[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77Z0JNP8183HTW2PVY80TGW":3,"skill-same:01M77Z0JNP8183HTW2PVY80TGW":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M77Z0JNP8183HTW2PVY80TGW","youos",null,"YouOS — local-first personal email copilot that learns your writing style from Gmail, Google Docs, and WhatsApp exports, then drafts replies in your voice. Use for drafting replies, reviewing how you usually respond, and running a self-improving personal communication workflow.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fy\u002Fyouos\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: youos\ndescription: >\n  YouOS — local-first personal email copilot that learns your writing style from Gmail,\n  Google Docs, and WhatsApp exports, then drafts replies in your voice. Use for drafting\n  replies, reviewing how you usually respond, and running a self-improving personal\n  communication workflow.\nmetadata:\n  openclaw:\n    requires:\n      bins: [\"python3\", \"gog\"]\n      platform: darwin\n      arch: arm64\n      minRam: \"8GB\"\n    install:\n      - kind: instructions\n        label: \"Manual install required\"\n        steps:\n          - \".\u002Fscripts\u002Finstall.sh\"\n          - \"source .venv\u002Fbin\u002Factivate\"\n          - \"youos setup\"\n    credentials:\n      required:\n        - \"A Google ingestion backend for Gmail\u002FDocs (set ingestion.google_backend): gog CLI authenticated (default), Google's gws CLI authenticated, or the native Google-API backend (pip install youos[google] + OAuth)\"\n      optional:\n        - \"Claude CLI\u002FAPI credentials only if model.fallback uses external provider\"\n    privacy:\n      localStorage:\n        - \"SQLite DB under YOUOS_DATA_DIR\u002Fvar\u002Fyouos.db (or local var\u002Fyouos.db)\"\n      networkEgress:\n        - \"None by default for local mode\"\n        - \"Optional outbound requests when external fallback is enabled\"\n---\n\n# YouOS — Personal Email Copilot\n\nYouOS is a full local Python app (not an instruction-only snippet). It drafts email replies in your style, grounded in your real past replies.\n\n**Naming:** *YouOS* is the shared app\u002Fpackage. During setup it personalizes its name to *\u003CFirst>OS* (e.g. **BaherOS**) for **your local instance** at `YOUOS_DATA_DIR=~\u002FYouOS-Instances\u002F\u003Cyou>\u002F` — that's a local config\u002Fdata directory, not a fork of the project.\n\n## Safety & impact\n\nRead these before installing:\n\n- **Sensitive data ingested locally.** YouOS reads your Gmail (sent + threads), Google Docs, and optional WhatsApp exports into a local SQLite DB. This stays on your machine, but it *is* sensitive content — protect the data directory (`YOUOS_DATA_DIR\u002Fvar\u002Fyouos.db`) accordingly.\n- **Installation runs local package code.** `.\u002Fscripts\u002Finstall.sh` builds a `.venv` and installs this repository — review the source (especially `scripts\u002Finstall.sh`, `pyproject.toml`, `app\u002F`) before running.\n- **Background persistence is opt-in.** YouOS only runs as a launchd LaunchAgent if you explicitly run `youos service install`. Foreground `youos serve` does not persist.\n- **Scheduled\u002Fnightly runs are opt-in.** Ingestion, fine-tuning, and autoresearch only run automatically if you've enabled the nightly pipeline; `youos improve` is the manual equivalent.\n- **External model fallback is optional.** Drafting is on-device by default. Cloud fallback only fires if `review.draft_model` or `model.fallback` is set to a cloud model — set `model.fallback: none` and `review.draft_model: local` for strict local-only operation.\n\n## Install and runtime model\n\n- Install is **manual**: run `.