building-with-llms

building-with-llms is a skill for Claude Code, Codex from cnfeat/top-pm-skills. It costs 49 tokens per session (1,382 once invoked), scanned A, original, MIT.

Practical guidance for building applications that use large language models, the AI systems behind tools such as chatbots and coding assistants. It covers prompts, application design, retrieval-augmented generation, agents, and output evaluation.

In plain words
What is it for?
Use it when creating chatbots, agents, content generators, retrieval systems, prompts, or evaluations for AI features.
Why use it?
It helps identify whether poor results come from the prompt, the supplied context, the model, or the application design. It also encourages testing outputs instead of judging them by impression alone.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it when creating chatbots, agents, content generators, retrieval systems, prompts, or evaluations for AI features.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cnfeat/top-pm-skills/building-with-llms
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add cnfeat/top-pm-skills --skill building-with-llms
Clone the repo
git clone --depth 1 https://github.com/cnfeat/top-pm-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for building-with-llms

README.md
[![agentmods](https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/building-with-llms/github.svg)](https://agentmods.dev/skills/cnfeat/top-pm-skills/building-with-llms)
Your own site
<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/building-with-llms"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/building-with-llms/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for building-with-llms

Your own site · 80×15
<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/building-with-llms"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/building-with-llms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01382
Opus 5 $0.00024 $0.00691
Sonnet 5 $0.00010 $0.00276
Haiku 4.5 $0.00005 $0.00138

Measured 11d ago against content hash 315b164a0e1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

building-with-llms scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

参考skill/lenny-skills-main (2)/lenny-skills-main/skills/building-with-llms/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building with LLMs

Help the user build effective AI applications using practical techniques from 60 product leaders and AI practitioners.

How to Help

When the user asks for help building with LLMs:

  1. Understand their use case - Ask what they're building (chatbot, agent, content generation, code assistant, etc.)
  2. Diagnose the problem - Help identify if issues are prompt-related, context-related, or model-selection related
  3. Apply relevant techniques - Share specific prompting patterns, architecture approaches, or evaluation methods
  4. Challenge common mistakes - Push back on over-reliance on vibes, skipping evals, or using the wrong model for the task

Core Principles

Prompting

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."

Architecture

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."

Read the full file on GitHub · 124 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 124 lines · 49 tokens per session scan A 315b164a0e1d

Subscribe to this mod's changes

building-with-llms is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,382 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.