All authors
Claude Skills by NeverSight
github.com/NeverSight3,203 skills96 installs8,182 views
- Workflow GateUse BEFORE loading heavier workflow skills (brainstorming, discuss-before-plan, writing-plans, subagent-driven-development, agentic-review-handoff, executing-plans, finishing-a-development-branch) when the route is not already obvious. A 60-90 second advisory classifier that prevents over-escalation and under-escalation. Outputs one Route, one single-token Runtime skill to load next, one optional Fallback alias for Claude/Codex compatibility, and one Execution path. Creative work (new feature...Votes: 0GitHub stars: 207
- Zustand Store ScaffoldScaffold class-based Zustand stores with flattenActions: web (component-level store + Context + Provider) and core (slice-based store with immer). Class-based actions provide Go-to-Definition DX, #private field encapsulation, and prototype-safe slice composition.Votes: 0GitHub stars: 207
- Adonisjs Docs WriterAdonisJS documentation writing style guide. Use when creating, editing, or reviewing AdonisJS documentation, tutorials, guides, or API references. Provides priority-ranked patterns for document structure, code examples, tone, warnings, and explanatory writing. Includes an interview workflow for gathering requirements when creating new documentation from scratch.Votes: 0GitHub stars: 207
- Expedia Stay SearchUse this skill when the user wants to search for hotels on Expedia by destination and dates, find available stays, check hotel pricing, or get a Hotel-Search URL. Triggers on "find a hotel", "search Expedia", "look up hotels in <city>", "book a stay", "hotel availability", or any request that implies Expedia stay search. Requires an authenticated Tabby browser session for the `expedia` profile; not usable as a generic hotel search tool for sites other than Expedia.Votes: 0GitHub stars: 207
- Noui Generate McpUse this skill when the user wants to start, stop, check, or list generated NoUI MCP servers, or connect a server to Claude Code. Triggers on "start the MCP server", "run noui mcp", "connect to Claude Code", "add to mcpServers", "noui mcp start", "noui mcp list", "noui mcp status", "how do I use the generated server", or "I want to call this tool from Claude".Votes: 0GitHub stars: 207
- Noui Record LoginUse this skill when the user wants to record a login flow for an authenticated app and register it with Tabby to get a tabby_profile_id. Triggers on "record a login", "capture a login flow", "register with Tabby", "set up authentication for NoUI", "create a tabby_profile_id", "noui login record", "login recording mode", or "I need auth for my workflow".Votes: 0GitHub stars: 207
- Noui Record WorkflowUse this skill when the user wants to record a browser workflow and export it as a FastMCP server, a Claude Code Skill, or both. Triggers on "record a workflow", "export as MCP", "export as skill", "generate a FastMCP server", "generate a Claude Code skill", "noui workflow record", "workflow export", "capture a workflow", "turn a workflow into a tool", "create an MCP server from a website", or "I want to automate this workflow". Covers authenticated (session-cookie via Tabby), static API-key,...Votes: 0GitHub stars: 207
- Noui SetupUse this skill when the user wants to set up the NoUI project for the first time, install dependencies, configure the environment, load the Chrome extension, or prepare to run any NoUI skill. Triggers on "set up NoUI", "install NoUI", "configure noui", "load the Chrome extension", "first time setup", "get NoUI running", or "I want to start using NoUI".Votes: 0GitHub stars: 207
- Analyzing Innovation PortfolioAnalyze innovation project workbooks and cost tracking data to surface portfolio-level insights, trends, and recommendations for where to focus innovation efforts.Votes: 0GitHub stars: 207
- Planning Innovation Cost And CapacityUse innovation cost tracking data and project list to estimate spend, capacity, and tradeoffs across innovation projects.Votes: 0GitHub stars: 207
- Structuring Innovation IntakeNormalize raw innovation ideas into structured backlog entries for an innovation workbook, using consistent Why/How/What, success metrics, and ownership fields.Votes: 0GitHub stars: 207
- Process DocumentationCreates clear, maintainable process documentation including standard operating procedures (SOPs), workflow diagrams, decision trees, and runbooks. Use when documenting business processes, creating training materials, or building operational playbooks.Votes: 0GitHub stars: 207
