[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GEQ17NB0CF5VZC320532VB":3,"skill-same:01M6GEQ17NB0CF5VZC320532VB":79},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6GEQ17NB0CF5VZC320532VB","x-psychology-transformer-gnn-workflow",null,"Train a small Transformer + GNN on recent X post features to derive psychological axes and cluster the user's posting style.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fcc\u002Fcc22fb462fda1bfc6f6a05466aaefd65927efa3399e029f8b2a7e1d8bb3deab0\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"workflow","x psychology transformer gnn workflow","Transformer","psychology","gnn","social-media","Media","hermes","hermes agent","twitter","user","social","train","pytorch","posting","style","post","cluster","windows","linux","2026-11-10 10:12:30",false,"---\r\nname: x-psychology-transformer-gnn-workflow\r\ndescription: \"Train a small Transformer + GNN on recent X post features to derive psychological axes and cluster the user's posting style.\"\r\nversion: 1.0.0\r\nauthor: Hermes Agent\r\nlicense: MIT\r\nplatforms: [windows, linux, macos]\r\ntags: [x, twitter, social-media, pytorch, transformer, gnn, psychology, clustering]\r\n---\r\n\r\n# X Psychology Transformer + GNN Workflow\r\n\r\nUse this skill when the user wants to turn recent X posts into a small deep-learning analysis that treats feature scores as psychological signals and then uses a Transformer + GNN to cluster or interpret the posting style.\r\n\r\n## Purpose\r\n- model the user's posting style as latent psychological axes\r\n- keep the analysis lightweight enough to run on a consumer GPU such as RTX 3060\r\n- ground the analysis in real public post artifacts rather than invented examples\r\n- produce a reproducible report and a file-backed result\r\n\r\n## Inputs\r\n- recent public X post history, usually from `~\u002F.hermes\u002Flm-twitterer\u002Factivity.jsonl`\r\n- a compact feature scoring scheme such as:\r\n  - utility\r\n  - proof\r\n  - contrast\r\n  - self-relevance\r\n  - fork-differentiation\r\n  - execution-first\r\n\r\n## Recommended interpretation axes\r\nMap the above into a small psychological space such as:\r\n- **agency**: willingness to act, ship, and execute\r\n- **epistemic grounding**: reliance on evidence, repo status, results, or proofs\r\n- **opposition**: contrast, tension, hype-vs-reality framing\r\n- **self_reference**: how much the post connects to the reader or the speaker's self-positioning\r\n\r\n## Workflow\r\n\r\n### 1) Collect data\r\nLoad the latest public posts from the activity log. Keep only real public posts; avoid drafts, secrets, or private artifacts.\r\n\r\n### 2) Convert posts to feature vectors\r\nTurn each post into a fixed-length vector of feature scores. Use a simple heuristic scoring layer first; the workflow is meant to be lightweight and reproducible.\r\n\r\n### 3) Derive psychological targets\r\nCreate small latent targets from the features. Keep the mapping transparent and explainable.\r\n\r\n### 4) Train a Transformer\r\nUse a Transformer encoder over the feature tokens for per-post representation learning.\r\n\r\n### 5) Train a GNN\r\nBuild a similarity graph over posts and run a tiny GCN\u002FGCN-like model over the learned embeddings.\r\n\r\n### 6) Cluster and interpret\r\nCluster the learned embeddings and summarize each cluster with:\r\n- mean feature profile\r\n- mean psychological profile\r\n- representative post\r\n- a plain-language interpretation\r\n\r\n### 7) Save a report\r\nWrite a JSON report and a Markdown implementation log in the repo `_docs` folder.\r\n\r\n## Operational notes\r\n- Prefer CPU only for tiny smoke tests; use CUDA when available for the real run.\r\n- For Windows mother-ship PCs, check `nvidia-smi` and then verify `torch.cuda.is_available()` inside the project venv.\r\n- If the project venv lacks `pip`, bootstrap it with `python -m ensurepip --upgrade` before installing wheels.\r\n- If `scikit-learn` or other analysis deps are missing in the venv, install them explicitly rather than assuming the base environment has them.\r\n- Keep the dataset small enough to run quickly on a consumer GPU.\r\n\r\n## Output format\r\nReturn:\r\n- device \u002F CUDA status\r\n- number of posts used\r\n- transformer loss\r\n- GNN loss\r\n- cluster summaries\r\n- one short psychological interpretation\r\n\r\n## Pitfalls\r\n- Do not claim clinical or diagnostic meaning from the axes.\r\n- Do not use private or secret data as training input.\r\n- Do not overfit the interpretation to a tiny sample; label it as exploratory.\r\n- If the GPU is visible to the OS but not to PyTorch, install a CUDA-enabled PyTorch wheel in the active venv and rerun.\r\n\r\n## Relationship to other skills\r\nPairs well with:\r\n- `x-post-feature-scoring-workflow`\r\n- `hermes-x-posting-workflows`\r\n- `ebbinghaus-memory`\r\n\r\nUse this skill as the analysis layer when the user wants to go beyond scorecards into a small learned model.\r\n","# X Psychology Transformer + GNN Workflow\r\n\r\nUse this skill when the user wants to turn recent X posts into a small deep-learning analysis that treats feature scores as psychological signals and then uses a Transformer + GNN to cluster or interpret the posting style.\r\n\r\n## Purpose\r\n- model the user's posting style as latent psychological axes\r\n- keep the analysis lightweight enough to run on a consumer GPU such as RTX 3060\r\n- ground the analysis in real public post artifacts rather than invented examples\r\n- produce a reproducible report and a file-backed result\r\n\r\n## Inputs\r\n- recent public X post history, usually from `~\u002F.hermes\u002Flm-twitterer\u002Factivity.jsonl`\r\n- a compact feature scoring scheme such as:\r\n  - utility\r\n  - proof\r\n  - contrast\r\n  - self-relevance\r\n  - fork-differentiation\r\n  - execution-first\r\n\r\n## Recommended interpretation axes\r\nMap the above into a small psychological space such as:\r\n- **agency**: willingness to act, ship, and execute\r\n- **epistemic grounding**: reliance on evidence, repo status, results, or proofs\r\n- **opposition**: contrast, tension, hype-vs-reality framing\r\n- **self_reference**: how much the post connects to the reader or the speaker's self-positioning\r\n\r\n## Workflow\r\n\r\n### 1) Collect data\r\nLoad the latest public posts from the activity log. Keep only real public posts; avoid drafts, secrets, or private artifacts.