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-library-curatorgit 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-library-curator)<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/prompt-library-curator"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/prompt-library-curator/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-library-curator"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/prompt-library-curator.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 | $0.00095 | $0.01815 |
| Opus 5 | $0.00048 | $0.00907 |
| Sonnet 5 | $0.00019 | $0.00363 |
| Haiku 4.5 | $0.00010 | $0.00181 |
Grade A, and why
prompt-library-curator 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 Library Curator
This skill organises a personal collection of saved prompts into a structured, navigable markdown catalog. It assigns categories, tags, summaries, and complexity ratings to each prompt, detects duplicates, and outputs a clean prompt-library.md file ready for reuse and sharing.
Input:
- Raw prompts as pasted text, an inline list, or a
.md/.txtfile
Output:
prompt-library.md— structured catalog with index table, categorised prompts, and flagged duplicates
Language Detection
Detect the user's language from their message:
- If Russian (or contains Cyrillic): respond in Russian, use Russian category names in output, and generate the entire catalog in Russian
- If English (or other Latin-script language): respond in English, use English category names, and generate the entire catalog in English
- If ambiguous: respond in the language of the trigger phrase used and generate catalog in that language
Instructions
Step 1: Accept and Validate Input
-
Determine input source:
- Pasted text block in chat
- Uploaded or referenced
.md/.txtfile - Inline numbered or bulleted list
-
Validate input is non-empty
- If empty: stop and respond — "No prompts found. Paste your prompts directly or attach a .md/.txt file."
-
Check for unsupported file formats (
.docx,.xlsx,.pdf, etc.)- If detected: stop and respond — "Unsupported format. Please paste your prompts as plain text or upload a .md or .txt file."
-
Check if input looks like a conversation log rather than a prompt collection
- Heuristic: high ratio of questions and conversational turns with no clear prompt-style structure
- If detected: respond — "This looks like a chat log, not a prompt collection. Paste the prompt texts you want to organise, or specify which lines are prompts."
Step 2: Split into Individual Prompts
- Attempt to split the raw input into individual prompts using these separator heuristics (in priority order):
- Horizontal rules (
---) - Numbered list items (
1.,2., etc.) - Blank-line-separated paragraphs
- Double newlines
- Horizontal rules (
What ships with it
4 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 · 95 tokens per session scan A 665b704c1f53
prompt-library-curator is a skill published in the GitHub repository KirKruglov/claude-skills-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 95 tokens to every session and 1,815 once invoked, about $0.0005 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.