[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AZHQ29PNAYYEXACHTMAGR4":3,"skill-same:01M7AZHQ29PNAYYEXACHTMAGR4":50},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":14,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7AZHQ29PNAYYEXACHTMAGR4","visual-gen-fallback",null,"Infographic fallback when renderer or vision is unavailable.","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\u002Fcreative\u002Fvisual-gen-fallback\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: visual-gen-fallback\ndescription: \"Infographic fallback when renderer or vision is unavailable.\"\nversion: 1.0.0\nlicense: MIT\nplatforms: [linux, macos, windows]\n---\n\n# Visual Asset Generation Without a Renderer (Fallback)\n\nUse this when a user wants a generated visual (infographic, social graphic, image with a\nbrand character) but the agent has **no `image_generate` tool**, **no local diffusion\nbackend** (ComfyUI absent, no GPU), and\u002For **`vision_analyze` is unavailable**. Do NOT hang\nor fabricate output. Take the available path and report blockers as actionable asks.\n\n## Decision: can I render at all?\n\n- `image_generate` in toolset? → use it (see `baoyu-infographic` \u002F `comfyui` skills).\n- Local ComfyUI on `:8188` + `comfy` CLI + GPU? → `comfyui` skill (best for exact brand\n  match via Flux\u002FSDXL img2img with the reference image).\n- Comfy Cloud API key + paid tier? → `comfyui` skill against `https:\u002F\u002Fcloud.comfy.org`\n  (also good for exact match).\n- **None of the above** → use the NotebookLM fallback below.\n\n## Step 1 — Characterize the reference image WITHOUT vision (PIL fallback)\n\n`vision_analyze` may fail with `404` (file:\u002F\u002F not readable by the vision backend) or `429`\n(rate-limited). Don't assume blindness — read pixels directly for the facts a generator\nneeds (transparency, dominant palette):\n\n```python\nfrom PIL import Image\nfrom collections import Counter\nim = Image.open(\"character.png\").convert(\"RGBA\")   # force alpha\nw,h = im.size; px = im.load()\ncnt = Counter()\nfor y in range(0,h,2):\n    for x in range(0,w,2):\n        r,g,b,a = px[x,y]\n        if a > 40:                                  # skip transparent pixels\n            cnt[(r\u002F\u002F24*24, g\u002F\u002F24*24, b\u002F\u002F24*24)] += 1\nprint(\"mode:\", im.mode, \"size:\", im.size)          # RGBA => transparent background\nprint(\"alpha extrema:\", im.split()[-1].getextrema())\nfor (r,g,b),n in cnt.most_common(10):\n    print(f\"  #{r:02X}{g:02X}{b:02X}  freq={n}\")\n```\n\nThis yields the factual palette + alpha info to brief any generator. (Example: a warm\ndark owl came out RGBA 360x360, transparent bg, maroon\u002Frust\u002Fblack dominant.)\n\n## Step 2 — Upload brief + reference image to NotebookLM, then generate\n\n`nlm source add --file` accepts BOTH a `.md`\u002F`.txt` brief and a `.png`\u002F`.jpg` reference\n(the image source `type` becomes `image`). Create a notebook, add both, generate:\n\n```bash\nNL=\u002Fhome\u002Fdeeone\u002F.local\u002Fbin\u002Fnlm\nNBID=$($NL notebook create \"Infographic Pack\" --json \\\n       | grep -o '\"notebook_id\": *\"[^\"]*\"' | sed 's\u002F.*\"notebook_id\": *\"\u002F\u002F;s\u002F\"\u002F\u002F')\n$NL source add \"$NBID\" --file \u002Fpath\u002Fto\u002Fbrief.md --title \"Brief\" --wait\n$NL source add \"$NBID\" --file \u002Fpath\u002Fto\u002Fcharacter.png --title \"Brand Character (reference)\" --wait\n$NL infographic create \"$NBID\" --orientation portrait --style professional \\\n   --focus \"Hand-drawn doodle style, warm cozy colors, include the character pointing to tips\" --confirm\n```\n\n(See `nlm-productivity` skill for the full `nlm` command surface, download-by-id, and rate\nlimits. Requires `nlm` CLI + auth.)\n\n**Caveat — fidelity:** NotebookLM infographic generation produces layout\u002Fstructure but will\nNOT pixel-match a brand character the way Flux\u002FSDXL img2img would. If an *exact* visual match\nmatters, you need a diffusion backend (Comfy Cloud key + img2img with the reference).