\u002Fscripts\u002Finstall.sh` (Python 3.11+) — it creates a `.venv`, installs YouOS, sets up the on-device model (**MLX**) on Apple Silicon, and runs the doctor\n- Note: this executes local package install code from this repository; review source before installing\n- Requires `python3` (3.11+) and a Google ingestion backend — `gog` (default), `gws`, or native (see Credentials)\n- Drafts run on your **fine-tuned local model by default** (Qwen + your LoRA, served warm); the cloud is only a cold-start before your model is trained, or a fallback\n- Optional runtime path override: `YOUOS_DATA_DIR`\n\n## Credentials and configuration\n\n- Required: a Google ingestion backend for Gmail\u002FDocs — `gog` (default), `gws`, or native (`youos[google]` + OAuth); set `ingestion.google_backend`\n- Optional: Claude CLI\u002FAPI credentials only for the cold-start\u002Ffallback (`review.draft_model` \u002F `model.fallback`)\n- For strict local-only: set `review.draft_model: local` and `model.fallback: none`\n\n## Trigger phrases\n\n- \"draft a reply to this email\"\n- \"write this email for me\"\n- \"how would I respond to this\"\n- \"what would I say to\"\n- \"help me reply\"\n- \"draft in my style\"\n- \"youos\"\n- \"my email copilot\"\n- \"email copilot\"\n- \"my copilot\"\n- \"generate a draft\"\n- \"reply draft\" \u002F \"email draft\" \u002F \"draft reply\"\n- \"compose reply\"\n- \"write a response\"\n- \"email response\"\n- \"how do I usually reply to\"\n- \"reply to this\"\n- \"help me write\"\n- \"write an email\"\n- \"compose a response\"\n- \"email assistant\"\n- \"my writing style\"\n- \"train on my emails\"\n\n## Requirements\n\n- Apple Silicon Mac (M1\u002FM2\u002FM3\u002FM4) with 8GB+ RAM (16GB recommended) — the local model runs on MLX (`.\u002Fscripts\u002Finstall.sh` sets it up)\n- Python 3.11+\n- A Google ingestion backend for Gmail\u002FDocs: [gog CLI](https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fgog) (default), Google's `gws` CLI, or the native Google API (`youos[google]` + OAuth)\n- ~5GB free disk space\n- Run the UI locally by default (do not expose publicly unless intentionally secured)\n\n## Quick start\n\n```bash\n# Install (creates .venv, installs YouOS + MLX on Apple Silicon, runs the doctor)\ncd youos\n.\u002Fscripts\u002Finstall.sh\nsource .venv\u002Fbin\u002Factivate\n\n# Check system requirements (Python, Google backend, MLX, disk space, etc.)\nyouos doctor\n\n# Run setup wizard (identity, ingestion, style analysis) — or open \u002Fwelcome in the browser\nyouos setup\n\n# Draft a reply (uses your local fine-tuned model by default)\nyouos draft \"paste inbound email here\"\nyouos draft --sender john@company.com \"email text\"\n\n# Run the web UI (then open \u002Ffeedback, \u002Fstats, \u002Fsettings, \u002Fabout)\nyouos serve\nyouos service install     # or run it as a background service (starts at login)\n\n# Compare the backends on YOUR mail, ranked by how closely each sounds like you\nyouos compare-models --limit 30 --semantic\n\n# Warm local-model server (loaded once for fast drafting)\nyouos model server status\n\n# Check status \u002F view stats\nyouos status\nyouos stats\n\n# Run the nightly pipeline manually (add --verbose for step-by-step output)\nyouos improve --verbose\n\n# Golden benchmark (10 curated cases)\nyouos eval --golden\n\n# Full corpus health report (pairs, quality scores, top senders)\nyouos corpus\n\n# Ingest a WhatsApp chat export (optional — augments your corpus)\nyouos ingest --whatsapp ~\u002FDownloads\u002FWhatsApp-Chat.txt\n\n# Add a sender note (immediately rebuilds their profile)\nyouos note john@company.com \"integration partner, prefers bullet points\"\n\n# Submit a feedback pair directly from the terminal\nyouos feedback --inbound \"email text\" --reply \"your reply\" --rating 4\n\n# Teardown (remove all data, keep code)\nyouos teardown\n```\n\n## Drafting inside Gmail\n\nInstall the **YouOS browser extension** (Chrome\u002FEdge\u002FBrave) — it lives in the repo's\n`extension\u002F` folder ([homepage](https:\u002F\u002Fgithub.com\u002FDrBaher\u002Fyouos\u002Ftree\u002Fmain\u002Fextension)),\nand the web UI's Gmail page has one-click \"Load unpacked\" steps. The extension adds a\npanel to Gmail:\n- Open an email → click the teal ✉ launcher → the panel opens\n- Sender + message auto-detected; add an instruction or pick a tone\n- Click **Generate** → drafted in your voice; **Insert into Gmail** drops it in the reply box\n- Rate 1–5 and **Submit feedback** — YouOS learns from it, same as the Review Queue\n\nA bookmarklet remains as a no-install fallback (it can break when Gmail changes its markup;\nthe extension doesn't).