[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AZJ0JE3E4VWRDJSQHBHZPQ":3,"skill-same:01M7AZJ0JE3E4VWRDJSQHBHZPQ":60},{"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":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M7AZJ0JE3E4VWRDJSQHBHZPQ","jupyter-live-kernel",null,"Iterative Python via live Jupyter kernel (hamelnb).","dbillion\u002Fhermes-skills-public","dbillion","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F49393855?v=4","01M7AVH8QPGCM8WKWS22TRT0T6","Oludayo Adeoye","01M7AVH8RD1JJWA0YS9CFEWAV9",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fdata-science\u002Fjupyter-live-kernel\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: jupyter-live-kernel\ndescription: \"Iterative Python via live Jupyter kernel (hamelnb).\"\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [jupyter, notebook, repl, data-science, exploration, iterative]\n    category: data-science\n---\n\n# Jupyter Live Kernel (hamelnb)\n\nGives you a **stateful Python REPL** via a live Jupyter kernel. Variables persist\nacross executions. Use this instead of `execute_code` when you need to build up\nstate incrementally, explore APIs, inspect DataFrames, or iterate on complex code.\n\n## When to Use This vs Other Tools\n\n| Tool | Use When |\n|------|----------|\n| **This skill** | Iterative exploration, state across steps, data science, ML, \"let me try this and check\" |\n| `execute_code` | One-shot scripts needing hermes tool access (web_search, file ops). Stateless. |\n| `terminal` | Shell commands, builds, installs, git, process management |\n\n**Rule of thumb:** If you'd want a Jupyter notebook for the task, use this skill.\n\n## Prerequisites\n\n1. **uv** must be installed (check: `which uv`)\n2. **JupyterLab** must be installed: `uv tool install jupyterlab`\n3. A Jupyter server must be running (see Setup below)\n\n## Setup\n\nThe hamelnb script location:\n```\nSCRIPT=\"$HOME\u002F.agent-skills\u002Fhamelnb\u002Fskills\u002Fjupyter-live-kernel\u002Fscripts\u002Fjupyter_live_kernel.py\"\n```\n\nIf not cloned yet:\n```\ngit clone https:\u002F\u002Fgithub.com\u002Fhamelsmu\u002Fhamelnb.git ~\u002F.agent-skills\u002Fhamelnb\n```\n\n### Starting JupyterLab\n\nCheck if a server is already running:\n```\nuv run \"$SCRIPT\" servers\n```\n\nIf no servers found, start one:\n```\njupyter-lab --no-browser --port=8888 --notebook-dir=$HOME\u002Fnotebooks \\\n  --IdentityProvider.token='' --ServerApp.password='' > \u002Ftmp\u002Fjupyter.log 2>&1 &\nsleep 3\n```\n\nNote: Token\u002Fpassword disabled for local agent access. The server runs headless.\n\n### Creating a Notebook for REPL Use\n\nIf you just need a REPL (no existing notebook), create a minimal notebook file:\n```\nmkdir -p ~\u002Fnotebooks\n```\nWrite a minimal .ipynb JSON file with one empty code cell, then start a kernel\nsession via the Jupyter REST API:\n```\ncurl -s -X POST http:\u002F\u002F127.0.0.1:8888\u002Fapi\u002Fsessions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"path\":\"scratch.ipynb\",\"type\":\"notebook\",\"name\":\"scratch.ipynb\",\"kernel\":{\"name\":\"python3\"}}'\n```\n\n## Core Workflow\n\nAll commands return structured JSON. Always use `--compact` to save tokens.\n\n### 1. Discover servers and notebooks\n\n```\nuv run \"$SCRIPT\" servers --compact\nuv run \"$SCRIPT\" notebooks --compact\n```\n\n### 2. Execute code (primary operation)\n\n```\nuv run \"$SCRIPT\" execute --path \u003Cnotebook.ipynb> --code '\u003Cpython code>' --compact\n```\n\nState persists across execute calls. Variables, imports, objects all survive.\n\nMulti-line code works with $'...' quoting:\n```\nuv run \"$SCRIPT\" execute --path scratch.ipynb --code $'import os\\nfiles = os.listdir(\".