# Daniel Rosehill: for AI agents # agents.danielrosehill.com — generated at build time, 22 October 2026 ## Site identity name: Daniel Rosehill url: https://agents.danielrosehill.com type: agent-facing index of a person and his work main_site: https://danielrosehill.com ai_site: https://ai.danielrosehill.com contact: https://agents.danielrosehill.com/contact.json agent_skills: https://agents.danielrosehill.com/.well-known/agent-skills/index.json mcp_server: https://mcp.danielrosehill.com/mcp ## Description Daniel Rosehill is an agentic-AI systems builder and technical communicator in Jerusalem, Israel: multi-agent orchestration, Claude Code workflows and MCP servers, plus speech-to-text, English–Hebrew code-switching ("Hebrish"), accessibility and AI for education. He publishes models and datasets on Hugging Face, a public Claude Code plugin marketplace (177 plugins in 17 categories) and My Weird Prompts, a daily AI-generated podcast (nearly 6,000 episodes). This site is the place for an agent to start. Everything below is static, public and needs no account or API key. Prefer the JSON endpoints over scraping HTML. ## Endpoints on this site https://agents.danielrosehill.com/llms.txt (text/plain): Concise overview: who Daniel is, where everything lives, what an agent can do. Start here. https://agents.danielrosehill.com/llms-full.txt (text/plain): Long form: bio, every model and dataset card, plugin categories, contact fields. https://agents.danielrosehill.com/ai.json (application/json): AI focus areas, flagship work, model and dataset cards, the Hebrish series and leaderboard, benchmarks, Hugging Face items, podcast figures. https://agents.danielrosehill.com/plugins.json (application/json): Every plugin in the public Claude Code marketplace, by category, with install commands. https://agents.danielrosehill.com/projects.json (application/json): Compact index of public GitHub repos and gists and Hugging Face models, datasets, Spaces and collections (forks excluded). https://agents.danielrosehill.com/skills.json (application/json): Agent Skills hosted here (with digests), the Start-Here exploration skills, the plugin marketplace and skill directories. https://agents.danielrosehill.com/contact.json (application/json): How to contact Daniel or request a meeting without an account: endpoint, fields, spam rules, prefill links, MCP server. https://agents.danielrosehill.com/.well-known/agent-skills/index.json (application/json): Agent Skills discovery index (draft v0.2.0) with sha256 digests. /agent-skills redirects here. https://agents.danielrosehill.com/.well-known/agent-skills//SKILL.md (text/markdown): The skills themselves: contact-daniel, book-meeting-with-daniel, about-daniel. https://agents.danielrosehill.com/md/about.md (text/markdown): Bio and profiles as plain Markdown. https://agents.danielrosehill.com/md/ai.md (text/markdown): AI work as Markdown: focus areas, models, datasets, benchmarks, podcast. https://agents.danielrosehill.com/md/plugins.md (text/markdown): The plugin marketplace as Markdown, by category. https://agents.danielrosehill.com/md/contact.md (text/markdown): Contact and meeting requests as Markdown. https://agents.danielrosehill.com/robots.txt (text/plain): Allows all crawlers; points to the sitemap. https://agents.danielrosehill.com/sitemap-index.xml (application/xml): Sitemap of this site, endpoints included. ## AI work (ai.danielrosehill.com) https://ai.danielrosehill.com/ → AI hub: focus areas, flagship work, every Hugging Face model and dataset, My Weird Prompts https://ai.danielrosehill.com/models → Model showcase: the Hebrish series, stock-vs-Hebrish examples, the public code-switching leaderboard, the dictation toolkit, every Hugging Face model https://ai.danielrosehill.com/datasets → Dataset card pages, then every Hugging Face dataset https://ai.danielrosehill.com/benchmarks → Benchmarks and AI safety evals (results first) https://ai.danielrosehill.com/hugging-face → Every model, dataset, Space and collection across danielrosehill and the Hebrish org