\n\n## How it works\n\n1. Ingests Gmail, Google Docs, WhatsApp exports — plus organic pairs from emails you sent without YouOS\n2. Builds a retrieval index — BM25 + query expansion + semantic (LRU-cached) + multi-intent + per-account isolation + same-thread 2× + subject + topic signals + sender-type boosts + quality scores + relative confidence thresholds\n3. When you ask for a draft: detects multi-intent, retrieves score-ranked thread-deduplicated exemplars (reply preserved 600 chars, inbound trimmed 400), prompt token budget enforced; generates with per-mode persona + first-name greeting on your **fine-tuned local model by default** (Qwen + your LoRA, served warm via `mlx_lm.server` so it's fast and on-device). The cloud is only a cold-start (before your model is trained) or a fallback; a per-draft model badge + the Stats \"Drafting with\" row always show which model actually ran\n4. Every email you review trains the model further — curriculum-ordered, quality-filtered, training pairs deduplicated by similarity, DPO pairs supported; nightly pipeline skips steps when data insufficient\n5. Nightly: ingests + organic pairs, incremental persona re-analysis (90-day weighted, EWMA avg words, p25\u002Fp75 confidence intervals), fine-tunes (with golden eval check), runs autoresearch on rotating benchmark sample\n6. Autoresearch benchmarks rotate weekly (seeded re-sample) — prevents overfitting to fixed test cases; golden eval composite tracked in pipeline log\n7. Style drift detection: Stats dashboard flags when your writing patterns shift significantly\n8. Your best-rated, least-edited replies surface higher in future retrievals via quality scoring\n9. Sender profiles track reply-time patterns and topics; `youos note` immediately rebuilds that contact's profile\n10. Submit feedback from terminal: `youos feedback --inbound \"...\" --reply \"...\" --rating 4`\n11. Setup wizard asks for internal domains — accurate sender classification from day one\n12. Facts store (`\u002Fapi\u002Ffacts`) — save context about contacts, projects, and preferences; facts are injected into generation prompts automatically for context-aware drafts\n13. Auto fact extraction — sender notes and feedback notes are parsed automatically on save using 15+ rule patterns (preferences, timezone, schedule, sign-offs, roles, relationships, project metadata); negation-aware with confidence scoring; LLM (Claude CLI) fallback for unstructured notes; fact deduplication\u002Fmerging on upsert\n14. Measure it, don't guess — `youos compare-models` drafts your held-out replies under each backend and scores them against what you actually wrote (voice-match), so you can verify the local fine-tuned model beats the cloud on your mail\n15. Readiness gate — a soft \"preparing your voice model\" banner holds you back from relying on drafts until your model is trained **and** benchmarked (with a \"Run benchmark now\" action); drafting still works meanwhile\n16. Becomes *your* OS — during setup the app personalizes its name from your first name (e.g. Baher → BaherOS)\n\n## Security & privacy notes\n\n- Gmail\u002FDocs ingestion uses your configured Google backend's auth (`gog` \u002F `gws` \u002F native OAuth); review connected accounts before ingestion\n- Drafting is on-device by default; the cloud is only the cold-start\u002Ffallback. If it's used (`review.draft_model: claude` or `model.fallback: claude`), inbound email\u002Fcontext is sent to Claude for that draft\n- For strict local-only operation, set `review.draft_model: local` and `model.fallback: none` in `youos_config.yaml`\n- Data location defaults to local instance paths under `YOUOS_DATA_DIR` (e.g. `~\u002FYouOS-Instances\u002F\u003Cyou>\u002F`), or the repo's `var\u002F`\n- Review `PRIVACY.md` before first ingestion\u002Fdeployment\n\n## Provenance\n\n- Source\u002Fhomepage: https:\u002F\u002Fgithub.com\u002FDrBaher\u002Fyouos\n- This skill bundles a full local Python app and is intended for explicit local install\u002Freview before use.