\n\n## Step 3 — Report blockers as actionable asks (never a dead end)\n\nWhen fully blocked, the user expects TWO things: (a) take the available path (e.g. upload to\nNotebookLM), AND (b) itemize each blocker with the exact unblock. Template:\n\n- **Vision 404 (file:\u002F\u002F):** deliver the image as a MEDIA attachment the runtime decodes, or\n  configure the vision backend to read local paths. (PIL fallback above avoids needing it.)\n- **Vision 429:** wait out the cooldown, or use a vision-capable model\u002Fprovider with quota.\n- **No image-generation backend:** local ComfyUI absent on this host; Comfy Cloud needs a\n  paid API key (best for exact match via Flux\u002FSDXL img2img). Or any image-gen endpoint key\n  (OpenAI\u002FDALL·E, etc.).\n\n## Pitfalls\n\n- PIL characterization must `convert(\"RGBA\")` before reading alpha; transparent pixels have\n  `a` near 0 — skip them (`a > 40`) or the histogram is dominated by the bg color.\n- `vision_analyze` 404 on `file:\u002F\u002F` is NOT \"image missing\" — the file often exists; the\n  vision backend just can't reach the local FS. Verify with `search_files`\u002Ffile stat first.\n- NotebookLM infographic ≈ layout generator, not a character renderer. Don't promise brand\n  fidelity from it.\n- `nlm` extraction with `grep ... | python3` can trip a security scanner (pipe-to-interpreter).\n  Prefer `grep -o` + `sed` to pull the ID without piping JSON into an interpreter.\n\n## See Also\n\n- `nlm-productivity` — full NotebookLM CLI surface (user-owned; recommend `hermes curator adopt`\n  if you want to fold this in).\n- `comfyui` — local\u002Fcloud diffusion when a renderer IS available (best for pixel-matching a\n  brand character via img2img).\n- `baoyu-infographic` — layout×style infographic planner that assumes `image_generate` exists\n  (bundled; protected).\n","# Visual Asset Generation Without a Renderer (Fallback)\n\nUse this when a user wants a generated visual (infographic, social graphic, image with a\nbrand character) but the agent has **no `image_generate` tool**, **no local diffusion\nbackend** (ComfyUI absent, no GPU), and\u002For **`vision_analyze` is unavailable**. Do NOT hang\nor fabricate output. Take the available path and report blockers as actionable asks.\n\n## Decision: can I render at all?\n\n- `image_generate` in toolset? → use it (see `baoyu-infographic` \u002F `comfyui` skills).\n- Local ComfyUI on `:8188` + `comfy` CLI + GPU? → `comfyui` skill (best for exact brand\n  match via Flux\u002FSDXL img2img with the reference image).\n- Comfy Cloud API key + paid tier? → `comfyui` skill against `https:\u002F\u002Fcloud.comfy.org`\n  (also good for exact match).\n- **None of the above** → use the NotebookLM fallback below.\n\n## Step 1 — Characterize the reference image WITHOUT vision (PIL fallback)\n\n`vision_analyze` may fail with `404` (file:\u002F\u002F not readable by the vision backend) or `429`\n(rate-limited). Don't assume blindness — read pixels directly for the facts a generator\nneeds (transparency, dominant palette):\n\n```python\nfrom PIL import Image\nfrom collections import Counter\nim = Image.open(\"character.png\").convert(\"RGBA\")   # force alpha\nw,h = im.size; px = im.load()\ncnt = Counter()\nfor y in range(0,h,2):\n    for x in range(0,w,2):\n        r,g,b,a = px[x,y]\n        if a > 40:                                  # skip transparent pixels\n            cnt[(r\u002F\u002F24*24, g\u002F\u002F24*24, b\u002F\u002F24*24)] += 1\nprint(\"mode:\", im.mode, \"size:\", im.size)          # RGBA => transparent background\nprint(\"alpha extrema:\", im.split()[-1].getextrema())\nfor (r,g,b),n in cnt.most_common(10):\n    print(f\"  #{r:02X}{g:02X}{b:02X}  freq={n}\")\n```\n\nThis yields the factual palette + alpha info to brief any generator. (Example: a warm\ndark owl came out RGBA 360x360, transparent bg, maroon\u002Frust\u002Fblack dominant.)