- Backend Refactor Quality GateQuality gate for Fintrack.Server backend refactors in CeroBase: verify domain encapsulation, CQRS folder layout, Result-based application messaging, FluentValidation, EF migrations, API consistency, and mandatory tests before marking work complete. Use whenever refactoring aggregates (e.g. Guid migrations), restructuring Application commands/queries, aligning a feature with an established pattern such as Budgets, or any multi-layer backend change where "quick fixes" would leave the codebase i...Votes: 0GitHub stars: 207
- Cqrs Command GeneratorGenerates CQRS Commands with Handlers, Validators, and Request DTOs following Clean Architecture patterns. Commands represent actions that modify state and return Result types for proper error handling.Votes: 0GitHub stars: 207
- Fluent ValidationGenerates FluentValidation validators for commands and queries. Includes common validation rules, custom validators, async validation, and integration with MediatR pipeline behaviors.Votes: 0GitHub stars: 207
- Cc Pr Review CiComprehensive TypeScript/React PR review. Outputs structured review.json consumed by a posting script that creates a GitHub Review with inline comments. Agent runs read-only; the workflow script holds write permissions.Votes: 0GitHub stars: 207
- Deep ThinkPuts Claude code into a different frame of mind for better resultsVotes: 0GitHub stars: 207
- Plan To TasksConvert project plans to JSONL format (issues + dependencies). Use when users ask "convert plan to jsonl", "create jsonl from plan", "export plan as json" or "convert plan to taks", "create tasks from plan", "export plan as tasks".Votes: 0GitHub stars: 207
- React Router Loader PerformanceReact Router v7 loader performance optimization techniques. Use when optimizing TTFB, eliminating waterfalls, consolidating database queries, or streaming secondary data in loaders. Triggers on "slow loaders", "optimize TTFB", "speed up React Router", "loader performance", or when loaders exceed 500ms response time.Votes: 0GitHub stars: 207
- Tdd IntegrationEnforce Test-Driven Development with strict Red-Green-Refactor cycle using integration tests. Auto-triggers when implementing new features or functionality. Trigger phrases include "implement", "add feature", "build", "create functionality", or any request to add new behavior. Does NOT trigger for bug fixes, documentation, or configuration changes.Votes: 0GitHub stars: 207
- Typescript PatternsBest practices for TypeScript types, interfaces, assertions, and type safety. Use when writing or reviewing TypeScript code.Votes: 0GitHub stars: 207
- VoiceStarts a voice conversation with the user via the agent-voice CLI. Use when the user invokes /voice. The user is not looking at the screen — they are listening and speaking. All agent output and input goes through voice until the conversation ends.Votes: 0GitHub stars: 207
- EvalsRun and create evals for testing agent behavior. Use when the user wants to create or run an eval.Votes: 0GitHub stars: 207
- Ie6 HacksInternet Explorer 6 CSS and JavaScript compatibility patterns reference. Use when identifying legacy browser-specific code for removal during codebase modernization, explaining unusual CSS patterns in legacy systems, or auditing stylesheets for deprecated workarounds.Votes: 0GitHub stars: 207
- Inspector OperationsNavigate and inspect 3Lens entities including meshes, materials, textures, and shaders. Use when examining specific entities, understanding dependencies, tracing cost attribution, or selecting entities by query.Votes: 0GitHub stars: 207
- Mount OperationsFramework mount development workflows for React, Vue, Angular, Svelte, and other frameworks. Use when creating framework-specific mount kits, integrating 3Lens with frameworks, or debugging mount kit issues.Votes: 0GitHub stars: 207
- Testing OperationsContract and regression testing workflows. Use when writing tests, validating contract compliance, or creating regression test suites.Votes: 0GitHub stars: 207
- RaycastBest practices and workflows for developing and modifying Raycast Extensions (React/Node). Use when the user asks to create, update, or troubleshoot a Raycast extension, whether it interfaces with external APIs (Notion, Spotify) or executes local scripts (AppleScript, Keyboard Maestro).Votes: 0GitHub stars: 207
