skill

prompt-engineer · davila7 — Claude Code skill: what it does, how to install

Q: How do I install prompt-engineer in Claude Code?

Run `npx claude-code-templates@latest --skill ai-research/prompt-engineer` in your terminal. Claude Code will immediately make the skill available.

Q: What skills work well alongside prompt-engineer?

It pairs directly with `ai-agents-architect`, `rag-engineer`, `backend`, and `product-manager`.

Designs structured system prompts, few-shot examples, and reasoning chains for LLM apps. Helpful when prompts need rigorous instructions and strict output formats.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill ai-research/prompt-engineer

Open on GitHub

What prompt-engineer does

This skill treats prompts like code. It arranges system instructions into separate blocks: persona, background context, direct instructions, negative constraints, output schema, and demonstrations. This setup keeps models from guessing schemas.

It applies few-shot patterns using 2 to 5 diverse test cases, including edge cases and negative samples. For difficult logic, it configures chain-of-thought prompts to extract intermediate thinking before the answer. Basic programming concepts and tokenization knowledge are required.

Uncurated context degrades prompt performance fast. The skill focuses on removing irrelevant details, setting task-specific temperature, and guarding inputs against prompt injection. Measuring output quality matters.

What it helps with

Structure complex system prompts with negative constraints and clear schemas
Select 2 to 5 balanced few-shot examples covering edge cases
Implement chain-of-thought logic to inspect intermediate reasoning steps
Protect user inputs against prompt injection attacks

Example prompts for the agent

Write a structured system prompt for an API log parser with negative constraints
Build few-shot examples for a classifier handling ambiguous inputs
Add chain-of-thought reasoning to debug our reasoning prompt failures

How to install prompt-engineer

1claude-code-templates

npx claude-code-templates@latest --skill ai-research/prompt-engineer

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill prompt-engineer -a claude-code

3Manually: put the files in place

~/.claude/skills/prompt-engineer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/prompt-engineer/

Manually: put the files in place

.agents/skills/prompt-engineer/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/prompt-engineer/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates prompt-engineer

2Manually: put the files in place

.github/skills/prompt-engineer/SKILL.md

Platform CLI

gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/prompt-engineer

Manually: put the files in place

.devin/skills/prompt-engineer/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about prompt-engineer

How do I install prompt-engineer in Claude Code?

Run npx claude-code-templates@latest --skill ai-research/prompt-engineer in your terminal. Claude Code will immediately make the skill available.

What does the prompt-engineer skill do?

It guides the creation of system prompts, context management, few-shot demonstrations, and chain-of-thought reasoning for LLM applications.

What skills work well alongside prompt-engineer?

It pairs directly with ai-agents-architect, rag-engineer, backend, and product-manager.

Similar skills

All skills for AI and ML →

prompt-engineer by other authors comes first.

prompt-engineer https://github.com/Jeffallan A skill that writes, refactors and tests LLM prompts: templates, JSON schemas, scoring rubrics, test suites. Useful when model output is inconsistent and you need to know why. CX Codex +1 5,600installs prompt-engineer sickn33 Transforms unstructured prompts into structured prompts using frameworks like RTF, RISEN, and Chain of Thought. Helpful when a task needs clearer instructions. CX Codex +1 1,600installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 350,300installs

From the same set495

The whole set →

interactive-portfolio A skill that shapes a personal portfolio so a visitor gets who you are and what you do within seconds. Aimed at developers and designers. 608installs sql-injection-testing A skill that walks an agent through SQL injection testing on web apps: spotting injectable parameters, confirming the flaw, and getting past filters. Meant for pentests you are authorized to run. 605installs web-design-reviewer Walks a running site in the browser, spots layout, responsive and accessibility defects, then fixes them in the source. Saves you a manual click-through of every page. 605installs graphql-performance-optimizer A subagent that digs into slow GraphQL queries: finds N+1 patterns, wires up DataLoader, sets caching. Useful when a user list page drags for seconds. 599installs pr-review This command reviews a pull request from six perspectives, spanning product, engineering, QA, security, DevOps, and UI/UX. It directs the agent to address findings immediately. 562installs nextjs-bundle-analyzer A Claude slash command that breaks down your Next.js bundle size and points at what to trim. 560installs design-rest-api Designs RESTful API architectures, endpoints, authentication flows, and OpenAPI documentation directly from project code. 559installs frontend-dev-guidelines A skill that gives the agent one set of rules for React and TypeScript work: Suspense, lazy loading, features layout, MUI v7 and TanStack. 556installs