\")\\nprint(f\"Found {len(files)} files\")' --compact\n```\n\n### 3. Inspect live variables\n\n```\nuv run \"$SCRIPT\" variables --path \u003Cnotebook.ipynb> list --compact\nuv run \"$SCRIPT\" variables --path \u003Cnotebook.ipynb> preview --name \u003Cvarname> --compact\n```\n\n### 4. Edit notebook cells\n\n```\n# View current cells\nuv run \"$SCRIPT\" contents --path \u003Cnotebook.ipynb> --compact\n\n# Insert a new cell\nuv run \"$SCRIPT\" edit --path \u003Cnotebook.ipynb> insert \\\n  --at-index \u003CN> --cell-type code --source '\u003Ccode>' --compact\n\n# Replace cell source (use cell-id from contents output)\nuv run \"$SCRIPT\" edit --path \u003Cnotebook.ipynb> replace-source \\\n  --cell-id \u003Cid> --source '\u003Cnew code>' --compact\n\n# Delete a cell\nuv run \"$SCRIPT\" edit --path \u003Cnotebook.ipynb> delete --cell-id \u003Cid> --compact\n```\n\n### 5. Verification (restart + run all)\n\nOnly use when the user asks for a clean verification or you need to confirm\nthe notebook runs top-to-bottom:\n\n```\nuv run \"$SCRIPT\" restart-run-all --path \u003Cnotebook.ipynb> --save-outputs --compact\n```\n\n## Practical Tips from Experience\n\n1. **First execution after server start may timeout** — the kernel needs a moment\n   to initialize. If you get a timeout, just retry.\n\n2. **The kernel Python is JupyterLab's Python** — packages must be installed in\n   that environment. If you need additional packages, install them into the\n   JupyterLab tool environment first.\n\n3. **--compact flag saves significant tokens** — always use it. JSON output can\n   be very verbose without it.\n\n4. **For pure REPL use**, create a scratch.ipynb and don't bother with cell editing.\n   Just use `execute` repeatedly.\n\n5. **Argument order matters** — subcommand flags like `--path` go BEFORE the\n   sub-subcommand. E.g.: `variables --path nb.ipynb list` not `variables list --path nb.ipynb`.\n\n6. **If a session doesn't exist yet**, you need to start one via the REST API\n   (see Setup section). The tool can't execute without a live kernel session.\n\n7. **Errors are returned as JSON** with traceback — read the `ename` and `evalue`\n   fields to understand what went wrong.\n\n8. **Occasional websocket timeouts** — some operations may timeout on first try,\n   especially after a kernel restart. Retry once before escalating.\n\n## Timeout Defaults\n\nThe script has a 30-second default timeout per execution. For long-running\noperations, pass `--timeout 120`. Use generous timeouts (60+) for initial\nsetup or heavy computation.\n","# Jupyter Live Kernel (hamelnb)\n\nGives you a **stateful Python REPL** via a live Jupyter kernel. Variables persist\nacross executions. Use this instead of `execute_code` when you need to build up\nstate incrementally, explore APIs, inspect DataFrames, or iterate on complex code.\n\n## When to Use This vs Other Tools\n\n| Tool | Use When |\n|------|----------|\n| **This skill** | Iterative exploration, state across steps, data science, ML, \"let me try this and check\" |\n| `execute_code` | One-shot scripts needing hermes tool access (web_search, file ops). Stateless. |\n| `terminal` | Shell commands, builds, installs, git, process management |\n\n**Rule of thumb:** If you'd want a Jupyter notebook for the task, use this skill.