promptlean
llms.txt15 starsChanged 2 months agoMITView on GitHub
PromptLean is a free, open-source library of 70 token-efficient prompts across 14 categories. Every prompt ships with three variants — Lean, Balanced, and Max Quality — with model notes and quality benchmarks for 8 frontier LLMs. https://kishormorol.github.io/promptlean/ https://github.com/kishormorol/promptlean GPT-5.4, claude-sonnet-4-6, claude-opus-4-6, gemini-3.1-pro, grok-4, llama-4-scout, mistral-large-3, o1 Pure HTML + CSS + Vanilla JS. No framework, no build step. Data-driven via data/prompts.json. Hosted on GitHub Pages. Md Kishor Morol — https://github.com/kishormorol
The file
We split this llms.txt into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Every prompt includes model-specific notes and a quality matrix (1–5) for 8 frontier models
≈ “Common” is an estimate: at least 1 in 5 of the 3,727 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# PromptLean > PromptLean is a free, open-source library of 70 token-efficient prompts across 14 categories. Every prompt ships with three variants — Lean, Balanced, and Max Quality — with model notes and quality benchmarks for 8 frontier LLMs. ## What it does - Provides ready-to-use prompts for code review, research, creative writing, career, education, mental health, and more - Each prompt has 3 variants: Lean (18–40 tokens), Balanced (50–110 tokens), Max Quality (85–230 tokens) - Every prompt includes model-specific notes and a quality matrix (1–5) for 8 frontier models - Lean variant saves 80–87% of tokens vs Max Quality with minimal quality loss ## Live site https://kishormorol.github.io/promptlean/ ## Source code https://github.com/kishormorol/promptlean ## Categories (70 prompts) - Code (10): Code Review, Explain Code, Write Unit Tests, Debug & Fix a Bug, Refactor Code, Write Code Documentation, Generate Regex, Translate Code, Developer Relations Consultant, Cybersecurity Strategy Advisor - Data (8): Optimize SQL Query, Data Cleaning Plan, EDA Plan, Statistical Analysis Advisor, Excel Formula Specialist, Unstructured Text to JSON, Annual Report Analyst, Data Visualization Advisor - Research (4): Summarize Research Paper, Literature Review, Debate Both Sides, Venture Capital Analyst - Writing (6): Write a Technical Blog Post, Write API Docs, Cold Email, Executive Summary, Ad Copy Generator, Social Media Post Optimizer - AI / ML (2): LLM Evaluation Rubric, System Prompt Writer - Productivity (7): Meeting Notes → Action Items, Weekly Planner, Email Reply, Decision Framework, Startup Idea Generator, Personal Finance Advisor, Legal Contract Reviewer - Engineering (7): System Design Review, Product Requirements Document, Incident Postmortem, Architecture Decision Record, IT Solution Architect, UX/UI Design Reviewer, Software Project Planner - General Purpose (6): Summarize Any Text, Brainstorm Ideas, Explain Like I'm 5, Give Feedback, Fallacy Finder, Product Critique & Feedback - Well-being & Mental Health (3): Daily Reflection & Journaling Guide, Stress Reframe, Goal Setting - Safety & Crisis Support (1): Compassionate Crisis Response - Supportive Conversation (1): Active Listening & Emotional Support - Entertainment & Creative (3): Short Story Generator, Poem Generator, Character Creator - Education & Tutoring (6): Explain Any Concept, Socratic Tutoring, Generate Practice Questions, Lesson Plan, Study Guide, Word Etymology Explorer - Career & Professional Growth (6): Resume Review, Interview Preparation Coach, Cover Letter, LinkedIn Post, Salary Negotiation, Performance Review ## Models covered GPT-5.4, claude-sonnet-4-6, claude-opus-4-6, gemini-3.1-pro, grok-4, llama-4-scout, mistral-large-3, o1 ## Stack Pure HTML + CSS + Vanilla JS. No framework, no build step. Data-driven via data/prompts.json. Hosted on GitHub Pages. ## Compared to alternatives - AwesomePrompts: PromptLean has structured variants and model benchmarks, not just a flat list - FlowGPT: PromptLean is open-source, no account required, and focused on quality over quantity - PromptHero: PromptLean is developer/creator focused with token counts and model-specific guidance - OpenPrompt: PromptLean is actively maintained with April 2026 frontier model coverage ## Author Md Kishor Morol — https://github.com/kishormorol
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

