[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EFVYA19682HT7RPMFCPT85":3,"skill-same:01M7EFVYA19682HT7RPMFCPT85":73},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7EFVYA19682HT7RPMFCPT85","inference-deployment",null,"Guide Chinese-LLaMA-Alpaca Hugging Face inference, Gradio chat, OpenAI-compatible API serving, and optional LangChain integrations.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: inference-deployment\ndescription: \"Guide Chinese-LLaMA-Alpaca Hugging Face inference, Gradio chat,\n  OpenAI-compatible API serving, and optional LangChain integrations.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Inference and Deployment Router\n\nUse this sub-skill when a user has, or is preparing, Chinese-LLaMA-Alpaca model assets for local generation, batch prediction, interactive instruction mode, Gradio chat, an OpenAI-compatible FastAPI server, embeddings, or LangChain QA\u002Fsummarization. The commands below assume the current working directory is this sub-skill directory.\n\nDo not launch a long-running server, download model weights, or load a large 7B+ model unless the user confirms model paths, backend use, port\u002Fnetwork exposure, and runtime budget. If the user only has LoRA adapters and no loadable base\u002Fmerged model, route first to `..\u002Fmodel-reconstruction\u002F`.\n\n## Fast Route\n\n1. **Pick the model family.** Chinese LLaMA is base\u002Fcontinuation-oriented; Chinese Alpaca is instruction\u002Fchat-oriented. Use [`references\u002Fhf-inference.md`](references\u002Fhf-inference.md) for prompt and flag details.\n2. **Run batch or interactive HF inference** with [`scripts\u002Finference_hf.py`](scripts\u002Finference_hf.py) when a HF model\u002Fbase+LoRA path is available.\n3. **Use Gradio or API serving only with explicit launch approval.** See [`references\u002Fgradio-and-api-server.md`](references\u002Fgradio-and-api-server.md) before running [`scripts\u002Fgradio_demo.py`](scripts\u002Fgradio_demo.py) or [`scripts\u002Fopenai_api_server.py`](scripts\u002Fopenai_api_server.py).\n4. **Use LangChain guidance for optional app demos.** See [`references\u002Flangchain-integrations.md`](references\u002Flangchain-integrations.md); these scripts require extra packages and model\u002Fembedding paths.\n5. **Debug failures with exact symptoms.** Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for tokenizer mismatch, CPU\u002FGPU, 8-bit, NTK, xFormers, Gradio, FastAPI request schema, and optional dependency errors.\n\n## Bundled Runtime Files\n\n- [`scripts\u002Finference_hf.py`](scripts\u002Finference_hf.py): HF batch and single-turn interactive inference.\n- [`scripts\u002Fgradio_demo.py`](scripts\u002Fgradio_demo.py): Gradio chat UI.\n- [`scripts\u002Fopenai_api_server.py`](scripts\u002Fopenai_api_server.py) and [`scripts\u002Fopenai_api_protocol.py`](scripts\u002Fopenai_api_protocol.py): OpenAI-compatible completions\u002Fchat\u002Fembeddings server and schemas.\n- [`scripts\u002Fpatches.py`](scripts\u002Fpatches.py): local attention and NTK scaling patch module used by inference\u002Fserver scripts.\n- [`scripts\u002Flangchain_qa.py`](scripts\u002Flangchain_qa.py), [`scripts\u002Flangchain_sum.py`](scripts\u002Flangchain_sum.py), and [`scripts\u002Fdoc.txt`](scripts\u002Fdoc.txt): optional LangChain examples.\n\n## Scope Boundaries\n\n- Model conversion, tokenizer extension, SHA256 checks, and LoRA merging belong to `..\u002Fmodel-reconstruction\u002F`.\n- Training or SFT of new adapters belongs to `..\u002Ftraining-finetuning\u002F`.\n- C-Eval scoring and example benchmark interpretation belong to `..\u002Fevaluation-benchmarks\u002F`.\n- This sub-skill can plan CPU-only checks, but CPU generation for 7B+ models is often very slow and is not a substitute for GPU performance validation.\n","# Inference and Deployment Router\n\nUse this sub-skill when a user has, or is preparing, Chinese-LLaMA-Alpaca model assets for local generation, batch prediction, interactive instruction mode, Gradio chat, an OpenAI-compatible FastAPI server, embeddings, or LangChain QA\u002Fsummarization. The commands below assume the current working directory is this sub-skill directory.\n\nDo not launch a long-running server, download model weights, or load a large 7B+ model unless the user confirms model paths, backend use, port\u002Fnetwork exposure, and runtime budget. If the user only has LoRA adapters and no loadable base\u002Fmerged model, route first to `..\u002Fmodel-reconstruction\u002F`.\n\n## Fast Route\n\n1. **Pick the model family.** Chinese LLaMA is base\u002Fcontinuation-oriented; Chinese Alpaca is instruction\u002Fchat-oriented. Use [`references\u002Fhf-inference.md`](references\u002Fhf-inference.md) for prompt and flag details.\n2. **Run batch or interactive HF inference** with [`scripts\u002Finference_hf.py`](scripts\u002Finference_hf.py) when a HF model\u002Fbase+LoRA path is available.\n3. **Use Gradio or API serving only with explicit launch approval.** See [`references\u002Fgradio-and-api-server.md`](references\u002Fgradio-and-api-server.md) before running [`scripts\u002Fgradio_demo.py`](scripts\u002Fgradio_demo.py) or [`scripts\u002Fopenai_api_server.py`](scripts\u002Fopenai_api_server.py).\n4. **Use LangChain guidance for optional app demos.