\n\n## Prerequisites\n\n1. **uv** must be installed (check: `which uv`)\n2. **JupyterLab** must be installed: `uv tool install jupyterlab`\n3. A Jupyter server must be running (see Setup below)\n\n## Setup\n\nThe hamelnb script location:\n```\nSCRIPT=\"$HOME\u002F.agent-skills\u002Fhamelnb\u002Fskills\u002Fjupyter-live-kernel\u002Fscripts\u002Fjupyter_live_kernel.py\"\n```\n\nIf not cloned yet:\n```\ngit clone https:\u002F\u002Fgithub.com\u002Fhamelsmu\u002Fhamelnb.git ~\u002F.agent-skills\u002Fhamelnb\n```\n\n### Starting JupyterLab\n\nCheck if a server is already running:\n```\nuv run \"$SCRIPT\" servers\n```\n\nIf no servers found, start one:\n```\njupyter-lab --no-browser --port=8888 --notebook-dir=$HOME\u002Fnotebooks \\\n  --IdentityProvider.token='' --ServerApp.password='' > \u002Ftmp\u002Fjupyter.log 2>&1 &\nsleep 3\n```\n\nNote: Token\u002Fpassword disabled for local agent access. The server runs headless.\n\n### Creating a Notebook for REPL Use\n\nIf you just need a REPL (no existing notebook), create a minimal notebook file:\n```\nmkdir -p ~\u002Fnotebooks\n```\nWrite a minimal .ipynb JSON file with one empty code cell, then start a kernel\nsession via the Jupyter REST API:\n```\ncurl -s -X POST http:\u002F\u002F127.0.0.1:8888\u002Fapi\u002Fsessions \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"path\":\"scratch.ipynb\",\"type\":\"notebook\",\"name\":\"scratch.ipynb\",\"kernel\":{\"name\":\"python3\"}}'\n```\n\n## Core Workflow\n\nAll commands return structured JSON. Always use `--compact` to save tokens.\n\n### 1. Discover servers and notebooks\n\n```\nuv run \"$SCRIPT\" servers --compact\nuv run \"$SCRIPT\" notebooks --compact\n```\n\n### 2. Execute code (primary operation)\n\n```\nuv run \"$SCRIPT\" execute --path \u003Cnotebook.ipynb> --code '\u003Cpython code>' --compact\n```\n\nState persists across execute calls. Variables, imports, objects all survive.\n\nMulti-line code works with $'...' quoting:\n```\nuv run \"$SCRIPT\" execute --path scratch.ipynb --code $'import os\\nfiles = os.listdir(\".\")\\nprint(f\"Found {len(files)} files\")' --compact\n```\n\n### 3. Inspect live variables\n\n```\nuv run \"$SCRIPT\" variables --path \u003Cnotebook.ipynb> list --compact\nuv run \"$SCRIPT\" variables --path \u003Cnotebook.ipynb> preview --name \u003Cvarname> --compact\n```\n\n### 4. Edit notebook cells\n\n```\n# View current cells\nuv run \"$SCRIPT\" contents --path \u003Cnotebook.ipynb> --compact\n\n# Insert a new cell\nuv run \"$SCRIPT\" edit --path \u003Cnotebook.ipynb> insert \\\n  --at-index \u003CN> --cell-type code --source '\u003Ccode>' --compact\n\n# Replace cell source (use cell-id from contents output)\nuv run \"$SCRIPT\" edit --path \u003Cnotebook.ipynb> replace-source \\\n  --cell-id \u003Cid> --source '\u003Cnew code>' --compact\n\n# Delete a cell\nuv run \"$SCRIPT\" edit --path \u003Cnotebook.ipynb> delete --cell-id \u003Cid> --compact\n```\n\n### 5. Verification (restart + run all)\n\nOnly use when the user asks for a clean verification or you need to confirm\nthe notebook runs top-to-bottom:\n\n```\nuv run \"$SCRIPT\" restart-run-all --path \u003Cnotebook.ipynb> --save-outputs --compact\n```\n\n## Practical Tips from Experience\n\n1. **First execution after server start may timeout** — the kernel needs a moment\n   to initialize. If you get a timeout, just retry.\n\n2. **The kernel Python is JupyterLab's Python** — packages must be installed in\n   that environment. If you need additional packages, install them into the\n   JupyterLab tool environment first.\n\n3. **--compact flag saves significant tokens** — always use it. JSON output can\n   be very verbose without it.\n\n4. **For pure REPL use**, create a scratch.ipynb and don't bother with cell editing.\n   Just use `execute` repeatedly.\n\n5. **Argument order matters** — subcommand flags like `--path` go BEFORE the\n   sub-subcommand. E.g.: `variables --path nb.ipynb list` not `variables list --path nb.ipynb`.