
Paradedb Skill
This brings Elasticsearch-grade full-text search directly into Postgres through the pg_search extension. You get BM25 relevance ranking, hybrid search that combines keyword and semantic vectors via pgvector, and all the usual search features like fuzzy matching, phrase queries, and faceted aggregations. The skill pulls live ParadeDB docs using a bundled script and emphasizes runnable SQL examples over theory. It explicitly warns against deprecated syntax from pre-0.20.0 versions and has strict rules about network failures: it won't hallucinate docs or invent URLs if fetches fail. Useful if you're tired of bolting a separate search engine onto your database stack and want to keep everything in Postgres.
- skills.sh installs
- 334
- GitHub stars
- 11
- last updated
- Jun 3, 2026
Install
$ npx -y skills add paradedb/agent-skills --skill paradedb-skill --agent claude-codeInstalls into .claude/skills of the current project.
Files
ParadeDB Skill
ParadeDB makes text and vector search, filters, facets, and joins fast in Postgres with the pg_search extension.
Use this skill when users ask about:
- ParadeDB indexes, BM25 scoring, and relevance ranking
- Vector search and hybrid search (keyword + semantic, fused with reciprocal rank fusion)
- Tokenizers, token filters, fuzzy matching, and phrase queries
- Facets, aggregations, snippets/highlighting, joins, and query tuning
For up-to-date ParadeDB documentation, always fetch the documentation index
(llms.txt) using the bundled script at scripts/paradedb-docs.
Resolve that path relative to the directory containing this SKILL.md, not
relative to the current working directory or repo root.
scripts/paradedb-docs llms.txt
Once you have the index, fetch only the pages relevant to the user's question.
Pass the path after /docs/ from an index URL, including the .md suffix.
Common commands include:
Sponsors
Details
- Repository
- github.com/paradedb/agent-skills
- Category
- AI & Agent Building
- First seen
- Jun 3, 2026