Skip to main content
skill CX Codex

prompt-engineering · 101-skills — Claude Code skill: write better AI prompts

prompt-engineering — a skill that lays out prompt structure for text models, image generators and video models, with examples you can run through the belt CLI.

no license 251 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill prompt-engineering -a claude-code
Open on GitHub

What prompt-engineering does

The skill covers how to build prompts for three kinds of models: text, image and video. LLM sections walk through role assignment, task wording, constraints and output format, then move on to step-by-step reasoning, few-shot examples and system messages. A separate part handles pulling structured JSON out of a text by a given schema.

Image prompts get ordered by subject, style, composition, lighting and technical terms, with a negative prompt passed as its own field. Video prompts add shot type, camera movement and temporal markers. Advanced material shows a prompt growing over several passes, from a plain subject to a styled and technically specified scene.

Every example runs through the inference.sh CLI belt: belt app run openrouter/, falai/flux-dev, google/veo-3-1-fast. The skill's allowed-tools: Bash(belt *) keeps the agent inside that one command. Install the CLI with npx skills add belt-sh/cli and sign in with belt login, otherwise the calls go nowhere and only the prompt advice is left.

What it helps with

  • turn a vague request into a prompt with a clear task and output format
  • make a model return JSON that matches a schema
  • write a negative prompt that drops watermarks and extra limbs
  • describe a camera move for a short video shot
  • add few-shot examples so the output style holds

Example prompts for the agent

  • Rewrite this prompt for a code review task with a role, constraints and an output format.
  • Draft a negative prompt for a headshot on falai/flux-dev and say which words to cut.
  • Check my google/veo-3-1-fast prompt and add a camera move.

How to install prompt-engineering

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill prompt-engineering -a claude-code

2Manually: put the files in place

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

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

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

Questions about prompt-engineering

How do I install prompt-engineering in Claude Code?

Run npx skills add 101-skills/superpowers --skill prompt-engineering -a claude-code. The skill file lands at ~/.claude/skills/prompt-engineering/SKILL.md.

What does prompt-engineering do?

It teaches prompting techniques for LLMs, image generators and video models: roles, few-shot examples, constraints, negative prompts and structured output.

Do the examples need anything besides the skill?

Yes, the belt CLI from inference.sh: install it with npx skills add belt-sh/cli and log in with belt login. The skill only allows Bash(belt *) commands.

Similar skills

All skills for AI and ML →

prompt-engineering by other authors comes first.

prompt-engineering NeoLabHQ prompt-engineering guides prompt design for agents, subagents, and LLM integrations. Helpful when building production templates, chain-of-thought prompts, or agent hooks. CX Codex +1 1,500installs prompt-engineering giuseppe-trisciuoglio The prompt-engineering skill helps write, debug, and test LLM prompts. Use it for few-shot examples, system prompts, reasoning workflows, and reusable templates. CX Codex +1 4,200installs prompt-engineering spencerpauly The prompt-engineering skill explains how to design prompts with examples, constraints, and fixed output formats. It fits code tasks, classification, and response parsing. CX Codex +1 456installs prompt-engineering martinholovsky prompt-engineering is a Claude Code skill with rules and patterns for secure prompt building, injection defense, and LLM response validation. CX Codex +1 228installs prompt-engineering oakoss prompt-engineering is a Claude Code skill for prompt design, covering reasoning chains, ReAct loops, system prompt layouts, extended thinking and context trimming. CX Codex +1 135installs prompt-engineering-patterns Seth Hobson The prompt-engineering-patterns skill helps design, test, and refine prompts for LLM applications. Use it for reusable templates, few-shot examples, and structured responses. CX Codex +1 23,418installs Senior AI & Data Engineering Meta-Prompt Generator mhe931 Senior AI & Data Engineering Meta-Prompt Generator directs your AI model to act as a prompt engineer and produce structured instructions tailored to a target LLM and task. GP ChatGPT ★ 178,201repo stars arize-prompts Arize-ai arize-prompts manages Arize Prompt Hub templates and versioning through the ax CLI. Helps save message transcripts, handle template variables, and manage staging or production labels. CX Codex +1 2,500installs toon-format reason-machines toon-format encodes JSON data into compact TOON syntax to trim prompt tokens by roughly 40%. Helps agents format inputs efficiently for language models. CX Codex +1 1,300installs context-engineering-advisor deanpeters context-engineering-advisor is a Claude Code skill that finds why agent workflows degrade under heavy prompts and helps structure memory retrieval. CX Codex +1 2,800installs prompt-engineering-guidance Orchestra Research prompt-engineering-guidance guides Claude Code in applying Microsoft Research's Guidance framework. It enforces structured LLM output using regular expressions and context-free grammars. CX Codex +1 237installs

From the same set81

The whole set →
p-video-avatar p-video-avatar — a skill for generating talking avatar videos from portrait images via CLI. Built-in text-to-speech, 30 voices, 10 languages, up to 1080p resolution — 18x faster and 6x cheaper than competitors. CX Codex +1 14,400installs ai-content-pipeline ai-content-pipeline — a skill that chains image, video, voice and music generation into one sequence on top of the inference.sh belt CLI. CX Codex +1 270installs video-prompting-guide video-prompting-guide breaks a video prompt into shot, movement, light and style, with phrase tables and per-model notes. For the point where plain descriptions stop working. CX Codex +1 268installs data-visualization data-visualization picks the right chart for your data, sets a palette and axis labels, then renders the figure through the belt CLI. CX Codex +1 255installs explainer-video-guide The explainer-video-guide skill maps an explainer video from script to assembly, with guidance for pacing, scene design, voiceover, and generated visuals. CX Codex +1 249installs logo-design-guide logo-design-guide guides AI agents through logo concept generation and prompt styling via the belt CLI, covering rules from favicon sizes to vectors. CX Codex +1 249installs ai-social-media-content ai-social-media-content produces multi-platform social media posts, videos, voiceovers, and captions via the belt command-line utility. CX Codex +1 248installs ai-music-generation The ai-music-generation skill lets an agent create music and songs through belt and inference.sh. Use it for background tracks, podcast jingles, game scores, and other audio. CX Codex +1 248installs

Project sponsors

Companies that keep this analytics open