Context & AI engineering
25,745 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
Pyfagorass/bookofspells/skills/qdrant/qdrant-scaling/scaling-data-volume/sliding-time-window Skill
no license2★ repoGuides 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'.
Pyfagorass/bookofspells/skills/qdrant/qdrant-scaling/scaling-data-volume/tenant-scaling Skill
no license2★ repoGuides 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.
Pyfagorass/bookofspells/skills/qdrant/qdrant-scaling/scaling-data-volume/vertical-scaling Skill
no license2★ repoGuides 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.
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/qdrant/qdrant-scaling/scaling-qps Skill
no license2★ repoGuides 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'.
Pyfagorass/bookofspells/skills/qdrant/qdrant-scaling/scaling-query-volume Skill
no license2★ repoGuides 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'.
The same file is in 2 other repositories
Pyfagorass/bookofspells/skills/qdrant/qdrant-search-quality Skill
no license2★ repoDiagnoses 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.
Pyfagorass/bookofspells/skills/qdrant/qdrant-search-quality/diagnosis Skill
no license2★ repoDiagnoses 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.
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/qdrant/qdrant-search-quality/search-strategies Skill
no license2★ repoGuides 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'
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/qdrant/qdrant-search-quality/search-strategies/hybrid-search Skill
no license2★ repoExplains 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'
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/qdrant/qdrant-search-quality/search-strategies/hybrid-search/combining-searches Skill
no license2★ repoUse 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'
Pyfagorass/bookofspells/skills/qdrant/qdrant-search-quality/search-strategies/hybrid-search/search-types Skill
no license2★ repoUse when someone asks 'how to combine lexical and semantic retrieval', '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?', 'BM25 vs SPLADE?'
Pyfagorass/bookofspells/skills/qdrant/qdrant-search-quality/search-strategies/relevance-feedback Skill
no license2★ repoUse 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.
Pyfagorass/bookofspells/skills/qdrant/qdrant-version-upgrade Skill
no license2★ repoGuidance on how to upgrade your Qdrant version without interrupting the availability of your application and ensuring data integrity.
Pyfagorass/bookofspells/skills/qdrant/relevance-feedback Skill
no license2★ repoUse 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.
Pyfagorass/bookofspells/skills/qdrant/scaling-data-volume Skill
no license2★ repoGuides 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'.
The same file is in 2 other repositories
Pyfagorass/bookofspells/skills/qdrant/scaling-data-volume/horizontal-scaling Skill
no license2★ repoDiagnoses 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.
Pyfagorass/bookofspells/skills/qdrant/scaling-data-volume/sliding-time-window Skill
no license2★ repoGuides 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'.
Pyfagorass/bookofspells/skills/qdrant/scaling-data-volume/tenant-scaling Skill
no license2★ repoGuides 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.
Pyfagorass/bookofspells/skills/qdrant/scaling-data-volume/vertical-scaling Skill
no license2★ repoGuides 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.
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/qdrant/scaling-qps Skill
no license2★ repoGuides 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'.
Pyfagorass/bookofspells/skills/qdrant/scaling-query-volume Skill
no license2★ repoGuides 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'.
The same file is in 2 other repositories
Pyfagorass/bookofspells/skills/qdrant/search-speed-optimization Skill
no license2★ repoDiagnoses 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.
Pyfagorass/bookofspells/skills/qdrant/search-strategies Skill
no license2★ repoGuides 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'
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/qdrant/search-strategies/hybrid-search Skill
no license2★ repoExplains 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'
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/qdrant/search-strategies/hybrid-search/combining-searches Skill
no license2★ repoUse 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'
Pyfagorass/bookofspells/skills/qdrant/search-strategies/hybrid-search/search-types Skill
no license2★ repoUse when someone asks 'how to combine lexical and semantic retrieval', '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?', 'BM25 vs SPLADE?'
Pyfagorass/bookofspells/skills/qdrant/search-strategies/relevance-feedback Skill
no license2★ repoUse 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.
Pyfagorass/bookofspells/skills/qdrant/search-types Skill
no license2★ repoUse when someone asks 'how to combine lexical and semantic retrieval', '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?', 'BM25 vs SPLADE?'
Pyfagorass/bookofspells/skills/qdrant/setup Skill
no license2★ repoGuides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when someone asks 'how to set up monitoring', 'Prometheus config', 'Grafana dashboard', 'health check endpoints', 'how to scrape Hybrid Cloud', 'what alerts to set', 'how to centralize logs', or 'audit logging'.
Pyfagorass/bookofspells/skills/qdrant/sliding-time-window Skill
no license2★ repoGuides 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'.
Pyfagorass/bookofspells/skills/qdrant/tenant-scaling Skill
no license2★ repoGuides 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.
Pyfagorass/bookofspells/skills/qdrant/vertical-scaling Skill
no license2★ repoGuides 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.