- Suggest EpicsSuggest candidate epics from a Product Vision, current system state, active epics, and archived epics without creating files until the user accepts a specific suggestion. Use when the user wants to brainstorm, slice a vision, find Product Vision coverage gaps, or generate new epic options.Votes: 0GitHub stars: 207
- Suggest StoriesSuggest remaining candidate stories for one active epic by reading the epic plus existing stories and bugfixes, without creating files until the user accepts specific suggestions. Use after `validate-epic`, and any time while the epic is active, to plan or revisit the story set needed to fulfill an epic, find missing story coverage, or choose the next independently implementable value slices.Votes: 0GitHub stars: 207
- Validate Change PlanValidate one epic-scoped or standalone story or bugfix change plan before implementation. Use after `add-story` or `add-bugfix` to confirm or correct the selected artifact's `Ready` or `Blocked` state.Votes: 0GitHub stars: 207
- Frontend DesignFrontend design expert for polished, production-ready UIs with distinctive visual characteristics and micro-interactions. Use when improving visual design, adding CSS animations, or polishing the UI with shadows, gradients, and transitions. Rejects generic AI aesthetics in favor of bold, distinctive design choices.Votes: 0GitHub stars: 207
- League SdkBuild League of Legends apps using league-sdk TypeScript library. Use when working with Riot API, summoner/player lookups, match history, champion mastery, ranked stats, live game spectator, or building LoL Discord bots, websites, or apps.Votes: 0GitHub stars: 207
- Google CalendarInteract with Google Calendar via the Google Calendar API – list upcoming events, create new events, update or delete them. Use this skill when you need programmatic access to your calendar from OpenClaw.Votes: 0GitHub stars: 207
- Optimize For TokensAnalisa e refatora código para reduzir consumo de tokens em contextos de IA, dividindo arquivos grandes em módulos coesos e eliminando confusão de contexto. Use esta skill SEMPRE que o usuário mencionar: arquivos grandes demais, contexto confuso, token limit, refatorar para IA, dividir componentes, separar lógica de UI, extrair types, otimizar contexto para LLM, "arquivo com mais de 300 linhas", ou qualquer pedido de organização de codebase visando eficiência com IA. Acione também quando o us...Votes: 0GitHub stars: 207
- Delphi ClaudeignoreCria e mantem automaticamente o arquivo .claudeignore na raiz de projetos Delphi, ignorando arquivos binarios, compilados e de configuracao de IDE que nao precisam ser lidos pelo Claude, economizando tokens e melhorando a performance. Use esta skill SEMPRE que detectar arquivos .dpr, .dproj ou .pas em um projeto que ainda nao possui .claudeignore. Tambem use quando o usuario mencionar: ".claudeignore", "ignorar arquivos delphi", "economizar tokens", "arquivos desnecessarios", "otimizar contex...Votes: 0GitHub stars: 207
- Delphi SpecEspecialista em geracao automatica de documentos de especificacao de software (SPEC) a partir do codigo-fonte de projetos Delphi. Use esta skill SEMPRE que o usuario mencionar: SPEC, especificacao de software, specification document, documento de requisitos, "crie uma SPEC", "gere a SPEC", "documente o sistema", "especificacao do projeto", "especificacao do modulo", "quero a SPEC do codigo", "gerar especificacao", "analise o codigo e gere a SPEC". Tambem use ao detectar pedidos de documentaca...Votes: 0GitHub stars: 207
- Delphi StandardsEspecialista em padrões de codificação Delphi. Use esta skill SEMPRE que detectar: arquivos .pas, .dpr, .dfm, .dpk, .dproj, código Object Pascal, menções a Delphi, FireMonkey (FMX), VCL, FireDAC, RAD Studio, Embarcadero. Também ativa ao discutir nomenclatura, indentação, prefixos, classes, métodos, componentes ou formatação de código Delphi. Esta skill carrega o Delphi Style Guide completo como contexto ativo.Votes: 0GitHub stars: 207
- Context BudgetingDeliberately manages the context window to cut token cost and prevent quality decay on long runs. Use when a task is long-running, involves large files or many tool outputs, the context feels full, or cost matters. For finding external info efficiently use progressive-research; for surviving multi-session work use sustained-execution.Votes: 0GitHub stars: 207
- Guarding Code QualityKeeps agent-generated code correct, safe, and consistent with the codebase, match existing conventions, verify behavior with a real run/test, and self-review before claiming done. Use whenever writing or editing code. Calls verifying-reasoning to confirm a fix actually fixes, and reports honestly when checks fail.Votes: 0GitHub stars: 207
