp
• spec-driven-developAutomates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migra