LightState Registry / Portable Agent Skill (SKILL.md)s / Engineering & DevOps / skill-pgvector-hnsw-indexing-tuning
⚡ Pulse Score 88/100
PostgreSQL pgvector HNSW Index & Recall Tuning Playbook
Tune pgvector HNSW m and ef_construction parameters, iterative index scans, and halfvec storage in Postgres.
⚡ 1-Click Agent & Developer Install
Zero Auth · Ready for Grok Bot, Claude Code & Cursornpx lightstate install skill-pgvector-hnsw-indexing-tuning
Copy-Paste System Prompt / Routine Blueprint:
Load the PostgreSQL pgvector HNSW Index & Recall Tuning Playbook (skill-pgvector-hnsw-indexing-tuning) playbook. First inspect our current configuration and codebase for pgvector, PostgreSQL, Embeddings. Then propose a concrete, step-by-step implementation plan following the skill-pgvector-hnsw-indexing-tuning guardrails, run the non-destructive verification commands (psql -c 'SELECT extversion FROM pg_extension WHERE extname = $$vector$$;'), and summarize any findings, risks, or required environment variables before making production changes.
📘 Complete SKILL.md Playbook Specification
--- name: pgvector-hnsw-indexing-tuning description: Tune pgvector HNSW m and ef_construction parameters, iterative index scans, and halfvec storage in Postgres. Use when working with pgvector, PostgreSQL, Embeddings. triggers: - pgvector hnsw indexing tuning - pgvector - postgresql --- # PostgreSQL pgvector HNSW Index & Recall Tuning Playbook ## 1. When to Use This Skill Load `skill-pgvector-hnsw-indexing-tuning` whenever an engineering, architecture, or operations task involves **pgvector, PostgreSQL, Embeddings**. Specifically: - Tune pgvector HNSW m and ef_construction parameters, iterative index scans, and halfvec storage in Postgres. - Designing, reviewing, refactoring, or debugging production configurations without guesswork or deprecated flags. - Running deterministic pre-flight validation and post-execution verification checks before reporting completion. ## 2. Prerequisites & Required Environment - **Target Stack:** pgvector, PostgreSQL, Embeddings - **Permissions Boundary:** Read-only inspection by default; ask for explicit human confirmation before executing destructive mutations or production deployments. - **Reference Specification:** `https://github.com/pgvector/pgvector` ## 3. Step-by-Step Execution Playbook 1. **Context & Configuration Discovery:** Inspect existing project manifests (`package.json`, `tsconfig.json`, `pyproject.toml`, `Cargo.toml`, `wrangler.jsonc`, or schema declarations) before proposing changes. Never overwrite existing bindings or credentials blindly. 2. **Deterministic Implementation:** Apply the canonical production patterns for **pgvector**: - Enforce strict schema and type validation at every external boundary. - Include explicit error handling, structured telemetry, and idempotency keys on all mutating calls. - Keep secrets in environment variables or managed secret stores—never hardcode tokens in source files. 3. **Verification & Regression Gate:** Run the verification commands below and inspect both exit codes and output payloads before marking the task complete. ## 4. Reference Commands & CLI Workflow ```bash psql -c 'SELECT extversion FROM pg_extension WHERE extname = $$vector$$;' ``` ## 5. Edge Cases & Anti-Hallucination Guardrails - **Zero Unverified Claims:** Never claim a build, migration, test run, or API call succeeded without inspecting the command output or HTTP status code. - **Rollback Readiness:** Always record the previous state or migration version so changes can be reverted cleanly if downstream health checks fail.
Synthesized Engineering Blueprint & Setup Guide
### Overview & Capability Scope
**PostgreSQL pgvector HNSW Index & Recall Tuning Playbook** (`skill-pgvector-hnsw-indexing-tuning`) is a verified, portable `SKILL.md` playbook curated with **@supabase** for Grok Bot (`x.ai/bot/`), Claude Code (`~/.claude/skills/`), and Cursor (`.cursor/skills/`).
Tune pgvector HNSW m and ef_construction parameters, iterative index scans, and halfvec storage in Postgres.
### Required Stack & Tooling
- **Primary Stack:** pgvector, PostgreSQL, Embeddings
- **Category:** `engineering`
- **Source & Reference:** [https://github.com/pgvector/pgvector](https://github.com/pgvector/pgvector)
### Quickstart Installation
Install this `SKILL.md` playbook directly into your agent workspace:
```bash
npx lightstate install skill-pgvector-hnsw-indexing-tuning
```
Or copy the complete `SKILL.md` specification below into `.cursor/skills/skill-pgvector-hnsw-indexing-tuning/SKILL.md` or `~/.claude/skills/skill-pgvector-hnsw-indexing-tuning/SKILL.md`.
### Verification Commands
```bash
psql -c 'SELECT extversion FROM pg_extension WHERE extname = $$vector$$;'
```
Tags: #pgvector#postgresql#embeddings#skill-md#engineering
✓ CERTIFIED X BUILDER PORTFOLIO
More Capabilities Curated from @supabase
Related Verified Capabilities
Explore Engineering & DevOps → MCP Server ★ Featured Partner ✓ Claimed
⚡ 98
Grok Template ✓ Claimed
⚡ 97
Dr. Eggbot — Meta-Agent Architect & Bot Builder
MCP Server ✓ Claimed
⚡ 89
Visual Sentinel MCP — Automated UI Pixel-Diff & Layout QA Server
MCP Server ✓ Claimed
⚡ 88
Cloudflare Official MCP — Workers, D1, R2, KV & Observability
MCP Server ✓ Claimed
⚡ 86
Supabase Official MCP — Postgres Schema, RLS & Edge Functions
MCP Server ✓ Claimed
⚡ 85