Skills worth trusting.
Agent skills from Anthropic, OpenAI, skills.sh, ClawHub, SkillsMP and other reputable sources. Savant assesses them for security risks and evaluates model-generated test cases using independent scoring. Workspaces import any skill into their own repositories through a reviewed pull request. Every listing on each hub is enumerated; packages are fetched, scanned and evaluated most-popular first as daily capacity allows.
working-backwards
Use when asked to "working backwards", "PR/FAQ", "Amazon PR/FAQ", "write a press release", "define a new product", or "write a customer-focused PRD". Helps define products by starting with the customer problem and desired outcome before building. The Working Backwards process (developed at Amazon) forces clarity on customer value before committing engineering resources.
bmad-gds
AI-driven Game Development Studio (BMAD-GDS). Routes game projects through Pre-production, Design, Architecture, Production, and Game Testing phases using 6 specialized agents. Supports Unity, Unreal Engine, Godot, and custom engines.
six-pager
Generate decision memos and product launch documents in Amazon's narrative style. Two modes: `memo` produces a 6-page narrative memo (Introduction, Goals, Tenets, State of Business, Lessons Learned, Strategic Priorities + unlimited appendix); `prfaq` produces a Press Release + External FAQ + Internal FAQ for product launches (work backwards from launch). Enforces Strunk's prose rules (active voice, concrete language, omit needless words, no qualifiers, parallel construction, topic-sentence paragraphs, no overstatement) and Anthropic's removability discipline at the line level. Use when: 'six pager', '6-pager', 'amazon memo', 'narrative memo', 'PRFAQ', 'press release', 'work backwards', 'decision memo', 'strategy doc', 'launch document', 'silent read doc', before any decision big enough to warrant the week-long writing process.
adc-dac-baremetal
Bare-metal ADC and DAC skill. Use when configuring analog sampling, DMA-driven ADC, calibration, or DAC output on MCUs. Activates on queries about ADC bare-metal, sampling time, DMA ADC, or DAC channel setup.
send-message
Send messages via SMS, WhatsApp, Email, Telegram, Instagram, Messenger, or Voice with channel selection logic.
vpe-review
/c-level-agents:vpe-review [plan] — Throughput-first VP of Engineering interrogation of any plan that touches delivery, eng hiring, team structure, or production discipline. Use when cycle time balloons, DORA metrics slide, or before committing to an eng hiring wave or a reorg.
tutorial-engineer
Creates step-by-step tutorials and educational content from code. Transforms complex concepts into progressive learning experiences with hands-on examples.
godot-composition-apps
Expert architectural standards for scalable Godot Apps, Tools, EditorPlugins, and Control-heavy UIs using Composition (Has-A Orchestrator + components). Use when building dashboards, tool windows, forms, settings panels, or EditorPlugin UIs. Do NOT use for gameplay entities (Player/Enemy/Weapon/Hitbox) — route those to godot-composition. Trigger keywords: Control, EditorPlugin, tool UI, Orchestrator, VLS, rock test, AuthComponent, ThemeManager, Saveable component, dependency injection.
syncfusion-blazor-appbar
Guide for implementing Syncfusion Blazor AppBar component (SfAppBar) in Blazor applications. Use this when implementing navigation bars, app bars, or header toolbars with action controls. This skill covers AppBar configuration, size modes (regular, prominent, dense), color modes, positioning (top, bottom, sticky), menu integration, and responsive design patterns.
uv-project-management
Python project setup, deps, and lockfiles with uv. Use when the user mentions uv, creating Python projects, managing dependencies, lockfiles, or pyproject.toml.
bitrix-console-commands
Bitrix CLI bitrix.php — make:* generators (module, controller, tablet, service, event, message, agent), orm:annotate, messenger:consume, own Symfony Console commands in module .settings.php. Use when scaffolding code or writing CLI/cron jobs.
coding-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
kicad-footprint
Generate compliant KiCad footprints from official KiCad Library Tools
bmad-sprint-status
Deprecated — forwards to bmad-sprint-planning (status view)
bee-security
lighting-environment
Lights and sky in Decentraland scenes - LightSource point and spot lights, shadows and gobos, a light that does not show, light budgets on desktop and mobile, SkyboxTime and day/night cycles, fixtures that glow and cast light. For emissive, metallic, roughness or transparent materials see advanced-rendering.
n8n:create-pr
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when the user says /pr or asks to create a pull request.
wasp-plugin-help
Shows the Wasp plugin's available features, commands, and skills.
pillar-content-architecture
How to design a content hub that earns topical authority. Pillar topic selection, cluster planning, internal linking architecture, URL structure, pillar and cluster page anatomy, topical authority signals for SEO and AEO/GEO, and the maintenance discipline that distinguishes intentional hubs from accidental orphans. Triggers on pillar content, content hub, topic cluster, topical authority, content architecture, hub and spoke, pillar page, cluster page, content silo, internal linking strategy. Also triggers when a content set is not ranking despite individual piece quality, when a pillar was launched without a cluster, or when content has accumulated without an architecture.
