qdrant-ingestion-best-practicesProvides production-grade guidance for designing, ingesting, and retrieving data in Qdrant-based RAG pipelines with best practices for chunking, metadata, mo...
Install via ClawdBot CLI:
clawdbot install encryptshawn/qdrant-ingestion-best-practicesGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Calls external URL not in known-safe list
http://localhost:6333Audited Apr 17, 2026 · audit v1.0
Generated Oct 8, 2026
A multi-department company builds an internal RAG assistant over Slack, email, tickets, and PDFs, using three Qdrant collections (company, restricted, PII) with payload-based access control so HR data is only retrievable by authorized roles. The skill provides the metadata schema, sensitivity classification, and filter-inside-query pattern to make this safe.
A SaaS support team ingests help-center articles, past tickets, and chat transcripts into Qdrant with hybrid dense+sparse retrieval and RRF so agents and end users get accurate answers on both semantic and keyword queries. Chunking per content type and idempotent upserts keep the index fresh as docs change.
A law firm or compliance team ingests contracts, policies, and regulatory filings into a restricted Qdrant collection with strict sensitivity classification at ingest time and payload-filtered retrieval. Deterministic chunking and normalized hashing ensure auditability and reproducible citations.
A health-tech platform indexes de-identified clinical notes and protocols into a PII-isolated Qdrant collection, using BGE-M3 hybrid retrieval for medical terminology and access control filters to enforce clinician scoping. Source normalization and source-specific chunking handle transcripts, notes, and PDFs.
An online retailer builds a RAG layer over product catalogs, reviews, and support Q&A using hybrid search with payload filters on category, price, and availability. Collection architecture is justified by query pattern and lifecycle, and deduplication via normalized chunk hashes prevents redundant embeddings.
Companies deploy the skill to build internal RAG assistants that reduce time spent searching Slack, email, tickets, and documents. The value is measured in hours saved per knowledge worker and faster onboarding.
Startups productize a vertical RAG assistant (legal, healthcare, support) powered by Qdrant with the skill's metadata, hybrid retrieval, and access-control standards as the technical foundation. The skill accelerates the path from prototype to production-grade multi-tenant deployment.
Consultancies and agencies use the skill as a reference architecture to design, audit, and harden client RAG pipelines. Deliverables include metadata schema design, ingestion pipelines, and retrieval quality tuning with measurable benchmarks.
💬 Integration Tip
Load the relevant guide from guides/ before writing any pipeline code, and follow the mandatory 9-stage pipeline order plus the 10 never-violate rules — especially classify sensitivity at ingest time and filter inside the Qdrant query.
Scored Oct 8, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.