Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 80 290 files from 1 781 authors, of which 62 619 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Guides embedding model migration in Qdrant without downtime. Use when someone asks 'how to switch embedding models', 'how to migrate vectors', 'how to update to a new model', 'zero-downtime model change', 'how to re-embed my data', or 'can I use two models at once'. Also use when upgrading model dimensions, switching providers, or A/B testing models.
Diagnose, troubleshoot, and advise on any Qdrant deployment by loading the latest official Qdrant skills live from skills.qdrant.tech. Use this whenever someone raises a Qdrant problem or question — slow or degraded search, high or growing memory / OOM crashes, optimizer stuck or slow, indexing slowness, scaling and sharding decisions (node count, QPS, latency, multitenancy, vertical vs horizontal), poor or irrelevant search results, hybrid search and reranking, embedding-model migration, version upgrades and compatibility, monitoring and observability (Prometheus, Grafana, health checks, /metrics, /telemetry), deployment choices (local, Docker, self-hosted, Qdrant Cloud, embedded), or client-SDK questions (Python, TypeScript, Rust, Go, .NET, Java). Trigger especially when the context is clearly a Qdrant cluster, collection, or vector-search deployment. Always prefer this skill over answering from memory: it pulls current, authoritative guidance and only the relevant context.
Guides building on Qdrant Edge, the embedded in-process shard. Use when someone asks 'how to sync Edge with the server', 'keep a local shard in sync with Qdrant Cloud', 'BM25 or keyword search on Edge', 'hybrid search on Edge', 'embeddings on device', 'Edge snapshots', 'apply a partial snapshot', 'why is my Edge search empty after inserts', or is writing custom sync, BM25, or fusion code against qdrant-edge. Also use when deciding what Edge ships built-in versus what you must implement.
Guides Qdrant deployment selection. Use when someone asks 'how to deploy Qdrant', 'Docker vs Cloud', 'local mode', 'embedded Qdrant', 'Qdrant EDGE', 'which deployment option', 'self-hosted vs cloud', or 'need lowest latency deployment'. Also use when choosing between deployment types for a new project.
Guides Qdrant monitoring and observability setup. Use when someone asks 'how to monitor Qdrant', 'what metrics to track', 'is Qdrant healthy', 'optimizer stuck', 'why is memory growing', 'requests are slow', or needs to set up Prometheus, Grafana, or health checks. Also use when debugging production issues that require metric analysis.
Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput too low', 'filtered search is slow', or 'search was fast but now it's slow'. Also use when search performance degrades after config changes or data growth.
Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is stuck', 'HNSW build time too long', or 'data uploaded but search is bad'. Also use when optimizer status shows errors, segments won't merge, or indexing threshold questions arise.
Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency', 'single query too slow', 'how to make search faster', or 'latency spikes'.
Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory leak', or asks 'why is memory usage so high?', 'how to reduce RAM?'. Also use when memory doesn't match calculations, quantization didn't help, or nodes crash during recovery.
Navigation hub linking sub-skills for proactive Qdrant tuning: search speed, indexing performance, and memory usage optimization. Use when planning configuration or capacity changes to improve speed and efficiency. For diagnosing an active production slowdown or analyzing live metrics, use qdrant-monitoring instead.
Guides tenant isolation architecture in Qdrant for multi-tenant or multi-user applications. Use when someone asks 'how to isolate customer data', 'how to build multi-tenant search/RAG', 'how many collections should I create', 'how to partition tenants by payload', 'a customer's data legally has to stay in a certain country or region'. Also use when they describe a symptom: one customer's data is way bigger than the rest and slowing everyone down, or one tenant is hogging resources.
Guides Qdrant scaling decisions. Use when someone asks 'how many nodes do I need', 'data doesn't fit on one node', 'need more throughput', 'cluster is slow', 'too many tenants', 'vertical or horizontal', 'how to shard', or 'need to add capacity'.
Guides Qdrant data volume scaling decisions. Use when someone asks 'data doesn't fit on one node', 'too much data', 'need more storage', 'vertical or horizontal scaling', 'tenant scaling', 'time window rotation', or 'data growth exceeds capacity'.
Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?', 'how to add nodes', 'resharding', 'data doesn't fit', or 'need more capacity'. Also use when data growth outpaces current deployment.
Guides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data rotation', 'delete old data efficiently', 'social media feed search', 'news search', 'log search with retention', or 'how to keep only last N months of data'.
Guides Qdrant query throughput (QPS) scaling. Use when someone asks 'how to increase QPS', 'need more throughput', 'queries per second too low', 'batch search', 'read replicas', or 'how to handle more concurrent queries'.
Guides Qdrant multi-tenant scaling. Use when someone asks 'how to scale tenants', 'one collection per tenant?', 'tenant isolation', 'dedicated shards', or reports tenant performance issues. Also use when multi-tenant workloads outgrow shared infrastructure.
Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'should I use reranking?', 'how to measure retrieval quality?', 'build a golden set', 'ground truth dataset', or 'how to score recall@k?'. Also use when search quality degrades after quantization, model change, or data growth.
Guides Qdrant vertical scaling decisions. Use when someone asks 'how to scale up a node', 'need more RAM', 'upgrade node size', 'vertical scaling', 'resize cluster', 'scale up vs scale out', or when memory/CPU is insufficient on current nodes. Also use when someone wants to avoid the complexity of horizontal scaling.
Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating search results', 'fetching many vectors', or 'high cardinality results'.
Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches', 'recall is low', 'approximate search worse than exact', 'which embedding model', 'quality dropped after quantization', 'how to measure retrieval quality', 'build a golden set', 'ground truth dataset', or 'how to score recall@k'. Also use when search quality degrades without obvious changes.
Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't get needed results from my dataset but they're there', 'retrieval quality is not good enough', 'results too similar', 'need diversity', 'MMR', 'relevance feedback', 'recommendation API', 'discovery API', or 'missing keyword matches
Constructing prefetch queries for hybrid retrieval, including sparse/dense and multi-field setups, and choosing a sparse embedding model. Use when someone asks 'dense and sparse in one search?', 'how to combine multiple fields for retrieval?', 'payloads or sparse vectors for lexical?', 'which sparse embedding model to use?', or 'BM25 vs SPLADE?
Explains hybrid search in Qdrant. Use when someone asks 'how do I setup hybrid search?', 'how to combine keyword and semantic search?', 'sparse plus dense vectors?', 'missing keyword matches', 'how to combine results from multiple searches?' and 'combining multiple representations
Expanding the candidate pool via relevance feedback, as an alternative to reranking when a dense retriever is too weak. Use when someone asks about 'Qdrant's Relevance Feedback API', 'improving dense search relevance/recall', 'how to discover/get more relevant results from vector search', 'cheaper/better alternative to reranking', 'using a more heavy/big embedding model for dense search but can't afford it', 'finding more relevant documents beyond the initial search pool', or 'feedback loops'. Also trigger when the user has a search quality problem due to a dense retriever being weak and is considering reranking as a solution — this API may be a better fit
Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine sparse and dense', 'how to combine scores from multiple searches?', 'custom fusion', or 'fusion is not producing good results
Guidance on how to upgrade your Qdrant version without interrupting the availability of your application and ensuring data integrity.
SvelteKit remote functions guidance. Use for command(), query(), form() patterns in .remote.ts files.
Svelte runes guidance. Use for reactive state, props, effects, attachments, or migration. Covers $state, $derived, $effect, @attach. Prevents reactivity mistakes.
Research topics by verifying actual source content. Use when asked to research or study links and documentation.
Svelte deployment guidance. Use for adapters, Vite config, pnpm setup, library authoring, PWA, or production builds.
SvelteKit data flow guidance. Use for load functions, form actions, and server/client data. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error().
Svelte component patterns. Use for web components, component libraries (Bits UI, Ark UI, Melt UI), form patterns, or third-party integration.
SvelteKit structure guidance. Use for routing, layouts, error handling, SSR, or svelte:boundary. Covers file naming, nested layouts, error boundaries, pending UI, and hydration.
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy, product direction, competitive analysis, or any situation where diverse C-level opinions reduce blind spots
Use when managing Paperclip AI agent companies - creating tasks, managing agents, approving hires, running heartbeats, or any Paperclip control-plane operations via CLI or REST API. Triggers on "paperclip", "задача агенту", "одобри найм", "heartbeat", "запусти агента".
