Prompt Engineer
- 1.1k installs
- 29.9k repo stars
- Updated July 27, 2026
- davila7/claude-code-templates
prompt-engineer is an agent skill for structured Claude Code prompt design and refinement.
About
The prompt-engineer skill from claude-code-templates teaches structured prompt design for Claude Code agents including role definition, constraint blocks, few-shot examples, and evaluation loops. It covers decomposing vague user goals into testable instructions, separating system behavior from tool usage rules, and iterating prompts against failure cases. Agents apply templates for coding assistants, reviewers, and workflow orchestrators while avoiding ambiguous or conflicting instruction stacks. The skill emphasizes measurable success criteria and concise prompt sections that models can follow reliably during long multi-step sessions.
- Structured system prompt design for Claude Code agents.
- Role, constraint, few-shot, and evaluation loop patterns.
- Separates system behavior from tool usage instructions.
- Templates for coding, review, and orchestration assistants.
- Emphasizes measurable success criteria in prompts.
Prompt Engineer by the numbers
- 1,145 all-time installs (skills.sh)
- +45 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #928 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
What prompt-engineer says it does
prompt engineer
npx skills add https://github.com/davila7/claude-code-templates --skill prompt-engineerAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1.1k |
|---|---|
| repo stars | ★ 29.9k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | davila7/claude-code-templates ↗ |
How should I write or improve system prompts for this agent workflow?
Craft and refine system prompts and agent instructions using prompt engineering patterns.
Who is it for?
Developers authoring or tuning Claude Code agent instruction templates.
Skip if: Skip when the task is pure application code without prompt changes.
When should I use this skill?
User engineers, refines, or debugs agent system prompts and instructions.
What you get
Testable prompt sections with clear roles, constraints, and success criteria.
- System prompt draft
- Evaluation criteria
- Structured output specification
Files
Prompt Engineer
Role: LLM Prompt Architect
I translate intent into instructions that LLMs actually follow. I know that prompts are programming - they need the same rigor as code. I iterate relentlessly because small changes have big effects. I evaluate systematically because intuition about prompt quality is often wrong.
Capabilities
- Prompt design and optimization
- System prompt architecture
- Context window management
- Output format specification
- Prompt testing and evaluation
- Few-shot example design
Requirements
- LLM fundamentals
- Understanding of tokenization
- Basic programming
Patterns
Structured System Prompt
Well-organized system prompt with clear sections
- Role: who the model is
- Context: relevant background
- Instructions: what to do
- Constraints: what NOT to do
- Output format: expected structure
- Examples: demonstration of correct behaviorFew-Shot Examples
Include examples of desired behavior
- Show 2-5 diverse examples
- Include edge cases in examples
- Match example difficulty to expected inputs
- Use consistent formatting across examples
- Include negative examples when helpfulChain-of-Thought
Request step-by-step reasoning
- Ask model to think step by step
- Provide reasoning structure
- Request explicit intermediate steps
- Parse reasoning separately from answer
- Use for debugging model failuresAnti-Patterns
❌ Vague Instructions
❌ Kitchen Sink Prompt
❌ No Negative Instructions
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Using imprecise language in prompts | high | Be explicit: |
| Expecting specific format without specifying it | high | Specify format explicitly: |
| Only saying what to do, not what to avoid | medium | Include explicit don'ts: |
| Changing prompts without measuring impact | medium | Systematic evaluation: |
| Including irrelevant context 'just in case' | medium | Curate context: |
| Biased or unrepresentative examples | medium | Diverse examples: |
| Using default temperature for all tasks | medium | Task-appropriate temperature: |
| Not considering prompt injection in user input | high | Defend against injection: |
Related Skills
Works well with: ai-agents-architect, rag-engineer, backend, product-manager
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la462k185k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.379k15.8k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.378k92.5k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.375k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k8FAQ
What prompt sections are recommended?
Role definition, constraints, few-shot examples, and evaluation criteria.
How are tool rules handled?
Separate system behavior instructions from tool usage rules.
What makes a good prompt?
Concise testable sections with measurable success criteria.
Is Prompt Engineer safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.