AI Tools
Work better with LLMs from both sides: sharpen prompts before you send them, count tokens, then detect, clean, and humanize AI output — plus repair malformed LLM JSON and manage CLAUDE.md files for coding agents. Free, no signup — same as every MarkdownMe tool.
Improve My Prompt
Reviews your prompt (Claude, ChatGPT, Gemini, or any LLM) against 12 rules: explicit role, context ordering, section delimiters, output format, few-shot examples, positive instructions, reasoning behind constraints, step breakdown, quantitative constraints, named audience, structured output, and grounding. Returns a numbered list of specific fixes and an overall score — does NOT rewrite your prompt. Powered by Amazon Nova Micro.
AI Prompt Optimizer (Rewrites Your Prompt)
Turn a vague one-liner into a complete, well-structured prompt you can paste straight into ChatGPT, Claude, or Gemini. The optimizer rewrites your input into six labeled sections — Role, Context, Task, Constraints, Output Format, and few-shot Examples — applying prompt-engineering best practices: XML-style delimiters, outcome-first task framing, positive instructions, quantitative constraints, and grounding. Unlike the Improve My Prompt tool (which critiques your prompt against a checklist and returns feedback), this one hands you the finished, ready-to-use prompt. Built on Amazon Nova, daily-capped to stay free.
Token Counter & Cost Estimator (Claude, GPT, Gemini, Nova)
Paste any text and see token counts + USD cost across every major LLM provider — OpenAI (GPT-5, GPT-4o, o1), Anthropic (Claude Opus 4.5, Sonnet 4.6, Haiku 4.5), Google (Gemini 2.5 Pro/Flash), Amazon (Nova Micro/Lite/Pro), DeepSeek, xAI Grok, Mistral. OpenAI counts are exact (gpt-tokenizer / o200k_base BPE). Other providers use character-based estimates because they don't publish browser-runnable tokenizers — drift is clearly labeled. Choose input-only, output-only, or 50/50 mix; project cost at 1 to 1M calls. All client-side, no signup.
AI Text Detector (Free, In-Browser)
Paste any text and see how likely it was AI-generated, scored 0-100 from 12 transparent, explainable heuristics: sentence-length burstiness, lexical diversity (MATTR), AI vocabulary clustering (delve, tapestry, leverage), em-dash density, negative parallelisms, rule-of-three triplets, transition-phrase density, and more. Every heuristic's contribution is shown so the score is never a black box. 100% client-side — your text never leaves your browser. This is a transparent smell-test, not proof: heuristic detection produces false positives on formal, academic, and non-native-English writing, so never use it for accusations or grading.
Humanize AI Text
Paste ChatGPT, Claude, or Gemini output and get a rewrite that sounds human. Removes AI vocabulary (delve, leverage, robust, tapestry), em-dash overuse, forced rule-of-three triplets, inflated symbolism ('marks a pivotal moment'), promotional language ('nestled, breathtaking'), conversational artifacts ('Certainly!'), and 15+ other patterns identified by Wikipedia's Signs of AI Writing project. Powered by Amazon Nova Micro on AWS. Daily-capped to stay free.
AI Output Cleaner
Paste AI-generated content and instantly remove common artifacts: 'Certainly!' openers, trailing disclaimers, excessive formatting, em dashes, and filler phrases. Makes AI output sound human.
LLM JSON Extractor (ChatGPT, Claude, Gemini)
Paste any LLM response — even one full of prose, markdown headings, code fences, summaries, and commentary — and get back just the JSON it contains, cleaned and valid. Designed for developers building on Claude / ChatGPT / Gemini APIs who need a quick paste-and-fix when JSON-mode isn't enforced. Handles multiple JSON blocks (returns them as an array), Python-style booleans, trailing commas, and the usual LLM output quirks. Built on Amazon Nova Micro.
AI JSON Repair (Fix Broken JSON)
Paste JSON that's almost-but-not-quite valid — from an LLM response, a log file, a half-broken config, or someone's hand-typed mess — and get back clean valid JSON with a visual diff showing exactly what changed. Handles trailing commas, unquoted keys, single quotes, Python True/False/None, JavaScript undefined, comments, surrounding prose, and markdown code fences. Built on Amazon Nova Micro (cheap and fast). Daily-capped to stay free.
CLAUDE.md Generator
Type a short description of your project — stack, deploy target, key dependencies — and get back a polished CLAUDE.md with all six standard sections (overview, tech, file structure, commands, workflows, behavioral rules). Powered by Amazon Nova Micro on AWS Bedrock. Daily-capped to stay free and fast.
CLAUDE.md Reviewer
Claude Code reads your CLAUDE.md every session, so every vague or unused line costs tokens and weakens behavior. Paste your CLAUDE.md and get a numbered audit: missing commands, missing file boundaries, generic rules, over-long explanations, contradictions, and 1-3 rewritten paragraphs you can drop in directly. Continue into AGENTS.md, Cursor, Copilot, and Windsurf formats with the related converter.
CLAUDE.md Converter
Paste your CLAUDE.md (or AGENTS.md, or raw rules) and instantly convert it into the format your other agent tool expects. Handles Claude Code, OpenAI Codex, Cursor, GitHub Copilot, and Windsurf. Preserves sections for markdown targets, extracts imperative rules for flat rule-files. Download or copy. No upload, all client-side.