** See [`references\u002Flangchain-integrations.md`](references\u002Flangchain-integrations.md); these scripts require extra packages and model\u002Fembedding paths.\n5. **Debug failures with exact symptoms.** Use [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md) for tokenizer mismatch, CPU\u002FGPU, 8-bit, NTK, xFormers, Gradio, FastAPI request schema, and optional dependency errors.\n\n## Bundled Runtime Files\n\n- [`scripts\u002Finference_hf.py`](scripts\u002Finference_hf.py): HF batch and single-turn interactive inference.\n- [`scripts\u002Fgradio_demo.py`](scripts\u002Fgradio_demo.py): Gradio chat UI.\n- [`scripts\u002Fopenai_api_server.py`](scripts\u002Fopenai_api_server.py) and [`scripts\u002Fopenai_api_protocol.py`](scripts\u002Fopenai_api_protocol.py): OpenAI-compatible completions\u002Fchat\u002Fembeddings server and schemas.\n- [`scripts\u002Fpatches.py`](scripts\u002Fpatches.py): local attention and NTK scaling patch module used by inference\u002Fserver scripts.\n- [`scripts\u002Flangchain_qa.py`](scripts\u002Flangchain_qa.py), [`scripts\u002Flangchain_sum.py`](scripts\u002Flangchain_sum.py), and [`scripts\u002Fdoc.txt`](scripts\u002Fdoc.txt): optional LangChain examples.\n\n## Scope Boundaries\n\n- Model conversion, tokenizer extension, SHA256 checks, and LoRA merging belong to `..\u002Fmodel-reconstruction\u002F`.\n- Training or SFT of new adapters belongs to `..\u002Ftraining-finetuning\u002F`.\n- C-Eval scoring and example benchmark interpretation belong to `..\u002Fevaluation-benchmarks\u002F`.\n- This sub-skill can plan CPU-only checks, but CPU generation for 7B+ models is often very slow and is not a substitute for GPU performance validation.\n",{"name":5,"license":24,"metadata":25,"description":7,"disable-model-invocation":27},"Apache 2.0",{"disco-role":26},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":27},[38,41,44],{"tool":39,"command":40},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill inference-deployment",{"tool":42,"command":43},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill inference-deployment",{"tool":45,"command":46},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill inference-deployment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment\u002FSKILL.md",[49,55,59,63,67],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fgradio-and-api-server.md","REFERENCE","参考文档",3609,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Fgradio-and-api-server.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fhf-inference.md",3836,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Fhf-inference.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Flangchain-integrations.md",2747,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Flangchain-integrations.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Ftroubleshooting.md",4054,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment\u002Freferences\u002Ftroubleshooting.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fdoc.txt","SCRIPT","脚本",6154,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fchinese-llama-alpaca\u002Fsub-skills\u002Finference-deployment\u002Fscripts\u002Fdoc.txt",[74,82,89,96,103,110],{"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":78,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EXRM12046G0GM1WGMMFXCN","ci-cd-and-automation","Automates CI\u002FCD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.","MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fci-cd-and-automation\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EXRFYYSJ3Y15AGPDDEWWQD","chrome-devtools","Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-devtools\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7EXR6EYPE4X5X1BTAE6QJRV","chrome-cdp","Drive a real Chrome via the Chrome DevTools Protocol (CDP). Ensures a\ndebuggable Chrome is running (launching it if needed) so the agent can\nnavigate, read page content, inspect the DOM, run JavaScript, and take\nscreenshots — without the user typing any launch command. Includes a\nfirst-class \"review a live running app\" flow: point Chrome at the app under\ndevelopment and inspect\u002Fscreenshot the REAL page (what a static-artifact tool\ncannot do). Backed by Glimpse and the chrome-devtools MCP server. Use when\nasked to \"use chrome\", \"open chrome\", \"drive my browser\", \"read the page in\nchrome\", \"review the running app\", \"screenshot the app\", or \"\u002Fchrome-cdp\".","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-cdp\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M7EXR1Y7E79KQKG4J798XGH6","check-identity-pack","Run an AFP 100-point or AUSTRAC safe-harbour identity check over a set of documents, and report exactly what's missing. Use when the user asks to check identity documents, verify someone's ID for onboarding, or assess whether a document pack satisfies Australian identity requirements.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcheck-identity-pack\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M7EXQXW7C7PGREJW9ZZTZ16H","changelog","Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchangelog\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":78,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7EXQMH2ZME3ANN8Q8MEWPFB","cellxgene-census","Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs\u002Fdownloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcellxgene-census\u002FSKILL.md",[],[]]