\n","# YouOS — Personal Email Copilot\n\nYouOS is a full local Python app (not an instruction-only snippet). It drafts email replies in your style, grounded in your real past replies.\n\n**Naming:** *YouOS* is the shared app\u002Fpackage. During setup it personalizes its name to *\u003CFirst>OS* (e.g. **BaherOS**) for **your local instance** at `YOUOS_DATA_DIR=~\u002FYouOS-Instances\u002F\u003Cyou>\u002F` — that's a local config\u002Fdata directory, not a fork of the project.\n\n## Safety & impact\n\nRead these before installing:\n\n- **Sensitive data ingested locally.** YouOS reads your Gmail (sent + threads), Google Docs, and optional WhatsApp exports into a local SQLite DB. This stays on your machine, but it *is* sensitive content — protect the data directory (`YOUOS_DATA_DIR\u002Fvar\u002Fyouos.db`) accordingly.\n- **Installation runs local package code.** `.\u002Fscripts\u002Finstall.sh` builds a `.venv` and installs this repository — review the source (especially `scripts\u002Finstall.sh`, `pyproject.toml`, `app\u002F`) before running.\n- **Background persistence is opt-in.** YouOS only runs as a launchd LaunchAgent if you explicitly run `youos service install`. Foreground `youos serve` does not persist.\n- **Scheduled\u002Fnightly runs are opt-in.** Ingestion, fine-tuning, and autoresearch only run automatically if you've enabled the nightly pipeline; `youos improve` is the manual equivalent.\n- **External model fallback is optional.** Drafting is on-device by default. Cloud fallback only fires if `review.draft_model` or `model.fallback` is set to a cloud model — set `model.fallback: none` and `review.draft_model: local` for strict local-only operation.\n\n## Install and runtime model\n\n- Install is **manual**: run `.\u002Fscripts\u002Finstall.sh` (Python 3.11+) — it creates a `.venv`, installs YouOS, sets up the on-device model (**MLX**) on Apple Silicon, and runs the doctor\n- Note: this executes local package install code from this repository; review source before installing\n- Requires `python3` (3.11+) and a Google ingestion backend — `gog` (default), `gws`, or native (see Credentials)\n- Drafts run on your **fine-tuned local model by default** (Qwen + your LoRA, served warm); the cloud is only a cold-start before your model is trained, or a fallback\n- Optional runtime path override: `YOUOS_DATA_DIR`\n\n## Credentials and configuration\n\n- Required: a Google ingestion backend for Gmail\u002FDocs — `gog` (default), `gws`, or native (`youos[google]` + OAuth); set `ingestion.google_backend`\n- Optional: Claude CLI\u002FAPI credentials only for the cold-start\u002Ffallback (`review.draft_model` \u002F `model.fallback`)\n- For strict local-only: set `review.draft_model: local` and `model.fallback: none`\n\n## Trigger phrases\n\n- \"draft a reply to this email\"\n- \"write this email for me\"\n- \"how would I respond to this\"\n- \"what would I say to\"\n- \"help me reply\"\n- \"draft in my style\"\n- \"youos\"\n- \"my email copilot\"\n- \"email copilot\"\n- \"my copilot\"\n- \"generate a draft\"\n- \"reply draft\" \u002F \"email draft\" \u002F \"draft reply\"\n- \"compose reply\"\n- \"write a response\"\n- \"email response\"\n- \"how do I usually reply to\"\n- \"reply to this\"\n- \"help me write\"\n- \"write an email\"\n- \"compose a response\"\n- \"email assistant\"\n- \"my writing style\"\n- \"train on my emails\"\n\n## Requirements\n\n- Apple Silicon Mac (M1\u002FM2\u002FM3\u002FM4) with 8GB+ RAM (16GB recommended) — the local model runs on MLX (`.\u002Fscripts\u002Finstall.sh` sets it up)\n- Python 3.11+\n- A Google ingestion backend for Gmail\u002FDocs: [gog CLI](https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fgog) (default), Google's `gws` CLI, or the native Google API (`youos[google]` + OAuth)\n- ~5GB free disk space\n- Run the UI locally by default (do not expose publicly unless intentionally secured)\n\n## Quick start\n\n```bash\n# Install (creates .venv, installs YouOS + MLX on Apple Silicon, runs the doctor)\ncd youos\n.