\n\n## Step 2 — Upload brief + reference image to NotebookLM, then generate\n\n`nlm source add --file` accepts BOTH a `.md`\u002F`.txt` brief and a `.png`\u002F`.jpg` reference\n(the image source `type` becomes `image`). Create a notebook, add both, generate:\n\n```bash\nNL=\u002Fhome\u002Fdeeone\u002F.local\u002Fbin\u002Fnlm\nNBID=$($NL notebook create \"Infographic Pack\" --json \\\n       | grep -o '\"notebook_id\": *\"[^\"]*\"' | sed 's\u002F.*\"notebook_id\": *\"\u002F\u002F;s\u002F\"\u002F\u002F')\n$NL source add \"$NBID\" --file \u002Fpath\u002Fto\u002Fbrief.md --title \"Brief\" --wait\n$NL source add \"$NBID\" --file \u002Fpath\u002Fto\u002Fcharacter.png --title \"Brand Character (reference)\" --wait\n$NL infographic create \"$NBID\" --orientation portrait --style professional \\\n   --focus \"Hand-drawn doodle style, warm cozy colors, include the character pointing to tips\" --confirm\n```\n\n(See `nlm-productivity` skill for the full `nlm` command surface, download-by-id, and rate\nlimits. Requires `nlm` CLI + auth.)\n\n**Caveat — fidelity:** NotebookLM infographic generation produces layout\u002Fstructure but will\nNOT pixel-match a brand character the way Flux\u002FSDXL img2img would. If an *exact* visual match\nmatters, you need a diffusion backend (Comfy Cloud key + img2img with the reference).\n\n## Step 3 — Report blockers as actionable asks (never a dead end)\n\nWhen fully blocked, the user expects TWO things: (a) take the available path (e.g. upload to\nNotebookLM), AND (b) itemize each blocker with the exact unblock. Template:\n\n- **Vision 404 (file:\u002F\u002F):** deliver the image as a MEDIA attachment the runtime decodes, or\n  configure the vision backend to read local paths. (PIL fallback above avoids needing it.)\n- **Vision 429:** wait out the cooldown, or use a vision-capable model\u002Fprovider with quota.\n- **No image-generation backend:** local ComfyUI absent on this host; Comfy Cloud needs a\n  paid API key (best for exact match via Flux\u002FSDXL img2img). Or any image-gen endpoint key\n  (OpenAI\u002FDALL·E, etc.).\n\n## Pitfalls\n\n- PIL characterization must `convert(\"RGBA\")` before reading alpha; transparent pixels have\n  `a` near 0 — skip them (`a > 40`) or the histogram is dominated by the bg color.\n- `vision_analyze` 404 on `file:\u002F\u002F` is NOT \"image missing\" — the file often exists; the\n  vision backend just can't reach the local FS. Verify with `search_files`\u002Ffile stat first.\n- NotebookLM infographic ≈ layout generator, not a character renderer. Don't promise brand\n  fidelity from it.\n- `nlm` extraction with `grep ... | python3` can trip a security scanner (pipe-to-interpreter).\n  Prefer `grep -o` + `sed` to pull the ID without piping JSON into an interpreter.\n\n## See Also\n\n- `nlm-productivity` — full NotebookLM CLI surface (user-owned; recommend `hermes curator adopt`\n  if you want to fold this in).\n- `comfyui` — local\u002Fcloud diffusion when a renderer IS available (best for pixel-matching a\n  brand character via img2img).\n- `baoyu-infographic` — layout×style infographic planner that assumes `image_generate` exists\n  (bundled; protected).\n",{"name":5,"license":15,"version":24,"platforms":25,"description":7},"1.0.0",[26,27,28],"linux","macos","windows","master","f341c46fed021656175d5c9ccc67a72126e50bfb","skills\u002Fcreative\u002Fvisual-gen-fallback","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":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add dbillion\u002Fhermes-skills-public --skill visual-gen-fallback",{"tool":42,"command":43},"bunx","bunx skills add dbillion\u002Fhermes-skills-public --skill visual-gen-fallback",{"tool":45,"command":46},"pnpm","pnpm dlx skills add dbillion\u002Fhermes-skills-public --skill visual-gen-fallback","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fcreative\u002Fvisual-gen-fallback\u002FSKILL.md",true,[],[51,58,65,74,81,88],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"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":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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",[],[]]