Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add KirKruglov/claude-skills-kit --skill prompt-buildergit clone --depth 1 https://github.com/KirKruglov/claude-skills-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kirkruglov/claude-skills-kit/prompt-builder)<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/prompt-builder"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/prompt-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/prompt-builder"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/prompt-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01734 |
| Opus 5 | $0.00036 | $0.00867 |
| Sonnet 5 | $0.00014 | $0.00347 |
| Haiku 4.5 | $0.00007 | $0.00173 |
Grade A, and why
prompt-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Builder
An interactive generator that builds structured prompts for Claude based on the user's task description. The skill asks 7 questions, interprets loose or vague answers, clarifies details, and assembles a ready-to-use prompt from a universal template.
Suitable for anyone who needs to create a reusable, well-structured prompt for Claude — for code review, content writing, data analysis, or any other repeatable task.
Language Detection
Detect the language of the user's first message:
- If the message is in Russian — conduct the entire interview and output the final prompt in Russian.
- If the message is in English — conduct the entire interview and output the final prompt in English.
- If the language is ambiguous, default to English.
All question texts, labels, and output section headers must match the detected language.
Input
A natural-language description from the user of what they want the prompt to accomplish. Can be brief ("I need a prompt for code review") or detailed.
Output
A structured prompt document with sections: Role, Context, Task, Input data, Output requirements, Constraints, and optionally Examples. Displayed in chat and optionally saved as a .md file.
Instructions
Step 1: Interactive interview
Ask questions in the order below. Wait for the user's answer after each question before proceeding.
Rules:
- User answers may be unstructured or vague — interpret the intent
- If an answer is unclear or incomplete, ask a clarifying question
- Do not move to the next item until you have enough information
- Collect answers into variables for final generation
Question 1: Claude's role
EN: "What role should Claude take on in this task? (E.g.: analyst, writer, tester, coder, etc.) Describe what it will do in general terms."
RU: "Какую роль должен взять на себя Claude в этой задаче? (Например: аналитик, писатель, тестировщик, кодер и т.д.) Опиши, что он будет делать в общих чертах."
Action: Interpret the answer, extract the role and core function. If the answer is too broad, ask: "If I understood correctly, Claude should act as [your interpretation]? Confirm or clarify?"
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 206 lines · 72 tokens per session scan A a90956f2a990
prompt-builder is a skill published in the GitHub repository KirKruglov/claude-skills-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,734 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
happyhorse-prompt-studio
Interactive prompt studio for HappyHorse 1.0 video generation. Guides users through scenario discovery with vivid examples, then assembles production-ready prompts in JP/CN/EN. Use when someone wants to create AI video content with HappyHorse but doesn't know where to start, or when they have a specific scenario and…
llm-prompt-optimizer
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage.
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
llm-application-dev-prompt-optimize
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-wrapper-product
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc. ) into focused tools people will pay for. Not just "ChatGPT but different" - products that solve specific problems with AI.