[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79K1STHT4SAA01HKJMNTH7T":3,"skill-same:01M79K1STHT4SAA01HKJMNTH7T":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M79K1STHT4SAA01HKJMNTH7T","pxrdgen",null,"Predict candidate crystal structures from powder X-ray diffraction data and retrieve generated CIF files. Use when a user provides a PXRD .dat input, chemical formula, or PXRDGen task and wants structure candidates or explicit inference trials.","infometa\u002Fworkbuddyskills","infometa","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F109397516?v=4","01M79FS3XQK361MJFWQ2GFK95C","01M79FS3YPWKZYW9EPAAP2BFBJ",447,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fmatelab\u002Fskills\u002Fpxrdgen\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fmatelab\u002Fskills\u002Fpxrdgen\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pxrdgen\ndescription: Predict candidate crystal structures from powder X-ray diffraction data and retrieve generated CIF files. Use when a user provides a PXRD .dat input, chemical formula, or PXRDGen task and wants structure candidates or explicit inference trials.\ndisplay_name: \"PXRDGen 晶体结构预测\"\ndisplay_name_en: \"PXRDGen Crystal Structure Prediction\"\ndescription_zh: \"根据粉末 X 射线衍射数据和化学式生成晶体结构候选，支持比较不同模型结果，并提供可用的 CIF 文件供后续验证。\"\ndescription_en: \"Generate candidate crystal structures from powder X-ray diffraction data and a chemical formula, compare model outputs, and retrieve available CIF files for further validation.\"\nversion: \"0.1.2\"\nauthor: \"Tiannian Zhu\"\n---\n\n# PXRDGen\n\nUse the task-oriented tools from the packaged `pxrdgen` MCP server. Tool names\nbelow are raw MCP names; let the client resolve their namespace.\n\n## Workflow\n\n1. For a local XRD `.dat` file, call `pxrdgen_prepare_upload` with its plain filename.\n   Send the raw bytes with the exact HTTP `PUT` URL, method, and headers it\n   returns. After a successful PUT, retain the returned `attachment_ref`.\n2. For a `.dat` file already available at an HTTP(S) URL under `iphy.ac.cn` or\n   one of its subdomains, call `pxrdgen_ingest_url` with the URL and plain filename.\n   Retain its returned `attachment_ref`.\n3. Call `pxrdgen_predict` with exactly one ref and the user-declared chemical formula.\n   Preserve any explicit `num_evals`, `cell_params`, `step_lr`,\n   `infer_timesteps`, and `model_family` settings. Reuse the same ref for\n   comparisons across parameter sets.\n4. Poll `pxrdgen_get_task_status` with the returned `task_id`. Stop on `FAILED` and\n   report the returned `error` message. Call `pxrdgen_get_task_outputs` only after\n   `SUCCEEDED`.\n5. Preserve candidate index order and use each available direct HTTP GET URL\n   to return the generated CIF file. Report unavailable artifacts rather than\n   reconstructing CIF text.\n\n## Input and Parameter Rules\n\n- Never place local paths, Base64, XRD points, or file bytes in MCP tool\n  arguments. MCP returns transfer instructions; it does not transport the\n  payload.\n- A valid input is UTF-8 `.dat` text no larger than 1 MiB, with exactly 7,500\n  whitespace-delimited `2theta intensity` rows on the grid from `5.00` through\n  `79.99` in increments of `0.01`. Let the Server validate it.\n- `num_evals` is 1–256. `model_family` is `flow` or `diffusion` when supplied.\n  `cell_params` selects constrained prediction and must represent\n  `a,b,c,alpha,beta,gamma`. Use `step_lr` and `infer_timesteps` only as explicit\n  inference controls, not as scientific confidence measures.\n- Treat upload URLs and their headers as short-lived capabilities. Use them\n  only for the specified PUT, and never copy credentials or authentication\n  headers into tool arguments, prose, logs, or retained files.\n\n## Retry and Scientific Boundaries\n\n- Repeating `pxrdgen_ingest_url` with the exact URL and filename is idempotent. An\n  exact `pxrdgen_predict` retry with the same ref, formula, and all parameters returns\n  the existing task. Do not blindly replay any other indeterminate mutation.\n- Retry only when a structured tool error marks the operation retryable, and\n  follow its recovery guidance. A failed task is not an empty prediction.\n- Generated structures are model candidates under the recorded inputs and\n  parameters. Do not describe them as experimentally confirmed, uniquely\n  solved, thermodynamically stable, or synthesizable without separate evidence.\n\nIf the MCP tools are unavailable, ask the user to connect the packaged\n`pxrdgen` server. Do not bypass MCP by calling private provider endpoints,\nsubstitute local structure prediction, or guess task, input, or artifact data.\nRaw HTTP is used only with upload or download instructions returned by MCP.\n","# PXRDGen\n\nUse the task-oriented tools from the packaged `pxrdgen` MCP server. Tool names\nbelow are raw MCP names; let the client resolve their namespace.\n\n## Workflow\n\n1. For a local XRD `.dat` file, call `pxrdgen_prepare_upload` with its plain filename.\n   Send the raw bytes with the exact HTTP `PUT` URL, method, and headers it\n   returns. After a successful PUT, retain the returned `attachment_ref`.\n2. For a `.dat` file already available at an HTTP(S) URL under `iphy.ac.cn` or\n   one of its subdomains, call `pxrdgen_ingest_url` with the URL and plain filename.\n   Retain its returned `attachment_ref`.\n3. Call `pxrdgen_predict` with exactly one ref and the user-declared chemical formula.\n   Preserve any explicit `num_evals`, `cell_params`, `step_lr`,\n   `infer_timesteps`, and `model_family` settings. Reuse the same ref for\n   comparisons across parameter sets.