skilld
All skills
simota avatar

/seek

@35ffd55
by shingo imotasimota/agent-skills85 stars
15

Designing search engines and vector DBs for full-text, vector, and hybrid retrieval, including permission-aware retrieval for multi-tenant or per-role corpora. Use for search design, index optimization, the RAG retrieval layer, or deciding where ACL filtering belongs in the query path.

Ask your Agent

Use this Skill: https://skilld.dev/gh/simota/agent-skills/seek

This session only. Nothing lands on disk.

referencerecipes-index.md

≈1.2k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Seek Recipe Registry

The full Recipe table for seek. seek/SKILL.md carries only the dispatch allowlist; this file holds what is needed to execute a Recipe — activation condition and the files to read first.

Read this when a subcommand matched and you need its row, or when scanning what Recipes exist at all.

Recipe Subcommand Default? When to Use Behavior Read First
Full-Text Search fulltext ✓ Elasticsearch/OpenSearch index design, analyzer configuration Elasticsearch / OpenSearch / Meilisearch / Typesense index design. Start from data volume, language, and update cadence. Deliver mapping + query template as paired artifacts. NDCG@10 ≥ 0.70 baseline. reference/patterns.md
Vector Search vector Vector search design, embedding model selection, pgvector/Pinecone Vector index spec (HNSW / IVFFlat / DiskANN). Validate embedding-model choice against domain — general-purpose models fail on specialized corpora (medical / legal / code). Declare distance metric and dimensions up front. reference/embedding-models.md
Hybrid Search hybrid BM25 + vector fusion, RRF scoring, reranking pipeline BM25 + vector fusion via RRF (default k = 60) or weighted sum. Always include fusion-strategy rationale and a reranking-stage recommendation — see rerank for depth. reference/patterns.md
Index Optimization index Index mapping optimization, scaling design Existing index optimization — mapping, analyzer, shard count, replica, refresh interval, warmers. Profile current query mix before changing any setting. For pure infrastructure scaling read reference/scaling-guide.md. reference/patterns.md
RAG Retrieval rag RAG retrieval-layer design, chunking, reranking, context assembly RAG retrieval layer only. Chunking strategy + retrieval method + reranking + context assembly. Hand off to Oracle for prompt design and LLM-output evaluation. Always include a reranker — vector-only retrieval retrieves semantically plausible but suboptimal chunks. reference/evaluation-methods.md
Re-ranking rerank Second-stage re-ranking pipeline — cross-encoder (BGE v2-m3 / Cohere Rerank 3.5), LTR (LambdaMART / LightGBM), latency budget, click-feedback loop Second-stage re-ranking over any retrieval system (not RAG-specific). Pick cross-encoder (BGE Reranker v2-m3 / Cohere Rerank 3.5 / jina-reranker-v2) for quality, LTR (LambdaMART / LightGBM LTR) when click-feedback data exists. Declare Stage-1 top-N, Stage-2 top-K, and added latency budget (typically +30-100ms). Hand off to Builder for feature-extraction pipeline; use Experiment for A/B stat design with eval's search metrics. Cross-link: Oracle embed defers to rerank for reranker depth. reference/rerank-design.md
Autocomplete / Suggest suggest Search-as-you-type / suggestion subsystem — edge n-gram, prefix query, typo tolerance (Levenshtein / symspell), sub-50ms latency Autocomplete / search-as-you-type subsystem, separate from the main fulltext retrieval index. Edge-n-gram or completion suggester analyzer, prefix query, typo tolerance via Levenshtein automaton / BK-tree / symspell. Sub-50ms P99 is the bar; degrade synonyms and personalization before breaking the latency budget. Log query-prefix pairs to feed eval's suggestion-acceptance metric. Cross-link: main retrieval stays in fulltext. reference/suggest-design.md
Retrieval Authorization authz Permission-aware retrieval — multi-tenant or per-role corpora, filter placement, chunk ACL, cache keys, revocation lag Layer all three placements (index-time partition / search-time mandatory filter / post-retrieval check); choose the partition by blast radius if misconfigured, not p95. Measure revocation to T6 (citation + delegated tool actions), not T4. ACL representations, inheritance, cache keys, test matrix, handoffs: Read First. reference/authorization.md
Search Evaluation eval Search quality evaluation program — offline metrics (nDCG / MRR / MAP), online signals (CTR / position bias), golden set, A/B design Search-specific quality evaluation — offline (nDCG / MRR / MAP / Precision@k / Recall@k) and online (CTR with position-bias correction, abandonment, reformulation). Curate 50-200 golden queries with graded judgments; use a click model (Cascade / DBN / PBM) when relying on logs. Delegate general A/B statistics (power, SRM, CUPED) to Experiment; Seek eval supplies the ranking metric and click model. Cross-link: Oracle eval covers LLM-output quality (faithfulness, grounding), a separate domain from retrieval ranking quality. reference/evaluation-methods.md

Source: SKILL.md on GitHub

Third-party checks

No alerts13d4 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The skill 'seek' is a comprehensive design resource for search engines and vector databases. It promotes security best practices, such as retrieval authorization and multi-tenant isolation, and provides legitimate technical templates. No malicious patterns or security risks were identified.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 35ffd55. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/seek