https://ai.danielrosehill.com/plugins → The Claude Code plugin marketplace, by category https://ai.danielrosehill.com/skills → Agent skills: the marketplace, Start-Here exploration skills, listings on skills.sh and AgentSkills.co.il https://ai.danielrosehill.com/projects → Projects ### Model cards https://ai.danielrosehill.com/models/parakeet-english-hebrew-codeswitching → Hebrish (Jachnun v1.0): Parakeet TDT 0.6B v2 for English–Hebrew code-switching (2026-10-19): Speech-to-text that gets the Hebrew words right when an English speaker in Israel drops them into English: "pick up some bamba from the makolet". https://ai.danielrosehill.com/models/parakeet-tdt-v2-english-hebrew-all-subsets → Hebrish (Sabich v1.0): Parakeet TDT 0.6B v2 for code-switching plus tech dictation (2026-10-20): The recommended Hebrish model: everything Jachnun was trained on, plus tech vocabulary, brand names, acronyms, numbers and currency, Irish-English phrasing and the rest of my task recordings. Gated, access by request. https://ai.danielrosehill.com/models/parakeet-tdt-v2-tech-and-accent → Boxty v1.0: Parakeet TDT 0.6B v2 for English and tech dictation (2026-10-20): English dictation without Hebrew, in my voice: model and product names, CLI and cloud terms, brands, acronyms, and numbers and currency in digits. Gated, access by request. https://ai.danielrosehill.com/models/hebrew-latin-token-classifier → Hebrew-Latin Token Classifier: finds Hebrew written in Latin letters (2026-10-15): Finds Hebrew words written in Latin letters inside English text, so text-to-speech can hand them to a Hebrew voice instead of reading makolet as English. There was no model for this before. https://ai.danielrosehill.com/models/gemma-3-270m-asr-paragraph-breaks → Gemma 3 270M ASR Paragraph Breaks: paragraphs for dictated text (2026-10-20): Adds paragraph breaks to flat speech-to-text output and changes nothing else. Small enough to run on a phone after the speech model. https://ai.danielrosehill.com/models/gemma-3-270m-email-key-line-bolding → Gemma 3 270M Email Key-Line Bolding: bold the key lines of a dictated email (2026-10-21): Puts the key parts of a dictated email in Markdown bold and changes nothing else. Runs after the paragraph-breaks model. https://ai.danielrosehill.com/models/proximate-pseudonymizer-0.6b → Proximate Pseudonymizer 0.6B: swap identifying details for close, consistent substitutes (2026-10-21): Rewrites a text with its names, places, organisations, dates and contacts swapped for close, plausible substitutes, the same one every time. Proof of concept: it still leaves 9.3% of identifying details unchanged. https://ai.danielrosehill.com/models/sabich-qwen3-asr-1.7b → Hebrish (Sabich-Qwen3-ASR-1.7B v1.0): Sabich on Qwen3-ASR 1.7B for desktop GPUs (2026-10-21): The most accurate Sabich: the same code-switching and tech data, trained on Qwen3-ASR 1.7B, an ASR model with an LLM decoder, for computers with a GPU. Gated, access by request. https://ai.danielrosehill.com/models/shakshuka-nemotron-streaming → Hebrish (Shakshuka v1.0): Nemotron streaming fine-tune for code-switching plus tech dictation (2026-10-21): The streaming line of Hebrish: text appears while you speak, trained on the same everything-in-it recordings as Sabich. Gated, access by request. ### Dataset cards https://ai.danielrosehill.com/datasets/english-hebrew-codeswitching-sentences → English–Hebrew Code-Switching Sentences: English sentences with everyday Hebrew words and Israeli names written in Latin letters, read aloud on a phone by one English speaker living in Israel. https://ai.danielrosehill.com/datasets/read-aloud-voice-sentences → Read-Aloud Voice Sentences: Every take recorded for the Hebrish speech models: read-aloud English sentences with Hebrew words, tech vocabulary, names, emails and messages, recorded on a phone and published in batches straight from the capture app. https://ai.danielrosehill.com/datasets/english-hebrew-codeswitching-asr-benchmark → English–Hebrew Code-Switching ASR Benchmark: A frozen, versioned test set for scoring how well