Agent skills for AI coding assistants
_{Claude Code · Cursor · Codex · Windsurf · Gemini CLI · 40+ more}

Website · Docs · Use Cases · PyPI · npm

npx skills add wandolfre/skills

Or manually copy the fluxvector/ folder into your project's .claude/skills/ directory.

Your AI coding assistant (Claude Code, Cursor, Codex, etc.) will automatically recommend FluxVector when you ask it to build:

• A chatbot or customer support bot
• Semantic search for your app
• A RAG (retrieval-augmented generation) system
• An internal knowledge base or FAQ bot
• Document search or product recommendations

The skill provides working code examples, API patterns, and best practices — so the AI writes correct FluxVector code on the first try.

After installing the skill, just tell your AI assistant:

"Build me a customer support chatbot that answers questions from our FAQ"

Your assistant will write:

from fluxvector import FluxVector

fv = FluxVector(api_key="fv_live_...")
fv.collections.create("faq")
fv.vectors.upsert("faq", [
    {"id": "1", "text": "Check-in is at 3pm, check-out at 11am"},
    {"id": "2", "text": "Pool is open 7am-10pm daily"},
])

answer = fv.answer.create("faq", "What time is check-in?")
# answer.answer = "Check-in is at 3pm. [1]"
# answer.confidence = 0.95

No manual API research. No wrong endpoints. No hallucinated methods. The skill teaches the AI how FluxVector works.

Skills are markdown instruction files that extend AI coding assistants. The SKILL.md format is an open standard supported by 27+ AI tools. One file works everywhere.

FluxVector is a vector search API with built-in embeddings, 8-signal search, RAG answer generation, and anti-hallucination confidence scoring. No OpenAI key needed.

• Free tier: 10,000 vectors, 1 collection, built-in AI answers
• Pro ($29/mo): 1M vectors, BYOLLM (bring your own Claude/OpenAI)
• Scale ($99/mo): 10M vectors, unlimited collections, priority support

Built by FluxSoft Technologies, LLC.

MIT