\n4. Poll `pxrdgen_get_task_status` with the returned `task_id`. Stop on `FAILED` and\n   report the returned `error` message. Call `pxrdgen_get_task_outputs` only after\n   `SUCCEEDED`.\n5. Preserve candidate index order and use each available direct HTTP GET URL\n   to return the generated CIF file. Report unavailable artifacts rather than\n   reconstructing CIF text.\n\n## Input and Parameter Rules\n\n- Never place local paths, Base64, XRD points, or file bytes in MCP tool\n  arguments. MCP returns transfer instructions; it does not transport the\n  payload.\n- A valid input is UTF-8 `.dat` text no larger than 1 MiB, with exactly 7,500\n  whitespace-delimited `2theta intensity` rows on the grid from `5.00` through\n  `79.99` in increments of `0.01`. Let the Server validate it.\n- `num_evals` is 1–256. `model_family` is `flow` or `diffusion` when supplied.\n  `cell_params` selects constrained prediction and must represent\n  `a,b,c,alpha,beta,gamma`. Use `step_lr` and `infer_timesteps` only as explicit\n  inference controls, not as scientific confidence measures.\n- Treat upload URLs and their headers as short-lived capabilities. Use them\n  only for the specified PUT, and never copy credentials or authentication\n  headers into tool arguments, prose, logs, or retained files.\n\n## Retry and Scientific Boundaries\n\n- Repeating `pxrdgen_ingest_url` with the exact URL and filename is idempotent. An\n  exact `pxrdgen_predict` retry with the same ref, formula, and all parameters returns\n  the existing task. Do not blindly replay any other indeterminate mutation.\n- Retry only when a structured tool error marks the operation retryable, and\n  follow its recovery guidance. A failed task is not an empty prediction.\n- Generated structures are model candidates under the recorded inputs and\n  parameters. Do not describe them as experimentally confirmed, uniquely\n  solved, thermodynamically stable, or synthesizable without separate evidence.\n\nIf the MCP tools are unavailable, ask the user to connect the packaged\n`pxrdgen` server. Do not bypass MCP by calling private provider endpoints,\nsubstitute local structure prediction, or guess task, input, or artifact data.\nRaw HTTP is used only with upload or download instructions returned by MCP.\n",{"name":5,"author":24,"version":25,"description":7,"display_name":26,"description_en":27,"description_zh":28,"display_name_en":29},"Tiannian Zhu","0.1.2","PXRDGen 晶体结构预测","Generate candidate crystal structures from powder X-ray diffraction data and a chemical formula, compare model outputs, and retrieve available CIF files for further validation.","根据粉末 X 射线衍射数据和化学式生成晶体结构候选，支持比较不同模型结果，并提供可用的 CIF 文件供后续验证。","PXRDGen Crystal Structure Prediction","main","33b6151ccee9aa0816c6f32d021be77d82772755","connectors\u002Fmatelab\u002Fskills\u002Fpxrdgen",138,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills","https:\u002F\u002Fgithub.com\u002Finfometa","2026-11-11 03:15:35",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add infometa\u002Fworkbuddyskills --skill pxrdgen",{"tool":43,"command":44},"bunx","bunx skills add infometa\u002Fworkbuddyskills --skill pxrdgen",{"tool":46,"command":47},"pnpm","pnpm dlx skills add infometa\u002Fworkbuddyskills --skill pxrdgen","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fmatelab\u002Fskills\u002Fpxrdgen\u002FSKILL.md",true,[51,57,61],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Flogo.png","ASSET","资产文件",291900,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fmatelab\u002Fskills\u002Fpxrdgen\u002Fassets\u002Flogo.png",{"path":58,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":15},"LICENSE","许可证",11358,{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"NOTICE","OTHER","其他",660,"https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fconnectors\u002Fmatelab\u002Fskills\u002Fpxrdgen\u002FNOTICE",[68,76,83,90,97,105],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7A1EC013S1PBBTSH2PA2S7D","yingmi-skill","当用户需要查询基金、策略、公告、财经资讯，做资产配置、组合诊断、风险回测、现金流分析，或生成图表、PDF 时，优先使用本 Skill 获取真实数据与可执行能力。","MIT","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fyingmi-skill\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7A194T67P6NRVYK8KCTH3CH","web-access","所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-access\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7A14FATMDD6FK8QAGXY5GVR","tencentmap-map-assistant","腾讯位置服务·地图助手 Skill，一句自然语言调用腾讯地图全套能力，无需开发者账号、开箱即用。提供 AI 旅游攻略、地点搜索（含评分\u002F人均\u002F营业时间）、关键词提示、路线规划（驾车\u002F步行\u002F公交\u002F骑行）、地址解析与逆解析、行政区划、IP 定位、距离计算、天气查询，并可将行程或多 POI 渲染成网页地图。涉及找地点、规划路线、旅游行程、查天气、坐标转换等出行场景时使用。","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Ftencentmap-map-assistant\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7A0SX4XW5053MZ2S921EDH2","skill-scanner","Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描, 检查 skill 安全, audit skill, scan skill, check skill safety, analyze skill, inspect skill, verify skill, skill security, skill supply chain. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fskill-scanner\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7A0SQC2CZB3450G8471673M","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends agent capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":72,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7A0RHV7BKS7DFQF9X9QCCNN","shader-dev","Comprehensive GLSL shader techniques for creating stunning visual effects — ray marching, SDF modeling, fluid simulation, particle systems, procedural generation, lighting, post-processing, and more.","https:\u002F\u002Fgithub.com\u002Finfometa\u002Fworkbuddyskills\u002Fblob\u002Fmain\u002Fskills\u002Fshader-dev\u002FSKILL.md",[],[]]