Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Search
2,149 results · page 35 of 72
- View details
knowledge-baseSkillSearch
Use this skill when designing help center architecture, writing support articles, or optimizing search and self-service. Triggers on knowledge base, help center, support articles, self-service, article templates, search optimization, content taxonomy, and any task requiring help documentation design
Ready to connect★ 236
- View details
nanobanana-skillSkillSearch
Generate, remix, or edit images with Nanobanana / Nano Banana 2 through the bundled Gemini CLI wrapper. Use this whenever the user wants AI image generation or editing, especially for reference-image composition, character consistency, grounded visuals that may need live web search, style transfer,
Ready to connect★ 236
- View details
qdrant-advisorSkillSearch
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 slow
Ready to connect★ 232
- View details
qdrant-edgeSkillSearch
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', 'w
Ready to connect★ 232
- View details
qdrant-hybrid-searchSkillSearch
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'. Also use for how
Ready to connect★ 232
- View details
qdrant-hybrid-search-combiningSkillSearch
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'
Ready to connect★ 232
- View details
qdrant-hybrid-search-prefetchesSkillSearch
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
Ready to connect★ 232
- View details
qdrant-indexing-performance-optimizationSkillSearch
Diagnoses and fixes slow Qdrant indexing, stuck optimizers, and poor search quality after data uploads.
Ready to connect★ 232
- View details
qdrant-minimize-latencySkillSearch
Guides your agent through diagnosing and fixing slow search queries in Qdrant to reduce response times.
Ready to connect★ 232
- View details
qdrant-monitoring-debuggingSkillSearch
Lets your agent diagnose Qdrant database problems like slow searches, high memory use, or stuck indexing using metrics.
Ready to connect★ 232
- View details
qdrant-multitenancySkillSearch
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 s
Ready to connect★ 232
- View details
qdrant-performance-optimizationSkillSearch
Guides your agent in tuning Qdrant vector database speed through indexing, query, and hardware advice.
Ready to connect★ 232
- View details
qdrant-relevance-feedbackSkillSearch
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/b
Ready to connect★ 232
- View details
qdrant-scaling-qpsSkillSearch
Guides your agent through increasing Qdrant database query speed and handling more concurrent searches.
Ready to connect★ 232
- View details
qdrant-scaling-query-volumeSkillSearch
Lets your agent follow proven guidance for Qdrant queries that return too many results or paginate slowly.
Ready to connect★ 232
- View details
qdrant-search-qualitySkillSearch
Lets your agent diagnose and improve the relevance of Qdrant vector search results.
Ready to connect★ 232
- View details
qdrant-search-quality-diagnosisSkillSearch
Diagnoses why Qdrant vector search returns poor or irrelevant results and suggests fixes.
Ready to connect★ 232
- View details
qdrant-search-speed-optimizationSkillSearch
Diagnoses and fixes slow Qdrant vector search, covering latency, throughput, and filtered query issues.
Ready to connect★ 232
- View details
qdrant-search-strategiesSkillSearch
Guides your agent in choosing the right Qdrant search approach when retrieval results are poor or relevance questions arise.
Ready to connect★ 232
- View details
qdrant-sliding-time-windowSkillSearch
Teaches your agent how to set up sliding time windows in Qdrant so old vector data expires on schedule.
Ready to connect★ 232
- View details
mathodology-evidence-searchSkillSearch
Use when an award run needs external evidence — literature, datasets, benchmarks, domain constants, prior-art checks, or citation verification — with combined built-in WebSearch and search MCP discovery, source reconciliation, document reading, citation confirmation, token budgets, and reproducibili
Ready to connect★ 229
- View details
weread-skillsSkillSearch
Lets your agent access your WeRead books, notes and highlights.
Ready to connect★ 225
- View details
Automation Tester Resume OptimizerSkillSearch
Build an SDET or automation engineer resume around framework ownership, tool-stack evidence, CI/CD integration, and GitHub proof that survives technical screening and recruiter keyword search.
Ready to connect★ 224
- View details
docs-seekerSkillSearch
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
Ready to connect★ 224
- View details
Elasticsearch Testing PatternsSkillSearch
Elasticsearch testing including index management, query validation, mapping verification, bulk operation testing, and search relevance scoring.
Ready to connect★ 224
- View details
brain:wikiSkillSearch
Browse, search, and generate Wikipedia-style knowledge articles from the brain. Auto-generated from brain DB entities, emails, docs, and decisions.
Ready to connect★ 220
- View details
cognee:recallSkillSearch
Semantic and graph search across Cognee knowledge graph. Queries project memory, finds related entities and decisions, injects results as agent context. Triggers on: 'cognee recall', 'search memory', 'what do we know about', 'find related', 'graph search', 'memory search', 'recall context'.
Ready to connect★ 220
- View details
meta:mediaSkillSearch
Multimodal memory — ingest, embed, and search media (images, video, audio, files) with Gemini Embedding 2 + ChromaDB
Ready to connect★ 220
- View details
clip-aware-embeddingsSkillSearch
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities,
Ready to connect★ 219
- View details
cloudflare-vectorizeSkillSearch
Cloudflare Vectorize vector database for semantic search and RAG. Use for vector indexes, embeddings, similarity search, or encountering dimension mismatches, filter errors.
Ready to connect★ 217
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
52,524 of the 52,958 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.