- Sustained ExecutionKeeps long, multi-session, or compaction-spanning tasks on track using an external task ledger, checkpoints, and resumable state. Use when work spans many steps/hours, may hit context limits, or must survive a reset. Pairs with decomposing-tasks (the plan), context-budgeting (the window), and operating-autonomously (unattended runs).Votes: 0GitHub stars: 207
- Specification ArchitectA rigorous, traceability-first system that generates five interconnected architectural documents (blueprint.md, requirements.md, design.md, tasks.md, and validation.md) with complete requirements-to-implementation traceability. Use this skill when users need to architect systems, create technical specifications, or develop structured project documentation with guaranteed traceability.Votes: 0GitHub stars: 207
- Punk Ip Article IllustrationsPunk 出品的完整个人 IP 插图工作流：从用户上传的人物照片创建、修订、确认并持久化可复用角色，也可直接启用内置 Punk 角色；角色确认后读取完整文章、Markdown、网页、帖子或观点，自动决定数量并生成复古彩色扁平 3D 小剧场正文插图。适用于创建个人 IP、角色设定板、切换角色、文章自动配图、长文多图、流程拆解图和核心动作图等连续任务。Votes: 0GitHub stars: 207
- Punk AvatarGenerate avatar images and reusable avatar image prompts from the shared Punk style library for people, pets, objects, profile pictures, pet portraits, and avatar-derived keepsake cards. Use this skill to identify the subject from image or text, choose one avatar-capable style, compile the selected style atom into the avatar blueprint, save the final prompt, and generate the image when an image-generation tool is available.Votes: 0GitHub stars: 207
- Punk CoverGenerate cover images and reusable image prompts from the shared Punk style library for articles, Xiaohongshu notes, WeChat public account posts, X posts, topic drafts, and requests for covers, social cover images, poster prompts, style-template-based image prompts, or image generation from long-form text. Use this skill to analyze source content, confirm platform/aspect ratio and visual style, save the final prompt, and generate the image when an image-generation tool is available.Votes: 0GitHub stars: 207
- Hyperresearch 1 DecomposeStep 1 of the hyperresearch V8 pipeline. Decomposes the canonical research query into atomic items, classifies pipeline_tier and response_format, and produces the coverage matrix that downstream steps depend on. The required_section_headings field this step produces is the single highest-leverage input for instruction-following scores. Invoked via Skill tool from the entry skill (hyperresearch).Votes: 0GitHub stars: 207
- Hyperresearch 10 Triple DraftStep 10 of the hyperresearch V8 pipeline. Orchestrator pre-curates 20-50 angle-specific source IDs per draft, then spawns 3 hyperresearch-draft- orchestrator subagents in parallel — each reads its curated list (no vault surveys, no source-fetching) and writes one angle-specific draft. This step ENDS when all 3 drafts are written and validated. Step 11 (synthesizer) handles the synthesis-write that produces the final report. For light tier: writes a single draft directly to final_report.md and...Votes: 0GitHub stars: 207
- Hyperresearch 11 SynthesizeStep 11 of the hyperresearch V8 pipeline. Reads the 3 angle-specific drafts from step 10, spot-checks factual conflicts, writes a synthesis plan + outline, then spawns ONE hyperresearch-synthesizer subagent (Read+Write tool-locked) that writes the final report in TWO passes — pass 1 rough integrated draft, pass 2 voice/redundancy/length cleanup. Skipped for light tier (which writes a single draft directly in step 10). Invoked via Skill tool from the entry skill (full tier).Votes: 0GitHub stars: 207
- Hyperresearch 13 Gap FetchStep 13 of the hyperresearch V8 pipeline. Conditional fetcher wave to fill vault gaps that critics identified. If a critic says "the draft ignored topic X" and the vault has zero sources on X, the patcher has nothing to cite. This step fetches the missing sources BEFORE patching so the patcher has ammunition. Capped at 5 gaps. Invoked via Skill tool from the entry skill (full tier).Votes: 0GitHub stars: 207
- Hyperresearch 14 PatcherStep 14 of the hyperresearch V8 pipeline. Spawns the hyperresearch-patcher subagent (TOOL-LOCKED to Read + Edit) to apply critic findings as surgical Edit hunks against the synthesized final report. Zero regeneration. Pre-stubs the patch log because Edit cannot create files. Handles orchestrator-escalated structural restructures inline. Invoked via Skill tool from the entry skill (full tier).Votes: 0GitHub stars: 207