llm-engineering-expert

llm-engineering-expert is a skill for Claude Code from personamanagmentlayer/pcl. It costs 92 tokens per session (2,377 once invoked), scanned A, original, Apache-2.0.

A guide to building dependable applications around large language models, which generate text probabilistically rather than following fixed rules. It covers prompts, structured output, testing, safety checks, and controlling token cost and response time.

In plain words
What is it for?
Use it to design model input and output pipelines, validate JSON responses, evaluate quality, and plan failure handling.
Why use it?
It helps handle invalid or variable model responses instead of treating one model call as the whole application.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to design model input and output pipelines, validate JSON responses, evaluate quality, and plan failure handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/personamanagmentlayer/pcl/llm-engineering-expert
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 personamanagmentlayer/pcl --skill llm-engineering-expert
Clone the repo
git clone --depth 1 https://github.com/personamanagmentlayer/pcl

Made for: Claude Code.

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 llm-engineering-expert

README.md
[![agentmods](https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/llm-engineering-expert/github.svg)](https://agentmods.dev/skills/personamanagmentlayer/pcl/llm-engineering-expert)
Your own site
<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/llm-engineering-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/llm-engineering-expert/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 llm-engineering-expert

Your own site · 80×15
<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/llm-engineering-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/llm-engineering-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,377 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Anti-Refusal · line 182
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
How audits are shown
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 $0.00092 $0.02377
Opus 5 $0.00046 $0.01189
Sonnet 5 $0.00018 $0.00475
Haiku 4.5 $0.00009 $0.00238

Measured 4d ago against content hash c51fc7191ee8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llm-engineering-expert 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 4d 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.

stdlib/ai/llm-engineering-expert/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Engineering Expert

Building on a language model is engineering against a component that is non-deterministic, occasionally confident and wrong, and priced per token. The discipline is in the surrounding structure, not in the wording of prompts.

Core Concepts

The Model Is a Component, Not the System

A production LLM feature is a pipeline: input validation, context assembly, the model call, output parsing and validation, then a decision about what to do when any of that fails. Treating the model call as the whole feature is the root of most reliability problems.

Determinism Is Not Available

Even at temperature zero, output can vary across model versions, infrastructure and batching. Design for a distribution of outputs, not a fixed one: validate what comes back, and make the failure path as considered as the success path.

Context Is a Budget

Everything competes for the same window: system instructions, examples, retrieved documents, conversation history, the user's input, and room for the answer. Attention is not uniform across a long context — material at the beginning and end is used more reliably than material buried in the middle. Spend the budget deliberately.

Evaluation Precedes Iteration

Without a scored test set, prompt changes are superstition. Ten to fifty representative cases with expected properties are enough to start and will catch most regressions.

Prompt Design

Structure that holds up

Order matters: instructions first, reference material next, the specific request last. Ending with the request keeps it close to generation.

SYSTEM = """You extract structured invoice data.

Rules:
- Return only fields present in the document. Never infer a missing value.
- Amounts are decimal strings with two places, e.g. "1234.50".
- If the document is not an invoice, set "is_invoice" to false and stop.
- Dates are ISO 8601 (YYYY-MM-DD).
"""

USER = """<document>
{document_text}
</document>

Extract the invoice fields defined by the schema."""

Read the full file on GitHub · 278 lines

Files

What ships with it

2 files 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. 4d ago First seen · 278 lines · 92 tokens per session scan A c51fc7191ee8

Subscribe to this mod's changes

llm-engineering-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 2,377 once invoked, about $0.0005 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 2026-09-05.

Related

Other skills, from other repositories

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.

davila7/claude-code-templates · 38 tokens

ai-engineering-toolkit

AI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching and the operator…

diegosouzapw/awesome-omni-skills · 81 tokens

instructor

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.

OpenLAIR/dr-claw · 41 tokens

instructor

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.

Orchestra-Research/AI-Research-SKILLs · 41 tokens

instructor

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.

liortesta/ClawdAgent · 41 tokens