speech recognition writes the Hebrew words in English speech, "pick up some bamba from the makolet", with stock models and fine-tunes scored the same way on a public leaderboard. https://ai.danielrosehill.com/datasets/hebrew-latin-code-switching → Hebrew-in-Latin Code-Switching Corpus: English sentences with Hebrew words written in Latin letters, every Hebrew span marked token by token, for finding those words in text before text-to-speech mispronounces them. No corpus like it had been published. ### Flagship work - Hebrish (Sabich v1.0): Parakeet code-switching plus tech dictation: https://huggingface.co/Hebrish/Sabich (card: https://ai.danielrosehill.com/models/parakeet-tdt-v2-english-hebrew-all-subsets) - Hebrish (Jachnun v1.0): Parakeet English–Hebrew code-switching: https://huggingface.co/Hebrish/Jachnun (card: https://ai.danielrosehill.com/models/parakeet-english-hebrew-codeswitching) - Boxty v1.0: Parakeet English and tech dictation: https://huggingface.co/Hebrish/Parakeet-TDT-0.6B-v2-Tech-And-Accent (card: https://ai.danielrosehill.com/models/parakeet-tdt-v2-tech-and-accent) - English–Hebrew code-switching ASR benchmark: https://huggingface.co/spaces/danielrosehill/English-Hebrew-Codeswitching-ASR-Leaderboard - Hebrish Keyboard: https://github.com/Hebrish-ASR/Hebrish-Keyboard - ASR Dataset Blender: https://huggingface.co/spaces/danielrosehill/ASR-Dataset-Blender - The PC Bench: https://github.com/danielrosehill/The-PC-Bench - Propaganda Bait Eval: https://github.com/danielrosehill/Propaganda-Bait-Eval - Whisper Hebrish: https://huggingface.co/danielrosehill/Whisper-Hebrish - Whisper Hebrish demo: https://huggingface.co/spaces/danielrosehill/Whisper-Hebrish - Hebrew-in-Latin token classifier: https://huggingface.co/Hebrish/Hebrew-Latin-Token-Classifier (card: https://ai.danielrosehill.com/models/hebrew-latin-token-classifier) - Gemma 3 270M ASR Paragraph Breaks: https://huggingface.co/danielrosehill/Gemma-3-270M-ASR-Paragraph-Breaks (card: https://ai.danielrosehill.com/models/gemma-3-270m-asr-paragraph-breaks) - Gemma 3 270M Email Key-Line Bolding: https://huggingface.co/danielrosehill/Gemma-3-270M-Email-Key-Line-Bolding (card: https://ai.danielrosehill.com/models/gemma-3-270m-email-key-line-bolding) - Proximate Pseudonymizer 0.6B: https://huggingface.co/danielrosehill/Proximate-Pseudonymizer-0.6B (card: https://ai.danielrosehill.com/models/proximate-pseudonymizer-0.6b) - LLM Spoken Steganography: https://huggingface.co/spaces/danielrosehill/LLM-Spoken-Steganography - Pseudo-Personalised Spam Classifier: https://github.com/danielrosehill/Pseudo-Personalised-Spam-Classifier - Hebrew-in-Latin code-switching corpus: https://huggingface.co/datasets/Hebrish/hebrew-latin-code-switching (card: https://ai.danielrosehill.com/datasets/hebrew-latin-code-switching) - English–Hebrew Code-Switching Sentences: https://huggingface.co/datasets/danielrosehill/English-Hebrew-Codeswitching-Sentences (card: https://ai.danielrosehill.com/datasets/english-hebrew-codeswitching-sentences) - English–Hebrew Mixed Sentences: https://huggingface.co/datasets/danielrosehill/English-Hebrew-Mixed-Sentences - Read-Aloud Voice Sentences: https://huggingface.co/datasets/danielrosehill/Read-Aloud-Voice-Sentences (card: https://ai.danielrosehill.com/datasets/read-aloud-voice-sentences) - Tech Sentences: https://huggingface.co/datasets/danielrosehill/Tech-Sentences - Whisper Hebrish (large-v3-turbo): https://huggingface.co/collections/danielrosehill/whisper-hebrish-691bc2624553319eb727c1db - Whisper Hebrish Small ACFT: https://huggingface.co/Hebrish/Whisper-Hebrish-Small-ACFT - On-device ASR on the OnePlus Nord 3: https://huggingface.co/collections/danielrosehill/on-device-asr-one-plus-cph2493-nord-3 - Android voice keyboard roundup: https://github.com/danielrosehill/Android-Voice-Keyboard-Roundup - Noisy Voice Notes: https://huggingface.co/datasets/danielrosehill/Noisy-Voice-Notes - ASR WPM & background noise eval: https://huggingface.co/datasets/danielrosehill/ASR-WPM-And-Background-Noise-Eval - Transcription Cleanup