The same file is in 1 other repository
Pyfagorass/bookofspells/skills/redis/redis-vector-search Skill
no license2★ repoRedis vector search guidance covering HNSW vs FLAT algorithm choice, vector index configuration (dims, distance metric, datatype), filtered hybrid search combining vector similarity with TAG or NUMERIC filters, and the RAG retrieval pattern with RedisVL. Use when defining a VECTOR field in FT.CREATE, integrating embeddings (OpenAI, Cohere, sentence-transformers), tuning HNSW parameters (M, EF_CONSTRUCTION, EF_RUNTIME), building a retrieval-augmented generation pipeline, or filtering vector results by attribute.
Pyfagorass/bookofspells/skills/supabase/supabase Skill
no license2★ repoUse when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector).
Pyfagorass/bookofspells/the-emissary Skill
no license2★ repoFind and connect an MCP server — an "Emissary of the Pact" — when the agent needs a tool, service, API, or data source it does not already have. Use when the user asks for an MCP server, to connect to or integrate an external service (Notion, GitHub, Figma, a database, Slack, a SaaS API…), asks "is there an MCP for X", "add an MCP", or sets a task that needs live tools the agent lacks. This rite DISCOVERS a server from the official MCP Registry and reputable directories and PROPOSES its connection config for the user to approve — it NEVER installs, launches, or writes credentials on its own. The companion to the-grimoire: that finds spells (inert skills); this finds Emissaries (live tool-servers).
Pyfagorass/bookofspells/the-grimoire Skill
no license2★ repoThe index to a Book of Spells — a large, curated library of ready-made spells (skills in the SKILL.md format) gathered from many providers (Google, OpenAI, and more), covering cloud platforms, deployment, design tools, PDFs, browser automation, security, and much else. The spells are NOT preloaded — there may be thousands. Use this whenever the user asks to cast a spell, or for a spell to do something, or names a capability, provider, or tool you do not already have loaded (e.g. "cast a spell for Figma", "is there a spell for deploying?", "use the bigquery spell"), or whenever a task might be served by a specialised, ready-made spell. Casting a spell MEANS consulting this index to discover and load the right one on demand — do that first, rather than improvising. This is also the single entry point to the Book's own keystones: route here to AUTHOR a new spell (the-spellwright), to FIND or CONNECT an MCP server / external tool (the-emissary), or to INSTALL the Book into a conduit (the-tether).
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/ai-engineering-command-desk Skill
2★ repoorchestrate AI engineering workflows from capability intent through model, prompt, tool, agent, retrieval, eval, safety, inference, observability, release, and incident stages using connector-grounded evidence, workflow packets, stage advancement, and halt behavior.
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/ai-incident-response-desk Skill
2★ repotriage AI production incidents involving hallucination spikes, safety failures, prompt injection, tool misuse, data leakage, model regressions, cost spikes, latency degradation, eval regressions, or user harm reports.
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/eval-design-desk Skill
2★ repodesign AI evaluation plans with goals, datasets, rubrics, grading methods, thresholds, regression slices, safety checks, human review, and reporting requirements.
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/eval-run-analysis-desk Skill
2★ repoanalyze completed AI eval runs, regression deltas, failure clusters, grading reliability, threshold status, release blockers, and rerun recommendations.
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/prompt-systems-desk Skill
2★ repodesign prompt systems, instruction hierarchy, context assembly, prompt contracts, refusal and defer behavior, prompt evaluation fixtures, prompt injection defenses, and prompt observability hooks for AI capabilities.
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/red-team-eval-desk Skill
2★ repoplan and analyze adversarial AI testing for jailbreaks, prompt injection, data exfiltration, harmful instructions, over-permissioned tools, and policy evasion.
MadewellRD/skills-lab/dist/skills/ai-engineering-command-desk/retrieval-rag-design-desk Skill
2★ repodesign retrieval augmented generation systems with indexing, chunking, embeddings, ranking, filters, citations, freshness policy, permission filtering, and grounding behavior.
MadewellRD/skills-lab/dist/skills/customer-success-command-desk/post-sale-handoff-desk Skill
2★ reporeconcile the executed order form against what the deal narrative promised at closed-won handoff, covering entitlement and term facts read from the contract, the commitment register of sales-cycle promises with who made them and to whom, the buying group as it stood at signature, implementation assumptions the deal was priced on, and the kickoff acceptance decision. use for handoff intake, sales to customer success transition, new logo readiness, co-term and amendment intake, and reconciling what was sold against what was signed.
MadewellRD/skills-lab/dist/skills/customer-support-command-desk/knowledge-base-desk Skill
2★ repoauthor and govern help center and internal knowledge base articles captured from resolved contacts, scoped to the product versions and editions they are true for, with steps verified against a stated build, titles and search terms written in the customer's words, ownership and review dates, duplicate and contradiction reconciliation, and a staleness register for articles a release has silently invalidated. use for knowledge-centered service work, article drafting, kb audits, content lifecycle, and post-release documentation checks.