\u002Fscripts\u002Finstall.sh\nsource .venv\u002Fbin\u002Factivate\n\n# Check system requirements (Python, Google backend, MLX, disk space, etc.)\nyouos doctor\n\n# Run setup wizard (identity, ingestion, style analysis) — or open \u002Fwelcome in the browser\nyouos setup\n\n# Draft a reply (uses your local fine-tuned model by default)\nyouos draft \"paste inbound email here\"\nyouos draft --sender john@company.com \"email text\"\n\n# Run the web UI (then open \u002Ffeedback, \u002Fstats, \u002Fsettings, \u002Fabout)\nyouos serve\nyouos service install     # or run it as a background service (starts at login)\n\n# Compare the backends on YOUR mail, ranked by how closely each sounds like you\nyouos compare-models --limit 30 --semantic\n\n# Warm local-model server (loaded once for fast drafting)\nyouos model server status\n\n# Check status \u002F view stats\nyouos status\nyouos stats\n\n# Run the nightly pipeline manually (add --verbose for step-by-step output)\nyouos improve --verbose\n\n# Golden benchmark (10 curated cases)\nyouos eval --golden\n\n# Full corpus health report (pairs, quality scores, top senders)\nyouos corpus\n\n# Ingest a WhatsApp chat export (optional — augments your corpus)\nyouos ingest --whatsapp ~\u002FDownloads\u002FWhatsApp-Chat.txt\n\n# Add a sender note (immediately rebuilds their profile)\nyouos note john@company.com \"integration partner, prefers bullet points\"\n\n# Submit a feedback pair directly from the terminal\nyouos feedback --inbound \"email text\" --reply \"your reply\" --rating 4\n\n# Teardown (remove all data, keep code)\nyouos teardown\n```\n\n## Drafting inside Gmail\n\nInstall the **YouOS browser extension** (Chrome\u002FEdge\u002FBrave) — it lives in the repo's\n`extension\u002F` folder ([homepage](https:\u002F\u002Fgithub.com\u002FDrBaher\u002Fyouos\u002Ftree\u002Fmain\u002Fextension)),\nand the web UI's Gmail page has one-click \"Load unpacked\" steps. The extension adds a\npanel to Gmail:\n- Open an email → click the teal ✉ launcher → the panel opens\n- Sender + message auto-detected; add an instruction or pick a tone\n- Click **Generate** → drafted in your voice; **Insert into Gmail** drops it in the reply box\n- Rate 1–5 and **Submit feedback** — YouOS learns from it, same as the Review Queue\n\nA bookmarklet remains as a no-install fallback (it can break when Gmail changes its markup;\nthe extension doesn't).\n\n## How it works\n\n1. Ingests Gmail, Google Docs, WhatsApp exports — plus organic pairs from emails you sent without YouOS\n2. Builds a retrieval index — BM25 + query expansion + semantic (LRU-cached) + multi-intent + per-account isolation + same-thread 2× + subject + topic signals + sender-type boosts + quality scores + relative confidence thresholds\n3. When you ask for a draft: detects multi-intent, retrieves score-ranked thread-deduplicated exemplars (reply preserved 600 chars, inbound trimmed 400), prompt token budget enforced; generates with per-mode persona + first-name greeting on your **fine-tuned local model by default** (Qwen + your LoRA, served warm via `mlx_lm.server` so it's fast and on-device). The cloud is only a cold-start (before your model is trained) or a fallback; a per-draft model badge + the Stats \"Drafting with\" row always show which model actually ran\n4. Every email you review trains the model further — curriculum-ordered, quality-filtered, training pairs deduplicated by similarity, DPO pairs supported; nightly pipeline skips steps when data insufficient\n5. Nightly: ingests + organic pairs, incremental persona re-analysis (90-day weighted, EWMA avg words, p25\u002Fp75 confidence intervals), fine-tunes (with golden eval check), runs autoresearch on rotating benchmark sample\n6. Autoresearch benchmarks rotate weekly (seeded re-sample) — prevents overfitting to fixed test cases; golden eval composite tracked in pipeline log\n7. Style drift detection: Stats dashboard flags when your writing patterns shift significantly\n8. Your best-rated, least-edited replies surface higher in future retrievals via quality scoring\n9. Sender profiles track reply-time patterns and topics; `youos note` immediately rebuilds that contact's profile\n10. Submit feedback from terminal: `youos feedback --inbound \"...