prompt-engineering
Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design
- Installs
- 192
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/rohitg00/awesome-claude-code-toolkit --skill prompt-engineering- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads prompt-engineering automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Prompt Engineering
Structured System Prompt
You are a senior code reviewer. Your role is to analyze pull requests for:
1. Correctness - logic errors, edge cases, off-by-one errors
2. Security - injection, authentication, data exposure
3. Performance - N+1 queries, unnecessary allocations, missing indexes
4. Maintainability - naming, complexity, test coverage
For each issue found, respond with:
- Severity: critical | warning | suggestion
- File and line reference
- What is wrong
- How to fix it (with code snippet)
If the code is well-written, say so briefly. Do not invent problems.
Structure system prompts with role, scope, output format, and constraints. Be explicit about what the model should NOT do.
Chain-of-Thought
Analyze this database query for performance issues.
Think step by step:
1. Identify the tables and joins involved
2. Check if appropriate indexes exist for the WHERE and JOIN conditions
3. Look for full table scans or cartesian products
4. Estimate the row count at each step
5. Suggest specific index creation or query restructuring
Query:
SELECT o.*, u.name, p.title
FROM orders o
JOIN users u ON o.user_id = u.id
JOIN products p ON o.product_id = p.id
WHERE o.created_at > '2024-01-01'
AND u.country = 'US'
ORDER BY o.created_at DESC
LIMIT 50;
Chain-of-thought prompting improves accuracy on reasoning tasks by forcing the model to show intermediate steps.
Few-Shot Examples
Convert natural language to SQL. Follow these examples:
Input: "How many orders were placed last month?"
Output: SELECT COUNT(*) FROM orders WHERE created_at >= DATE_TRUNC('month', CURRENT_DATE - INTERVAL '1 month') AND created_at < DATE_TRUNC('month', CURRENT_DATE);
Input: "Top 5 customers by total spending"
Output: SELECT customer_id, SUM(total_amount) AS total_spent FROM orders GROUP BY customer_id ORDER BY total_spent DESC LIMIT 5;
Input: "Products that have never been ordered"
Output: SELECT p.* FROM products p LEFT JOIN order_items oi ON p.id = oi.product_id WHERE oi.id IS NULL;
Now convert:
Input: "Average order value per country for the last quarter"
Provide 3-5 diverse examples that demonstrate the expected format and edge cases.
Tool Use / Function Calling
{
"tools": [
{
"name": "search_codebase",
"description": "Search for code patterns across the repository. Use when you need to find implementations, usages, or definitions.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Regex pattern or keyword to search for"
},
"file_type": {
"type": "string",
"description": "File extension filter (e.g., 'ts', 'py')"
}
},
"required": ["query"]
}
}
]
}
Write tool descriptions that explain WHEN to use the tool, not just what it does.
Prompt Template Pattern
def build_review_prompt(diff: str, context: str, rules: list[str]) -> str:
rules_text = "\n".join(f"- {rule}" for rule in rules)
return f"""Review this code diff against the following rules:
{rules_text}
Context about the codebase:
{context}
Diff to review:
{diff}
Respond with a JSON array of findings. If no issues, return an empty array.
Each finding: {{"severity": "critical|warning|info", "line": number, "message": "string", "suggestion": "string"}}"""
Anti-Patterns
- Vague instructions like "be helpful" or "do your best"
- Asking the model to "be creative" when you need deterministic output
- Not specifying output format (JSON, markdown, plain text)
- Stuffing too many unrelated tasks into a single prompt
- Using negations ("don't do X") without saying what to do instead
- Not testing prompts with adversarial or edge-case inputs
Checklist
- System prompt defines role, scope, format, and constraints
- Chain-of-thought used for multi-step reasoning tasks
- Few-shot examples cover typical and edge cases
- Output format explicitly specified (JSON schema, markdown, etc.)
- Tool descriptions explain when and why to use each tool
- Prompts tested with adversarial inputs
- Temperature and top_p set appropriately for the task
- Prompt templates are parameterized, not hardcoded strings
FAQ
What does the prompt-engineering skill do?
Prompt engineering patterns including structured prompts, chain-of-thought, few-shot learning, and system prompt design
How do I install prompt-engineering?
Run npx skills add https://github.com/rohitg00/awesome-claude-code-toolkit --skill prompt-engineering in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/prompt-engineering/ (personal) or .claude/skills/prompt-engineering/ (project).
Which AI agents can use prompt-engineering?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is prompt-engineering safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains prompt-engineering?
It is published by rohitg00 in rohitg00/awesome-claude-code-toolkit. It has 192 recorded installs.
More from rohitg00/awesome-claude-code-toolkit
devops-automation
rohitg00/awesome-claude-code-toolkit
CI/CD pipeline design with GitHub Actions, Docker, Kubernetes, Helm, and GitOps patterns
accessibility-wcag
rohitg00/awesome-claude-code-toolkit
Web accessibility patterns for WCAG 2.2 compliance including ARIA, keyboard navigation, screen readers, and testing
database-optimization
rohitg00/awesome-claude-code-toolkit
Query optimization, indexing strategies, and database performance tuning for PostgreSQL and MySQL
react-patterns
rohitg00/awesome-claude-code-toolkit
React 19 patterns including Server Components, Actions, Suspense, hooks, and component composition
websocket-realtime
rohitg00/awesome-claude-code-toolkit
Real-time communication patterns with WebSocket, Socket.io, Server-Sent Events, and scaling strategies
python-best-practices
rohitg00/awesome-claude-code-toolkit
Pythonic code with modern type hints, dataclasses, async patterns, packaging, and testing
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available