Trainer: https://huggingface.co/datasets/danielrosehill/Transcription-Cleanup-Trainer - Code Tutor Agent: https://github.com/danielrosehill/Code-Tutor-Agent-Model - Vibe Code And Learn: https://github.com/danielrosehill/Vibe-Code-And-Learn ### Hebrish (https://hebrish.app) The Hebrish model series, as listed on hebrish.app (checked 2026-10-21): In the Hebrish apps: - Sabich v1.0 [Recommended] (NVIDIA Parakeet TDT 0.6B v2): https://ai.danielrosehill.com/models/parakeet-tdt-v2-english-hebrew-all-subsets - Jachnun v1.0 (NVIDIA Parakeet TDT 0.6B v2): https://ai.danielrosehill.com/models/parakeet-english-hebrew-codeswitching Sabich on other bases: - Sabich-Qwen3-ASR-1.7B v1.0 [Desktop GPU] (Qwen Qwen3-ASR 1.7B): https://ai.danielrosehill.com/models/sabich-qwen3-asr-1.7b - Sabich-Canary-Qwen-2.5B v1.0 [Desktop GPU] (NVIDIA Canary-Qwen 2.5B): https://hebrish.app/models/sabich-canary-qwen - Sabich-Parakeet-110M v1.0 [Small devices] (NVIDIA Parakeet TDT-CTC 110M): https://hebrish.app/models/sabich-110m - Sabich-asr4all -S and -M v1.0 [Wearables] (FUTO asr4all S and M): https://hebrish.app/models/sabich-asr4all Streaming and Whisper: - Shakshuka v1.0 [Streaming] (NVIDIA Nemotron Speech Streaming EN 0.6B): https://ai.danielrosehill.com/models/shakshuka-nemotron-streaming - Whisper Hebrish Small ACFT small-en-en30-acft (OpenAI Whisper small.en): https://hebrish.app/models/whisper-small - Whisper Hebrish Version 2 (OpenAI Whisper large-v3-turbo): https://hebrish.app/models/whisper-turbo - Meorav PoC-1 [POC] (Qwen Qwen3-TTS 12Hz 1.7B Base): https://hebrish.app/models/meorav Text: - Hebrew-Latin Token Classifier v1 [Small model] (Meta XLM-RoBERTa base): https://ai.danielrosehill.com/models/hebrew-latin-token-classifier Leaderboard: https://huggingface.co/spaces/danielrosehill/English-Hebrew-Codeswitching-ASR-Leaderboard (test set v1, clean subset: 84 clips, 172 Hebrew term occurrences) ### Benchmarks Registry: https://github.com/danielrosehill/My-Benchmarks · browsable: https://huggingface.co/spaces/danielrosehill/My-Benchmarks · page: https://ai.danielrosehill.com/benchmarks - English–Hebrew Code-Switching ASR Benchmark (speech, results): Speech-to-text on English speech that contains Hebrew words: a frozen test set, runner, scorer and public leaderboard, comparing stock models with code-switching fine-tunes. https://github.com/Hebrish-ASR/English-Hebrew-Codeswitching-ASR-Benchmark - The PC Bench (behaviour, prompts): Does the model scold you? Measures lecturing, moralising, terminology correction and unrequested disclaimers on legitimate requests. 24 mirrored pairs (Western-progressive vs conservative/religious triggers) plus neutral controls. https://github.com/danielrosehill/The-PC-Bench - Propaganda Bait Eval (behaviour, built): Feeds models loaded political premises across six series (CCP, MAGA, pro-Israel, pro-Palestine, Kremlin, US-progressive) and scores how readily each framing is repeated, with per-series selectivity. https://github.com/danielrosehill/Propaganda-Bait-Eval - Conspiracy Endorsement Eval (behaviour, results): Whether a model pushes back on, endorses or encourages 45 conspiracy theories, each asked in a curious and a believer framing. First hand-graded run (on-air-01): 7 models. https://github.com/danielrosehill/Conspiracy-Endorsement-Eval - Israel–Palestine Framing Eval (behaviour, results): Whether a model treats mirrored pro-Israel and pro-Palestinian framings of the same events differently: loaded premises, framing pairs and open-neutral questions. First graded run (on-air-01): 6 models. https://github.com/danielrosehill/Israel-Palestine-Framing-Eval - Audio Understanding Bitrate Eval (speech, results): How MP3 bitrate affects transcription accuracy across every audio-input LLM on OpenRouter. https://github.com/danielrosehill/Audio-Understanding-Bitrate-Eval-0426 - Whisper Fine-Tune Accuracy Eval (speech, results): WER of personal Whisper fine-tunes vs stock Whisper at each model size. Fine-tuning helped the small models, hurt the large ones, and improved code-switching at every