vertical-slice-architecture
Enforce Vertical Slice Architecture (VSA) when building applications in any language (Go, .NET/C#, Java, Kotlin, TypeScript, Python, etc.) and any type (web API, mobile backend, CLI, event-driven). Organize code by feature/use-case instead of technical layers. Each feature is a self-contained vertical slice with a single entry point that receives the router/framework handle and its dependencies. Use when the user says "vertical slice architecture", "VSA", "organize by feature", "feature-based architecture", "slice architecture", or when building a new app or feature and the project already follows VSA conventions. Also use when reviewing or refactoring code to align with VSA principles.
effect-index
Skill index and decision guide. Use to pick the right Effect Skill quickly and follow a minimal decision tree.
xiaohongshu-cn
小红书分析 - 热门笔记发现、关键词监控、趋势分析(Instagram 中国版)
codebase-memory-mcp
Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead or complex code, or handling explicit Codebase Memory requests. Otherwise skip tasks confined to a supplied known file, tiny one-file check, exact literal, configuration value, error string, or non-code text.
specsfy-specialist-delivery-engineering
Projetar e revisar CI/CD, artefatos, releases, promoções, migrations, rollout, rollback e supply chain. Use para pipelines, workflows, ambientes, deploys ou estratégia de entrega; use também para escolher entre rolling, blue-green, canary ou feature flag; não publique, promova ou altere produção sem autorização explícita, e para a métrica que decide o rollout use `$specsfy-specialist-observability`.
512-frameworks-micronaut-data
Use when you need data access with Micronaut Data — @MappedEntity, CrudRepository/PageableRepository, @Query with parameters, @Transactional services, projections, @Version, and @MicronautTest with TestPropertyProvider and Testcontainers. For raw java.sql access without generated repositories, use @511-frameworks-micronaut-jdbc. This should trigger for requests such as Review or implement Micronaut Data repositories and entities; Add transactions, pagination, or projections in Micronaut persistence layer; Model Micronaut Data entities and repositories; Review Micronaut Data transactions and pageable queries; Improve projections or optimistic locking with Micronaut Data. Part of Plinth Toolkit
ecommerce-copywriting
When the user wants to write copy for e-commerce websites, webshops, or online stores. Use when building product pages, product descriptions, checkout flows, category pages, transactional emails, cart copy, or any online store copy. Also use when the user mentions product description, checkout copy, e-commerce copy, webshop copy, abandoned cart email, or order confirmation. Covers single and bulk product descriptions, cart/checkout UX copy, trust signals, promotional copy, SEO meta content, and email sequences.
ux-research
Plan and execute user research including research planning, recruiting, interview design, qualitative synthesis, and translating findings into product decisions. Use this skill whenever the user wants to plan user research, design interviews, recruit participants, conduct discovery, run formative research, or synthesize qualitative findings. Triggers on user research, UX research, user interviews, discovery research, generative research, formative research, qualitative research, user insights, research synthesis, recruitment, interview guide, jobs to be done. Also triggers when product decisions are being made without user input and the user wants to fix that.
tiny-fishing-game-online-unblocked
Play Tiny Fishing online free unblocked on SERP Games.
c4-architecture-c4-architecture
Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.
godot-platform-vr
Expert blueprint for VR platforms (Meta Quest, PSVR, SteamVR, Pico) covering XR toolkit (OpenXR), comfort settings (vignetting, snap turning, teleport), motion controls, hand tracking, and 90+ FPS requirements. Use when targeting VR headsets or implementing immersive 3D experiences. Keywords VR, XR, OpenXR, Meta Quest, motion sickness, comfort, locomotion, XRController3D, foveated rendering.
signoz-setting-up-observability
Run the full end-to-end observability setup for a service after its telemetry is already flowing into SigNoz: sequence SLI/SLO capture, data exploration (RED/USE), focused dashboards, saved Explorer views, burn-rate and absent-data alerts, and a tuning loop into one opinionated, SLO-aware workflow. Make sure to use this skill whenever the user says "set up observability after ingestion", "now that data is flowing, give me dashboards and alerts", "onboard this service to SigNoz end-to-end", "I want the full monitoring setup for X", or asks to go from raw telemetry to a complete dashboard + alerts + views package, even if they don't say "observability" explicitly. This is the orchestration layer: for a single artifact (just a dashboard, just one alert, just a saved view, or one static threshold alert, or a one-off query) use signoz-creating-dashboards, signoz-creating-alerts, signoz-managing-views, or signoz-generating-queries directly.