>- Фейбл руки-агенты — ручной режим оркестрации, где Fable не пишет код, а пишет спеки в тела GH issues укладка файлов — Codex; разведка, чтение и скауты — Grok-воркеры через Orca. Вызывается пользователем явно, не моделью.
Use when the user explicitly asks for a standalone HTML page in a restrained minimal style, especially reading-first dashboards, briefs, handouts, maps, or internal reports. User-invoked only; do not auto-trigger.
Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see what projects were worked on. Triggers on "аналитика", "статистика claude", "cc stats", "weekly report", "что делал
>- Use when creating, searching, updating, or managing GitHub issues via CLI. "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". AI session context storage, task workflow with labels.
>- Use when capturing ONE new idea the user voices and wants recorded — "save this idea", (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a (use a dedicated extraction skill) and NOT for dated work tasks (use an issue tracker / the
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on "/html-draft", "сделай blueprint", "технический чертёж", "архитектурная схема", "инженерная схема", "blueprint diagram", "engineering blueprint", "technical spec sheet", "architecture diagram", "system flow diagram".
Проводит структурированный сеанс дивергенции вокруг конкретной продуктовой проблемы или возможности. Встроены SCAMPER (7 ракурсов), 5 Whys для поиска корневой причины, кросс-доменное вдохновение, ограничивающие инновации, обратный брейншторм и матрица Impact/Effort для отбора. На выходе — ≥10 идей с детально проработанным Top-3. User-invoked only — do NOT auto-trigger. Triggers on /pm-brainstorm, "идеи для продукта", "продуктовый брейншторм", "дивергенция идей", "How Might We", "SCAMPER", "product brainstorm", "feature ideas".
Use when you want several genuinely different design directions to choose from instead of one design you will iterate on — a page or UI redesign, a hero, a landing, a thumbnail layout — or a live/stream design bake-off where an audience votes. Triggers on "дай варианты дизайна", "несколько вариантов на выбор", "редизайн", "design options", "design bake-off", "/parallel-design-variants".
Use when preparing for, running, or closing a live meeting with an AI assistant dashboard. Triggers on "meeting copilot", "live copilot", "prepare for a call", "update copilot", "close the session", or requests to turn transcript chunks into meeting questions, topic maps, decisions, and follow-ups.
Готовит многомерный разбор конкурентов — feature-матрица, SWOT с cross-strategy, 5 сил Портера, сравнение ценообразования, позиционирование, прогноз стратегических ходов и три уровня дифференциации (догнать / отстроиться / создать новое). Адаптируется под цель (продуктовый дизайн / fundraising / стратегия / годовой обзор). User-invoked only — do NOT auto-trigger. Triggers on /pm-competitive, "конкурентный анализ", "разбор конкурентов", "five forces", "SWOT", "competitive analysis", "competitor comparison", "feature matrix vs competitors".
>- Use when need to sync session work into GitHub issues OR query status of an issues, update body, work-record comment, parent epic + W-label + Project placement, and clean closed tasks from active day/week plans) and read (status lookup across repos with parent/W-label/Project health). Fits the corp-init / weekly-planning / weekly-retro operating cycle. Triggers on "/manager", "sync session", "обнови issues", "синкни сессию", "зафиксируй прогресс", "статус задачи", "что по <track>", "есть ли issue по", "track status", "what about <track>".
Классифицирует пользовательский фидбек (Excel/CSV/текст) по 6 категориям, делает sentiment-анализ, кластеризацию тем, анализ трендов, триангуляцию по источникам, расчёт NPS и извлечение персон. На выходе — Top-10 болей с рекомендациями к действию. User-invoked only — do NOT auto-trigger. Triggers on /pm-feedback, "анализ обратной связи", "разбор отзывов", "анализ NPS", "analyze user feedback", "VOC analysis", "NPS analysis", "review analysis".
