Claude MarketplacesSubmit
jeffallan avatar

Prompt Engineer

jeffallan/claude-skills

This one handles the full lifecycle of LLM prompt design, from writing your first zero-shot attempt to building evaluation frameworks that catch regressions. It walks you through the workflow (understand, design, test, iterate, deploy) and loads reference docs for specific patterns like chain-of-thought or structured outputs. The validation checkpoint at 80% accuracy is a nice forcing function to stop and diagnose failures before you keep tweaking randomly. What I appreciate is the before/after examples and the concrete constraints, like "make one change at a time when debugging" and "don't deploy without systematic evaluation." It's opinionated enough to keep you from common mistakes but flexible enough for different model families. Worth using if you're moving beyond ad-hoc prompt tweaking.

skills.sh installs
5.9K
GitHub stars
12.3K
last updated
Aug 21, 2026
View on GitHub

Install

$ npx -y skills add jeffallan/claude-skills --skill prompt-engineer --agent claude-code

Installs into .claude/skills of the current project.

Files

Prompt Engineer

Expert prompt engineer specializing in designing, optimizing, and evaluating prompts that maximize LLM performance across diverse use cases.

When to Use This Skill

  • Designing prompts for new LLM applications
  • Optimizing existing prompts for better accuracy or efficiency
  • Implementing chain-of-thought or few-shot learning
  • Creating system prompts with personas and guardrails
  • Building structured output schemas (JSON mode, function calling)
  • Developing prompt evaluation and testing frameworks
  • Debugging inconsistent or poor-quality LLM outputs
  • Migrating prompts between different models or providers

Core Workflow

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/jeffallan/claude-skills
Categories
Testing & QA, Code Review & Quality, AI & Agent Building, Debugging

More from jeffallan/claude-skills

All 66

Recommended

More Testing & QA
1forcedotcom avataragentforce-architecture-analyzeforcedotcom/sf-skillsDeclared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins. Renders a human-readable arch5.9Kskills.sh installs
2affaan-m avatarui-demoaffaan-m/eccRecord polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application.5.8Kskills.sh installs
3forcedotcom avataragentforce-observeforcedotcom/sf-skillsAnalyze production Agentforce agent behavior using session traces and Data Cloud. TRIGGER when: user queries STDM session data or Data Cloud trace records; inve5.8Kskills.sh installs
4getsentry avatarcode-reviewgetsentry/skillsPerform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Co5.7Kskills.sh installs
5jeffallan avatarterraform-engineerjeffallan/claude-skillsUse when implementing infrastructure as code with Terraform across AWS, Azure, or GCP. Invoke for module development (create reusable modules, manage module ver5.7Kskills.sh installs
6trailofbits avatarsemgrep-rule-variant-creatortrailofbits/skillsCreates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages 5.7Kskills.sh installs