\" --reply \"...\" --rating 4`\n11. Setup wizard asks for internal domains — accurate sender classification from day one\n12. Facts store (`\u002Fapi\u002Ffacts`) — save context about contacts, projects, and preferences; facts are injected into generation prompts automatically for context-aware drafts\n13. Auto fact extraction — sender notes and feedback notes are parsed automatically on save using 15+ rule patterns (preferences, timezone, schedule, sign-offs, roles, relationships, project metadata); negation-aware with confidence scoring; LLM (Claude CLI) fallback for unstructured notes; fact deduplication\u002Fmerging on upsert\n14. Measure it, don't guess — `youos compare-models` drafts your held-out replies under each backend and scores them against what you actually wrote (voice-match), so you can verify the local fine-tuned model beats the cloud on your mail\n15. Readiness gate — a soft \"preparing your voice model\" banner holds you back from relying on drafts until your model is trained **and** benchmarked (with a \"Run benchmark now\" action); drafting still works meanwhile\n16. Becomes *your* OS — during setup the app personalizes its name from your first name (e.g. Baher → BaherOS)\n\n## Security & privacy notes\n\n- Gmail\u002FDocs ingestion uses your configured Google backend's auth (`gog` \u002F `gws` \u002F native OAuth); review connected accounts before ingestion\n- Drafting is on-device by default; the cloud is only the cold-start\u002Ffallback. If it's used (`review.draft_model: claude` or `model.fallback: claude`), inbound email\u002Fcontext is sent to Claude for that draft\n- For strict local-only operation, set `review.draft_model: local` and `model.fallback: none` in `youos_config.yaml`\n- Data location defaults to local instance paths under `YOUOS_DATA_DIR` (e.g. `~\u002FYouOS-Instances\u002F\u003Cyou>\u002F`), or the repo's `var\u002F`\n- Review `PRIVACY.md` before first ingestion\u002Fdeployment\n\n## Provenance\n\n- Source\u002Fhomepage: https:\u002F\u002Fgithub.com\u002FDrBaher\u002Fyouos\n- This skill bundles a full local Python app and is intended for explicit local install\u002Freview before use.\n",{"name":5,"metadata":24,"description":52},{"openclaw":25},{"install":26,"privacy":34,"requires":40,"credentials":47},[27],{"kind":28,"label":29,"steps":30},"instructions","Manual install required",[31,32,33],".\u002Fscripts\u002Finstall.sh","source .venv\u002Fbin\u002Factivate","youos setup",{"localStorage":35,"networkEgress":37},[36],"SQLite DB under YOUOS_DATA_DIR\u002Fvar\u002Fyouos.db (or local var\u002Fyouos.db)",[38,39],"None by default for local mode","Optional outbound requests when external fallback is enabled",{"arch":41,"bins":42,"minRam":45,"platform":46},"arm64",[43,44],"python3","gog","8GB","darwin",{"optional":48,"required":50},[49],"Claude CLI\u002FAPI credentials only if model.fallback uses external provider",[51],"A Google ingestion backend for Gmail\u002FDocs (set ingestion.google_backend): gog CLI authenticated (default), Google's gws CLI authenticated, or the native Google-API backend (pip install youos[google] + OAuth)","YouOS — local-first personal email copilot that learns your writing style from Gmail, Google Docs, and WhatsApp exports, then drafts replies in your voice. Use for drafting replies, reviewing how you usually respond, and running a self-improving personal communication workflow.\n","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fy\u002Fyouos",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill youos",{"tool":68,"command":69},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill youos",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill youos","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fy\u002Fyouos\u002FSKILL.md",true,[],[77,84,91,98,105,112],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]