跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
AI 与知识库

ai-features

Use this skill when the user needs to add AI-powered features to their SaaS product, integrate LLM APIs, build AI assistants, implement RAG, or use AI to differentiate their product. Covers API selection, prompt engineering for product features, cost management, and building AI features that non-technical founders can ship and maintain.

whawkinsiv · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add whawkinsiv/solo-founder-skills --skill ai-features

技能说明


name: ai-features description: "Use this skill when the user needs to add AI-powered features to their SaaS product, integrate LLM APIs, build AI assistants, implement RAG, or use AI to differentiate their product. Covers API selection, prompt engineering for product features, cost management, and building AI features that non-technical founders can ship and maintain."

AI Features & LLM Integration

AI features should make your product 10x better at its core job, not be a marketing checkbox. This skill helps you choose the right AI pattern, manage costs, and ship AI features that users actually value.

Core Principles

  • AI features should make your product 10x better at its core job, not be a marketing checkbox.
  • Start with the API, not a custom model. You don't need to train anything.
  • Cost per API call matters at scale. Design for it from day one.
  • Prompt engineering is your product differentiator. The model is the same for everyone.
  • Always have a fallback. AI features should degrade gracefully, not crash the app.

When to Add AI Features

Add AI When:

  • Users do something repetitive that AI could automate (drafting, categorizing, summarizing)
  • Users need help interpreting data (analysis, recommendations, insights)
  • You can save users significant time on a task they do frequently
  • AI makes your product dramatically easier for non-experts to use
  • Competitors have AI features and users expect parity

Don't Add AI When:

  • It's just a chatbot wrapper with no product context
  • You're adding it for marketing ("AI-powered!") without clear user benefit
  • The task requires 100% accuracy (legal, medical, financial decisions)
  • A simple rule-based approach would work just as well
  • You haven't validated that users want it

AI Feature Patterns for SaaS

Pattern 1: Smart Drafts / Generation

What: AI writes a first draft that users edit and refine.

Examples: Email drafts, report summaries, product descriptions, social posts.

Tell AI:

Add an AI draft feature to [describe where in the app].
When the user clicks "Generate draft," call the Claude API with:
- Context from [what data the AI should use]
- A system prompt that produces [describe the output format]
- User can edit the result before saving
Include: loading state, error handling, and a "regenerate" button.
Use the Claude API with the claude-sonnet-4-5-20250929 model.

Pattern 2: Summarization / Analysis

What: AI condenses or interprets data the user has collected.

Examples: Meeting notes summary, customer feedback themes, dashboard insights.

Tell AI:

Add an AI summary feature that analyzes [data type].
Input: [describe the data — e.g., "all customer feedback from the last 30 days"]
Output: [describe what you want — e.g., "top 5 themes with supporting quotes"]
Display the summary in a card on [page name].
Cache the result so we don't re-call the API on every page load.

Pattern 3: Categorization / Tagging

What: AI automatically labels or categorizes incoming data.

Examples: Support ticket routing, lead scoring, content tagging.

Tell AI:

Auto-categorize incoming [items] using AI.
Categories: [list your categories]
When a new [item] is created, call the API to assign a category.
Store the result in the database. Allow users to override.
Use the cheapest model that works (start with claude-haiku-4-5-20251001).

Pattern 4: Smart Search / Q&A (RAG)

What: Users ask questions and get answers based on their own data.

Examples: "Search my documents," knowledge base Q&A, internal wiki search.

How RAG works (simplified):

1. User's documents → Split into chunks → Store as embeddings in vector DB
2. User asks a question → Convert to embedding → Find relevant chunks
3. Send relevant chunks + question to LLM → Get answer

Tell AI:

Add a Q&A feature where users can ask questions about their [data].
Use RAG (Retrieval-Augmented Generation):
- Embed their [documents/data] using [embedding model]
- Store embeddings in [Supabase pgvector / Pinecone]
- On query, retrieve top 5 relevant chunks
- Send to Claude with context for answer generation
Include: source citations, "I don't know" handling, loading state.

Pattern 5: AI-Powered Recommendations

What: Suggest next actions or choices based on user behavior and data.

Examples: "Try this feature next," product recommendations, workflow suggestions.


Choosing a Model

ModelCostSpeedBest For
Claude Haiku 4.5CheapestFastestCategorization, short responses, high-volume tasks
Claude Sonnet 4.5MediumMediumMost features — drafts, summaries, analysis
Claude Opus 4.6HighestSlowestComplex reasoning, multi-step analysis
GPT-4o miniCheapFastAlternative to Haiku for simple tasks
GPT-4oMediumMediumAlternative to Sonnet

Rule of thumb: Start with the cheapest model. Only upgrade if quality isn't good enough.


Cost Management

Estimating Costs

Cost per request = (input tokens × input price) + (output tokens × output price)

Example (Claude Sonnet):
- Input: ~1,000 tokens ($0.003)
- Output: ~500 tokens ($0.0075)
- Cost per request: ~$0.01

1,000 requests/day = ~$10/day = ~$300/month

Reducing Costs

StrategyHow
Use the cheapest model that worksStart with Haiku, upgrade only if needed
Cache responsesSame input = same output. Don't re-call
Limit output lengthSet max_tokens to what you actually need
Batch requestsCombine multiple small requests into one
Rate limit per userPrevent abuse with per-user daily limits
Use streamingBetter UX (users see progress) and same cost

Setting Usage Limits

Free plan: 10 AI requests/day
Starter plan: 50 AI requests/day
Pro plan: 500 AI requests/day
Enterprise: Unlimited (with fair use policy)

阅读完整来源 ↗