FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Design of search engines and vector databases v1.0.0
Use this resource to design full-text, vector or hybrid search
New
- 303 downloads
- 233 likes
- 152 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install search-and-vector-retrieval-designWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent helps choose the engine (Elasticsearch, Meilisearch, pgvector, Qdrant…), defines indexes and BM25 plus vector fusion, and places permission filtering in the query path. You get a search architecture and its optimisation rules.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- MIT
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- reference/: engine comparison, embedding models and evaluation methods
- reference/: reranking, RAG retrieval, authorization and scaling guide
Good fit for
- Your internal search does not surface the right documents
- You are building a RAG where each role sees only its own data
Not for
Tags
- search
- vectors
- rag
- embeddings
- index
About
You say
“Design the search for my catalogue with per-role filters, on PostgreSQL and pgvector.”
Skill published by simota under the MIT license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to design full-text, vector or hybrid search
- Review and adjust the result
Content preview
Files
- LICENSE1 KB
- NOTICE-PALATEKIT.md0.4 KB
- reference/authorization.md16.2 KB
- reference/autorun-schema.md1.2 KB
- reference/embedding-models.md6.3 KB
- reference/engine-comparison.md8.2 KB
- reference/evaluation-methods.md15.2 KB
- reference/handoffs.md6.7 KB
- reference/patterns.md8.2 KB
- reference/rag-retrieval.md2.3 KB
- reference/recipes-index.md4.7 KB
- reference/rerank-design.md6.8 KB
- reference/scaling-guide.md5.3 KB
- reference/suggest-design.md6.1 KB
- SKILL.md21.1 KB
Origin and licence
Listed unmodified
- Author
- simota
- Source
- github.com/simota/agent-skills/tree/2e02cc9efb3852a45334495df3784d59b87b0e18/seek
- Licence
- MIT
Notice
« seek » (simota, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…