prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Well-structured body with clear workflow validation and excellent progressive disclosure via a reference table. Trimmable redundancy in the Coverage Note and overlapping When-to-Use list are the main conciseness gaps.

Suggestions

Trim or remove the 'Coverage Note' section since it restates topics already enumerated in the reference table.

Collapse the 'When to Use This Skill' list or cross-reference the description triggers to avoid duplication with the frontmatter.

Add one concrete evaluation-metric example (e.g., an exact--match or rubric-score formula) to lift actionability from concrete templates to fully executable guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tight bullets and examples, but the redundant Coverage Note and an overlapping When-to-Use list could be trimmed to reach the lean 5 anchor.	4 / 5
Actionability	Concrete prompt templates and specific MUST/MUST-NOT constraints give actionable guidance; minor gaps in concrete eval-metric formulas or harness commands keep it just below 5.	4 / 5
Workflow Clarity	The 5-step Core Workflow includes an explicit validation checkpoint (accuracy < 80% triggers failure-pattern analysis) and a one-change-at-a-time iteration loop, matching the 5 anchor.	5 / 5
Progressive Disclosure	A clean overview body with a well-signaled reference table pointing to six verified, one-level-deep reference files, matching the clear-overview 5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with concrete actions and an explicit Use-when trigger clause. Only minor gap is the absence of file-extension-style synonym triggers.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — writes, refactors, evaluates prompts plus generating templates, schemas, rubrics, and test suites — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly states what the skill does and follows with a concrete 'Use when...' clause enumerating trigger scenarios, matching the 5 anchor.	5 / 5
Trigger Term Quality	Strong natural keywords (chain-of-thought, few-shot, system prompts, structured output, function calling) but lacks file-extension-style synonyms, so it sits just below the exhaustive-coverage 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (LLM prompt engineering) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jeffallan/claude-skills
Path: skills/prompt-engineer/SKILL.md
Commit: 882ef55

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.