\n\n6. **If a session doesn't exist yet**, you need to start one via the REST API\n   (see Setup section). The tool can't execute without a live kernel session.\n\n7. **Errors are returned as JSON** with traceback — read the `ename` and `evalue`\n   fields to understand what went wrong.\n\n8. **Occasional websocket timeouts** — some operations may timeout on first try,\n   especially after a kernel restart. Retry once before escalating.\n\n## Timeout Defaults\n\nThe script has a 30-second default timeout per execution. For long-running\noperations, pass `--timeout 120`. Use generous timeouts (60+) for initial\nsetup or heavy computation.\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":35,"description":7},"Hermes Agent","1.0.0",{"hermes":27},{"tags":28,"category":32},[29,30,31,32,33,34],"jupyter","notebook","repl","data-science","exploration","iterative",[36,37,38],"linux","macos","windows","master","f341c46fed021656175d5c9ccc67a72126e50bfb","skills\u002Fdata-science\u002Fjupyter-live-kernel","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public","https:\u002F\u002Fgithub.com\u002Fdbillion","I enjoy writing codes,teaching programming, solving problems, tasted automation in Python and never looked back😋😋😋💞","2026-10-14 03:31:55",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add dbillion\u002Fhermes-skills-public --skill jupyter-live-kernel",{"tool":52,"command":53},"bunx","bunx skills add dbillion\u002Fhermes-skills-public --skill jupyter-live-kernel",{"tool":55,"command":56},"pnpm","pnpm dlx skills add dbillion\u002Fhermes-skills-public --skill jupyter-live-kernel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fdata-science\u002Fjupyter-live-kernel\u002FSKILL.md",true,[],[61,68,75,84,91,98],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7B25T0V7RBKES86Y3RTXQRN","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7B25DSBBMZRHVD28MAX7N5X","gemini-vision-fallback","Vision fallback: Gemini REST API if vision_analyze blocked.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fvision\u002Fgemini-vision-fallback\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":79,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7B22XW9QXT2ZWWXVZDFWYZP","twitter-cli","Use twitter-cli for ALL Twitter\u002FX operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ftwitter-cli\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ftwitter-cli\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},"01M7B22QMWY1B4F7BC114RG4S6","prism-scan","Structural analysis through dynamically generated cognitive lenses. Generates the optimal analytical lens for the specific code\u002Fartifact, then executes it. Finds conservation laws, structural invariants, and concrete bugs that vanilla analysis misses. Use on any code file, system design, or text artifact.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-scan\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},"01M7B22JA5XCAP1ACT6V50WYR1","prism-reflect","Constraint transparency: analyzes an artifact structurally, then analyzes what its own analysis concealed. Produces a conservation law AND a constraint report showing what was maximized, what was sacrificed, and what to investigate next. The only AI skill that knows what it can't see.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-reflect\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},"01M7B22EB15M75M4X3C52YGDCC","prism-full","Full Prism: multi-pass structural analysis with mandatory adversarial self-correction. Designs custom analytical passes, executes them with chaining, then attacks its own findings before synthesizing. Use for maximum depth on important code or artifacts.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-full\u002FSKILL.md",[],[]]