MadewellRD/skills-lab/dist/skills/data-command-desk/batch-orchestration-desk Skill
2★ repodesign pipeline scheduling and the dag, covering data aware triggering that waits for data rather than for a clock, sensors and arrival timeouts, retry policy and non retryable failure classes, concurrency pools and queueing at peak, sla miss conditions and notification, catch up and backfill controls with partition bounds and concurrency caps, run isolation between backfill and scheduled runs, and the failure pattern read from run history. use for airflow or dagster dag design, scheduling reviews, sla definition, retry tuning, and backfill orchestration.
MadewellRD/skills-lab/dist/skills/sales-command-desk/customer-handoff-desk Skill
2★ repoprepare post-sale handoff packages for onboarding, customer success, support, or implementation teams. use when the assistant needs to perform or continue sales revenue command desk work involving accounts, leads, opportunities, crm, calendar, email, files, prospecting, proposals, forecasts, renewals, or customer handoffs.
MadewellRD/skills-lab/dist/skills/sdlc-command-desk/implementation-handoff-desk Skill
2★ repocreate, review, refine, and package connector-grounded implementation handoffs for coding agents after requirements, discovery, architecture, and issue planning are complete. use when the user asks for the coding agent instructions, branch work, commit plans, pull request handoffs, halt-resume prompts, merge-train runbooks, repo cleanup prompts, docs/proof handoffs, or low-token coding-agent execution plans backed by github, issues, docs, ci checks, and source facts.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/agent-architecture-desk Skill
2★ repodesign AI agent architecture including planning boundaries, execution loops, memory and state strategy, tool routing, approval gates, retries, delegation, and halt behavior.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/agent-observability-desk Skill
2★ repodesign observability for AI agents and workflows including traces, prompts, model calls, tool calls, retrieval events, approvals, errors, eval probes, cost, latency, and safety signals.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/ai-engineering-command-desk Skill
2★ repoorchestrate AI engineering workflows from capability intent through model, prompt, tool, agent, retrieval, eval, safety, inference, observability, release, and incident stages using connector-grounded evidence, workflow packets, stage advancement, and halt behavior.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/ai-incident-response-desk Skill
2★ repotriage AI production incidents involving hallucination spikes, safety failures, prompt injection, tool misuse, data leakage, model regressions, cost spikes, latency degradation, eval regressions, or user harm reports.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/eval-design-desk Skill
2★ repodesign AI evaluation plans with goals, datasets, rubrics, grading methods, thresholds, regression slices, safety checks, human review, and reporting requirements.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/eval-run-analysis-desk Skill
2★ repoanalyze completed AI eval runs, regression deltas, failure clusters, grading reliability, threshold status, release blockers, and rerun recommendations.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/prompt-systems-desk Skill
2★ repodesign prompt systems, instruction hierarchy, context assembly, prompt contracts, refusal and defer behavior, prompt evaluation fixtures, prompt injection defenses, and prompt observability hooks for AI capabilities.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/red-team-eval-desk Skill
2★ repoplan and analyze adversarial AI testing for jailbreaks, prompt injection, data exfiltration, harmful instructions, over-permissioned tools, and policy evasion.
MadewellRD/skills-lab/dist/vendor/anthropic/ai-engineering-command-desk/retrieval-rag-design-desk Skill
2★ repodesign retrieval augmented generation systems with indexing, chunking, embeddings, ranking, filters, citations, freshness policy, permission filtering, and grounding behavior.
MadewellRD/skills-lab/dist/vendor/anthropic/customer-success-command-desk/post-sale-handoff-desk Skill
2★ reporeconcile the executed order form against what the deal narrative promised at closed-won handoff, covering entitlement and term facts read from the contract, the commitment register of sales-cycle promises with who made them and to whom, the buying group as it stood at signature, implementation assumptions the deal was priced on, and the kickoff acceptance decision. use for handoff intake, sales to customer success transition, new logo readiness, co-term and amendment intake, and reconciling what was sold against what was signed.
MadewellRD/skills-lab/dist/vendor/anthropic/customer-support-command-desk/knowledge-base-desk Skill
2★ repoauthor and govern help center and internal knowledge base articles captured from resolved contacts, scoped to the product versions and editions they are true for, with steps verified against a stated build, titles and search terms written in the customer's words, ownership and review dates, duplicate and contradiction reconciliation, and a staleness register for articles a release has silently invalidated. use for knowledge-centered service work, article drafting, kb audits, content lifecycle, and post-release documentation checks.
MadewellRD/skills-lab/dist/vendor/anthropic/data-command-desk/batch-orchestration-desk Skill
2★ repodesign pipeline scheduling and the dag, covering data aware triggering that waits for data rather than for a clock, sensors and arrival timeouts, retry policy and non retryable failure classes, concurrency pools and queueing at peak, sla miss conditions and notification, catch up and backfill controls with partition bounds and concurrency caps, run isolation between backfill and scheduled runs, and the failure pattern read from run history. use for airflow or dagster dag design, scheduling reviews, sla definition, retry tuning, and backfill orchestration.