\r\n\r\n### 2) Convert posts to feature vectors\r\nTurn each post into a fixed-length vector of feature scores. Use a simple heuristic scoring layer first; the workflow is meant to be lightweight and reproducible.\r\n\r\n### 3) Derive psychological targets\r\nCreate small latent targets from the features. Keep the mapping transparent and explainable.\r\n\r\n### 4) Train a Transformer\r\nUse a Transformer encoder over the feature tokens for per-post representation learning.\r\n\r\n### 5) Train a GNN\r\nBuild a similarity graph over posts and run a tiny GCN\u002FGCN-like model over the learned embeddings.\r\n\r\n### 6) Cluster and interpret\r\nCluster the learned embeddings and summarize each cluster with:\r\n- mean feature profile\r\n- mean psychological profile\r\n- representative post\r\n- a plain-language interpretation\r\n\r\n### 7) Save a report\r\nWrite a JSON report and a Markdown implementation log in the repo `_docs` folder.\r\n\r\n## Operational notes\r\n- Prefer CPU only for tiny smoke tests; use CUDA when available for the real run.\r\n- For Windows mother-ship PCs, check `nvidia-smi` and then verify `torch.cuda.is_available()` inside the project venv.\r\n- If the project venv lacks `pip`, bootstrap it with `python -m ensurepip --upgrade` before installing wheels.\r\n- If `scikit-learn` or other analysis deps are missing in the venv, install them explicitly rather than assuming the base environment has them.\r\n- Keep the dataset small enough to run quickly on a consumer GPU.\r\n\r\n## Output format\r\nReturn:\r\n- device \u002F CUDA status\r\n- number of posts used\r\n- transformer loss\r\n- GNN loss\r\n- cluster summaries\r\n- one short psychological interpretation\r\n\r\n## Pitfalls\r\n- Do not claim clinical or diagnostic meaning from the axes.\r\n- Do not use private or secret data as training input.\r\n- Do not overfit the interpretation to a tiny sample; label it as exploratory.\r\n- If the GPU is visible to the OS but not to PyTorch, install a CUDA-enabled PyTorch wheel in the active venv and rerun.\r\n\r\n## Relationship to other skills\r\nPairs well with:\r\n- `x-post-feature-scoring-workflow`\r\n- `hermes-x-posting-workflows`\r\n- `ebbinghaus-memory`\r\n\r\nUse this skill as the analysis layer when the user wants to go beyond scorecards into a small learned model.\r\n",{"name":5,"tags":49,"author":53,"license":15,"version":54,"platforms":55,"description":7},[50,33,29,37,51,28,27,52],"x","transformer","clustering","Hermes Agent","1.0.0",[42,43,56],"macos","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002Fcc\u002Fcc22fb462fda1bfc6f6a05466aaefd65927efa3399e029f8b2a7e1d8bb3deab0",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add zapabob\u002FSkills --skill x-psychology-transformer-gnn-workflow",{"tool":71,"command":72},"bunx","bunx skills add zapabob\u002FSkills --skill x-psychology-transformer-gnn-workflow",{"tool":74,"command":75},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill x-psychology-transformer-gnn-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fcc\u002Fcc22fb462fda1bfc6f6a05466aaefd65927efa3399e029f8b2a7e1d8bb3deab0\u002FSKILL.md",true,[],[80,104,138,165,191,208],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":95,"publishedAt":44},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[86,89,90],{"categoryNo":87,"categoryName":88,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[82,96,56,97,98,43,42,99,100,101,29,102,30,31,32,33,57,35,103,40],"openclaw","cli","github","official","search","https","api","via",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":121,"publishedAt":44},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[110,113,116,117,118],{"categoryNo":111,"categoryName":112,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":114,"categoryName":115,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},{"categoryNo":119,"categoryName":120,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000036","内容创作者",[122,123,124,125,56,126,43,24,42,127,128,129,130,131,132,133,134,135,136,137],"writing","writing plans","plans","design","review","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":147,"publishedAt":44},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[140,56,43,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":174,"publishedAt":44},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[171],{"categoryNo":172,"categoryName":173,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[175,56,176,177,42,37,178,179,180,181,182,155,183,184,185,186,187,188,189,190],"weights and biases","tensorflow","experiments","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":44},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[197],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[193,56,199,98,43,200,201,202,203,204,205,31,32,206,207],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":209,"name":210,"nameZh":6,"description":211,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":212,"categories":213,"keywords":216,"publishedAt":44},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[214,215],{"categoryNo":87,"categoryName":88,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[217,218,219,43,220,148,221,222,223,151,224,102,225,226,227,228,229,230,231,232],"llms","vLLM","serving llms vllm","research","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]