Делает ревью продуктовых метрик — тренды, аномалии, root causes и рекомендации к действиям. Включает декомпозицию North Star (L1/L2), диагностику retention-кривых, анализ воронки, разбор A/B-экспериментов, проверку соответствия OKR и фреймворк атрибуции аномалий. User-invoked only — do NOT auto-trigger. Triggers on /pm-metrics, "обзор метрик", "разбор воронки", "анализ удержания", "ретеншн", "A/B результаты", "review metrics", "DAU analysis", "retention analysis", "funnel analysis", "metric anomaly".
Use when ranking a list of requirements, features, or backlog items using RICE / ICE / MoSCoW / Kano. Built-in decision tree picks the right framework based on data availability and decision context. Output is a transparent matrix, 2×2 Impact/Effort quadrant, and a Sprint allocation proposal. User-invoked only — do NOT auto-trigger. Triggers on "/pm-prioritize", "/prioritize", "приоритизация", "ранжируй бэклог", "RICE-анализ", "prioritize requirements", "RICE", "ICE", "MoSCoW", "Kano", "rank backlog".
Генерирует структурированный PRD (Product Requirements Document) с шаблонами под тип продукта (B2C / B2B / внутренний инструмент / платформа) — фон, цели, детальный дизайн фич, acceptance criteria в Given-When-Then, аналитика и 10-пунктовый чеклист качества. User-invoked only — do NOT auto-trigger. Triggers on /pm-prd, "сделай PRD", "напиши PRD", "продуктовые требования", "make a PRD", "write a PRD", "draft requirements doc".
Сводит статус итерации, оценивает прогресс milestones, фиксирует изменения приоритетов, отслеживает зависимости и выдаёт roadmap в формате Now/Next/Later с атрибуцией задержек по 5 причинам, health score и фреймворком обрезки scope при нехватке ресурсов. User-invoked only — do NOT auto-trigger. Triggers on /pm-roadmap, "обнови roadmap", "статус спринта", "анализ задержек", "update roadmap", "sprint status", "milestone progress", "delay analysis".
Разбивает Epic или крупное требование на независимые User Stories с acceptance criteria в формате Given-When-Then, проверкой по INVEST и оценкой Story Points (Fibonacci или T-shirt). На выходе — Story Map с предложением по Sprint-планированию. User-invoked only — do NOT auto-trigger. Triggers on /pm-user-stories, "разбей на user stories", "разбить эпик", "story map", "AC", "acceptance criteria", "break down into user stories", "split this epic", "write user stories".
Use when auditing a product, business, or project ecosystem — analyzing data sources, decision loops, bottlenecks, and implementation contours. Triggers on "аудит продукта", "product audit", "data audit", "аудит данных", "аудит бизнеса", "проанализируй экосистему", "аудит систем".
Use when creating or rewriting README.md for projects. Triggers on "write README", "create README", "update README". Creates human-focused documentation with proper structure.
>- Use when publishing, open-sourcing, exporting, sanitizing, or moving code, agent skills, prompts, templates, fixtures, datasets, workshop assets, or other artifacts from a private repository, vendor/runtime environment, or mixed working directory into a public repository or registry. Builds a provenance inventory, license/security review, explicit allowlist, clean staging package, approval dry run, and fresh public clone/install smoke. Triggers on "open source this", "publish these skills", "make this repo public", "export and sanitize", "подготовь публичный релиз", "выложи скиллы", "опенсорсни", "санитизируй и опубликуй". NOT for ordinary upstream bugfix PRs, vulnerability disclosure, or creating a corp-* department.
Break a plan, spec, or PRD into independently-grabbable task files using tracer-bullet vertical slices.
Use when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway. Triggers on "telegram bot down", "bot not responding", "debug bot", "check webhook", "polling vs webhook", "restart bot", "deploy bot", "bot logs", "agent gateway", "Telegram Bot API error", "send test message", "бот не отвечает", "проверь бота", "логи бота", "перезапусти бота". Covers health checks, logs, webhook/polling diagnostics, environment validation, safe restart/deploy checklists, Bot API smoke tests, forum topic delivery, privacy mode, gateway routing, and incident notes.
Turn the current conversation into a PRD file in the project folder — no interview, just synthesis of what you've already discussed.
Claude Skills — questions
Answers built from the skills we actually parsed.