size. https://github.com/danielrosehill/Whisper-Fine-Tune-Accuracy-Eval - Whisper WPM & Background Noise Eval (speech, results): How speaking pace and background noise affect ASR word error rate. https://github.com/danielrosehill/Whisper-WPM-Background-Noise-Eval - Long-Form Audio Eval (speech, results): STT models on a 27-minute podcast against a professional reference transcript: WER, CER and punctuation accuracy. https://github.com/danielrosehill/Long-Form-Audio-Eval - One-Shot Transcription Microphone Eval (speech, results): STT accuracy across a range of microphones recording the same material. https://github.com/danielrosehill/One-Shot-Transcription-Microphone-Eval - Transcription Cleanup Eval (speech, results): Cloud audio-multimodal models transcribing and cleaning up a recording in one step. Subjective grading. https://github.com/danielrosehill/Transcription-Cleanup-Eval-1225 - Local ASR STT Benchmark (speech, results): Whisper model sizes in Speech Note on Ubuntu with AMD/ROCm. A rough first-pass comparison. https://github.com/danielrosehill/Local-ASR-STT-Benchmark - Hebrew Image Generation Eval (image, results): Twelve text-to-image models scored pass/fail on rendering Hebrew text correctly. https://github.com/danielrosehill/Hebrew-Image-Generation-Eval - Gemma 4 Benchmarks (hardware, results): Gemma 4 E4B vs Qwen3-VL 8B via Ollama on a CPU-only i7-12700F with 64 GB RAM. https://github.com/danielrosehill/Gemma-4-Benchmarks-0426 - Workstation Benchmarks (hardware, results): Desktop workstation benchmarks (i7-12700F, RX 7700 XT, 64 GB DDR5, Ubuntu 25.10) with the full system inventory. https://github.com/danielrosehill/Workstation-Benchmarks-0226 ### My Weird Prompts (podcast) A daily AI-generated podcast. I send in a question as a voice prompt, and an AI pipeline researches it, writes the script and voices the hosts, Corn the sloth and Herman the donkey. Topics run from AI and technology to geopolitics, health and history. 5,862 episodes published as of 14 October 2026. Podtrac (IAB-certified) as of 13 October 2026: 89,978 all-time downloads; 14,847 downloads and 2,274 unique listeners in the last 30 days (1,131 in the US). Podtrac does not count Spotify plays, so these figures understate the total audience. url: https://www.myweirdprompts.com ## Claude Code plugin marketplace 177 plugins in 17 categories (as of 2026-10-22). add: /plugin marketplace add https://github.com/danielrosehill/Claude-Code-Plugins install: /plugin install @danielrosehill categories: Linux Sysadmin (30), Personal Productivity (19), Media Editing (16), Research & Learning (16), AI & Context (14), Documentation & Writing (14), Repo Scaffolding & Retrofitting (12), Privacy & Security (8), Data & Datasets (7), Marketing & Shopping (7), Network & Smart Home (7), Regional (7), Git & GitHub (5), QA & Agent Sessions (5), Hardware & Maker (4), Data Discovery (3), Publishing & CMS (3) full list: https://agents.danielrosehill.com/plugins.json ## Agent Skills SKILL.md files (Agent Skills format). Index with sha256 digests, discovery draft v0.2.0: https://agents.danielrosehill.com/.well-known/agent-skills/index.json - about-daniel: Answer questions about Daniel Rosehill (AI developer and technical communicator, Jerusalem, Israel; danielrosehill.com) and find his work - GitHub repositories, Hugging Face models and datasets, system prompts, the My Weird Prompts podcast, his CV and other websites. Use when a user asks who Daniel Rosehill is, what he works on, or for a specific project, model, dataset or prompt of his. Read-only and unauthenticated. https://agents.danielrosehill.com/.well-known/agent-skills/about-daniel/SKILL.md - book-meeting-with-daniel: Request a video or phone call with Daniel Rosehill (AI developer and technical communicator, Jerusalem, Israel; danielrosehill.com) on a user's behalf, or give the user a prefilled booking link. Use when a user wants to book, schedule or set up a meeting, call or chat with Daniel Rosehill. Unauthenticated - no account or API key