seedance-comic-to-video
使用 Seedance 2.0(Higgsfield)将漫画书面板、漫画页面、网络漫画和插画故事板转换为动画视频。在用户想要动画漫画、使插画栩栩如生、将漫画转换为视频、动画化故事板或从静态连环艺术创建运动时使用。触发词:漫画变视频、漫画动画、面板动画、故事板变视频、网络漫画动画、漫画书运动、连环艺术、图形小说动画或任何插画转动画请求。即使用户说"使这个画动起来"或"动画化这一页"也要使用。
alicloud-security-cloudfw-test
Minimal smoke test for Cloud Firewall skill. Validate read-only inventory query path.
twilio-sendgrid-email-send
Send transactional and bulk email via the SendGrid v3 Mail Send API. Covers single sends, personalized batch sends with dynamic templates, scheduled sends with cancellation, attachments, and sandbox mode for testing. Use this skill when the caller has a SendGrid API key (SG.-prefix). Do NOT use this skill if the caller is using the Twilio Email API (comms.twilio.com) — that is a separate product with different credentials.
resume-screener
Screen resumes efficiently against job requirements with structured scoring, red flag identification, and interview recommendations
seo-cannibalization-detector
Analyzes multiple provided pages to identify keyword overlap and potential cannibalization issues. Suggests differentiation strategies. Use PROACTIVELY when reviewing similar content.
prd-create
Creates documentation-first PRDs (a short forge issue plus a detailed prds/ file with milestones), then offers to start work, commit for later, or send the PRD to uzi. Use when the user wants to create a PRD, spec out a new feature, write a product requirements document, or turn a feature idea into a tracked GitHub/GitLab/Forgejo issue. Triggers include "create a PRD", "new PRD", "/prd-create", "write a PRD for", "spec this feature".
error-debugging-error-analysis
You are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions.
sap-unused-code
Find Z/Y custom objects never called at runtime by combining SAP call-monitor (SCMON) usage data with static where-used analysis — classifies each as UNUSED/LIKELY_UNUSED/USED/INDETERMINATE. Use when asked to "find unused custom code", "identify retirement candidates", "dead Z objects", or "what can we delete safely".
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system", "show all open transports", "transport backlog", "what is everyone working on", "basis transport overview", "which requests are ready to release", or "find import-order conflicts".
migrate-custom-code
ATC-driven S/4HANA custom code migration — runs ATC readiness checks, groups findings, and generates clean-core replacement code following modern ABAP patterns. Use when asked to "migrate this Z program", "fix ATC findings", "modernize this code for S/4HANA", "clean-core fixes", or "ABAP Cloud readiness for this object".
generate-rap-logic
Generate RAP determinations, validations, and custom action implementations for an existing behavior definition by reading the RAP stack and filling empty method stubs in the behavior pool. Use when asked to "implement RAP determinations", "fill in behavior pool methods", "add RAP validation logic", or "generate custom action code".
flutter-best-practices
Use when writing, reviewing, refactoring, or planning Flutter/Dart code — screens, features, project structure, state management, folders, widgets, cubits/blocs, repositories, services, or tests.
tooluniverse-cancer-genomics-tcga
TCGA/GDC cancer genomics analysis — cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, and multi-omics integration. Use for TCGA-BRCA-style cohort studies, mutation prevalence by cancer type, survival-by-mutation analysis, and pan-cancer driver discovery. Always cancer-type-specific (don't use pan-cancer counts without cohort context).
minimum-experiment
最小实验提示语原文。用户纠结的事情靠继续想已经不会更清楚、需要用现实反馈来验证时使用。触发词包括 最小实验、先试试、怎么验证、别空想了、跑个实验、小成本试错、七天验证、已经反复纠结过很多轮、想了很久还是选不出来。产出待验证假设、一个低成本可逆实验的完整设计,以及明天就能做的第一个动作。
first-principles
第一性原理提示语原文。用户的方案在反复打补丁、陷入路径依赖、想回到问题本质重新推导时使用。触发词包括 第一性原理、回到本质、从头推一遍、别打补丁了、推倒重来、这么做的根本原因是什么。产出原方案里只在修补表面的部分,加一条重新推导的新路径和验证第一步。适合你自己读自己想,不需要 Agent 代跑流程。要的是让人挑毛病、拆台,用 carl-idea-king。
eli5
大图小字讲解法提示语原文。用户想快速看懂一个陌生主题、希望图多字少地讲清楚、提到 eli5 或完全不懂某个东西时使用。要图、要一个能打开的页面时用它,只要文字讲清楚就不用它。触发词包括 大图小字、eli5、当我什么都不懂、图文讲解、少量文字讲清楚、我完全不懂给我讲讲、生成一个讲解页面。产出一个大图配少量文字的 HTML 讲解页面。