Practical guidance for building effective AI applications using techniques from 60 product leaders and practitioners.
Works with
Covers core prompting patterns: few-shot examples, decomposition for complex tasks, self-criticism, and context placement for cache efficiency
Emphasizes architecture decisions over prompt tuning: context engineering, RAG data preparation, layered model supervision, and specialized models for specific tasks
Provides evaluation frameworks: mandatory evals with binary P
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionbuilding-with-llmsExecute the skills CLI command in your project's root directory to begin installation:
Fetches building-with-llms from refoundai/lenny-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate building-with-llms. Access via /building-with-llms in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
616
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
616
stars
Help the user build effective AI applications using practical techniques from 60 product leaders and AI practitioners.
When the user asks for help building with LLMs:
Few-shot examples beat descriptions Sander Schulhoff: "If there's one technique I'd recommend, it's few-shot prompting—giving examples of what you want. Instead of describing your writing style, paste a few previous emails and say 'write like this.'"
Provide your point of view Wes Kao: "Sharing my POV makes output way better. Don't just ask 'What would you say?' Tell it: 'I want to say no, but I'd like to preserve the relationship. Here's what I'd ideally do...'"
Use decomposition for complex tasks Sander Schulhoff: "Ask 'What subproblems need solving first?' Get the list, solve each one, then synthesize. Don't ask the model to solve everything at once."
Self-criticism improves output Sander Schulhoff: "Ask the LLM to check and critique its own response, then improve it. Models can catch their own errors when prompted to look."
Roles help style, not accuracy Sander Schulhoff: "Roles like 'Act as a professor' don't help accuracy tasks. But they're great for controlling tone and style in creative work."
Put context at the beginning Sander Schulhoff: "Place long context at the start of your prompt. It gets cached (cheaper), and the model won't forget its task when processing."
Context engineering > prompt engineering Bret Taylor: "If a model makes a bad decision, it's usually lack of context. Fix it at the root—feed better data via MCP or RAG."
RAG quality = data prep quality Chip Huyen: "The biggest gains come from data preparation, not vector database choice. Rewrite source data into Q&A format. Add annotations for context humans take for granted."
Layer models for robustness Bret Taylor: "Having AI supervise AI is effective. Layer cognitive steps—one model generates, another reviews. This moves you from 90% to 99% accuracy."
Use specialized models for specialized tasks Amjad Masad: "We use Claude Sonnet for coding, other models for critiquing. A 'society of models' with different roles outperforms one general model."
200ms is the latency threshold Ryan J. Salva (GitHub Copilot): "The sweet spot for real-time suggestions is ~200ms. Slower feels like an interruption. Design your architecture around this constraint."
Evals are mandatory, not optional Kevin Weil (OpenAI): "Writing evals is becoming a core product skill. A 60% reliable model needs different UX than 95% or 99.5%. You can't design without knowing your accuracy."
Binary scores > Likert scales Hamel Husain: "Force Pass/Fail, not 1-5 scores. Scales produce meaningless averages like '3.7'. Binary forces real decisions."
Start with vibes, evolve to evals Howie Liu: "For novel products, start with open-ended vibes testing. Only move to formal evals once use cases converge."
Validate your LLM judge Hamel Husain: "If using LLM-as-judge, you must eval the eval. Measure agreement with human experts. Iterate until it aligns."
Retry failures—models are stochastic Benjamin Mann (Anthropic): "If it fails, try the exact same prompt again. Success rates are much higher on retry than on banging on a broken approach."
Be ambitious in your asks Benjamin Mann: "The difference between effective and ineffective Claude Code users: ambitious requests. Ask for the big change, not incremental tweaks."
Cross-pollinate between models Guillermo Rauch: "When stuck after 100+ iterations, copy the code to a different model (e.g., from v0 to ChatGPT o1). Fresh perspective unblocks you."
Compounding engineering Dan Shipper: "For every unit of work, make the next unit easier. Save prompts that work. Build a library. Your team's AI effectiveness compounds."
Learn to read and debug, not memorize syntax Amjad Masad: "The ROI on coding doubles every 6 months because AI amplifies it. Focus on reading code and debugging—syntax is handled."
Use chat mode to understand Anton Osika: "Use 'chat mode' to ask the AI to explain its logic. 'Why did you do this? What am I missing?' Treat it as a tutor."
Vibe coding is a real skill Elena Verna: "I put vibe coding on my resume. Build functional prototypes with natural language before handing to engineering."
For all 110 insights from 60 guests, see references/guest-insights.md
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
anthropics/claude-code
mblode/agent-skills
github/awesome-copilot
leonxlnx/taste-skill
sickn33/antigravity-awesome-skills
erichowens/some_claude_skills
Useful defaults in building-with-llms — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
building-with-llms has been reliable in day-to-day use. Documentation quality is above average for community skills.
We added building-with-llms from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
I recommend building-with-llms for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
building-with-llms is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
building-with-llms reduced setup friction for our internal harness; good balance of opinion and flexibility.
I recommend building-with-llms for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Keeps context tight: building-with-llms is the kind of skill you can hand to a new teammate without a long onboarding doc.
building-with-llms has been reliable in day-to-day use. Documentation quality is above average for community skills.
I recommend building-with-llms for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
showing 1-10 of 73