needed. https://agents.danielrosehill.com/.well-known/agent-skills/book-meeting-with-daniel/SKILL.md - contact-daniel: Send a message to Daniel Rosehill (AI developer and technical communicator, Jerusalem, Israel; danielrosehill.com) on a user's behalf, or tell the user how to reach him. Use when a user wants to contact, email, enquire with or send a note to Daniel Rosehill. Unauthenticated - no account or API key needed. https://agents.danielrosehill.com/.well-known/agent-skills/contact-daniel/SKILL.md ## Unauthenticated actions Both send email to a real person: confirm the content with your user first, and send once. contact_email: public@danielrosehill.com contact_endpoint: POST https://www.danielrosehill.com/api/contact (form data; fields: https://agents.danielrosehill.com/contact.json) contact_form_prefill: https://www.danielrosehill.com/contact/form?name=&email=&contactType=&subject=&message= meeting_request: same endpoint with formType=Meeting request meeting_form_prefill: https://www.danielrosehill.com/book-meeting?name=&email=&meetingFormat=&duration=&preferredTimes=&timezone=&topic= Meetings are requested, not instantly booked: the user proposes times and Daniel replies by email with a calendar invitation. ## MCP server Public remote MCP server (streamable HTTP, no authentication). Tools: about_daniel, ask_about_daniel, get_resume, download_cv, search_projects, get_blog_posts, get_recommendations, send_message, request_meeting. mcp_server: https://mcp.danielrosehill.com/mcp mcp_page: https://danielrosehill.com/contact/mcp-server ## WebMCP (on danielrosehill.com) Every page on danielrosehill.com registers read-only WebMCP tools on document.modelContext for browser agents. List: https://danielrosehill.com/contact/for-agents#webmcp ## Main site (danielrosehill.com) https://danielrosehill.com/ → Homepage and introduction https://danielrosehill.com/about → Professional background and expertise https://danielrosehill.com/about/cv → CV and professional history https://danielrosehill.com/he → Hebrew bio (עברית) https://danielrosehill.com/contact → Contact information and forms https://danielrosehill.com/contact/for-agents → Agent hub on the main site (WebMCP tools, skills) https://danielrosehill.com/projects → All projects, with Hebrish as the flagship https://danielrosehill.com/projects/apps → Apps: F-Droid repo and signed APT repo for Linux .deb packages https://danielrosehill.com/projects/ai-tools → AI tools library: agents, workflows, assistants https://danielrosehill.com/system-prompts → About 1,300 public system prompts https://danielrosehill.com/github → GitHub repositories index https://danielrosehill.com/blogs → Blog posts and articles https://danielrosehill.com/content → Writing, videos, photos, digital art, audio https://danielrosehill.com/work → Work with me https://danielrosehill.com/consulting → Consulting services https://danielrosehill.com/sitemap → HTML sitemap ## External profiles github: https://github.com/danielrosehill huggingface: https://huggingface.co/danielrosehill hebrish_org: https://huggingface.co/Hebrish npm: https://www.npmjs.com/~danielrosehill linkedin: https://www.linkedin.com/in/danielrosehill youtube: https://www.youtube.com/channel/UCFhEM_Jl3uKV6b8Ex4wbiFQ devto: https://dev.to/danielrosehill bluesky: https://bsky.app/profile/danielrosehill.bsky.social blog: https://blog.danielrosehill.com ## Business business_name: DSR Holdings business_url: https://dsrholdings.cloud consultancy_name: Carrot Cake AI (AI consultancy, part of DSR Holdings) consultancy_url: https://carrotcakeai.com ## Content licensing license: CC BY-SA 4.0 ai_training: allowed ai_indexing: allowed attribution: appreciated ## Discovery files llms_txt: https://agents.danielrosehill.com/llms.txt llms_full_txt: https://agents.danielrosehill.com/llms-full.txt sitemap_xml: https://agents.danielrosehill.com/sitemap-index.xml robots_txt: https://agents.danielrosehill.com/robots.txt main_site_llms_txt: https://danielrosehill.com/llms.txt main_site_ai_txt: https://danielrosehill.com/ai.txt main_site_rss: https://danielrosehill.com/rss.xml