[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P05391N2BW4NP3TXB2S2KA":3,"skill-same:01M6P05391N2BW4NP3TXB2S2KA":95},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6P05391N2BW4NP3TXB2S2KA","code-refactor",null,"Refactor Python code to match this repo's coding standards and style. Use when the user asks to \"refactor\", \"clean up\", \"fix coding standards\", or \"apply best practices\" to a module, file, or directory in this repo. Applies python-best-practices, pydantic v2, pytorch-lightning, and python-docs conventions as relevant to the target code.","arnabdeypolimi\u002Fclaude_code_setup","arnabdeypolimi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F32412133?v=4","01M6P0328AJ1TQ5N763ZSGNRF9","Arnab Dey","01M6P032C9PY7NRT2C9SNRFJ5G",5,"MIT","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-refactor\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"code","refactor","code refactor","use","python code","relevant","as","module","clean","best-practices","standards","up","directory","fix","repo","coding","Pydantic","coding standards","pytorch","python","2026-11-10 10:12:30",false,"---\nname: code-refactor\ndescription: >\n  Refactor Python code to match this repo's coding standards and style.\n  Use when the user asks to \"refactor\", \"clean up\", \"fix coding standards\",\n  or \"apply best practices\" to a module, file, or directory in this repo.\n  Applies python-best-practices, pydantic v2, pytorch-lightning, and\n  python-docs conventions as relevant to the target code.\n---\n\n# Code Refactor Skill\n\nSystematically refactor Python code to match this repo's standards.\n\n## Workflow\n\n### 1. Read Target Code\n\nRead every file in the target module. Never propose changes to code you haven't read.\n\n### 2. Audit Against Checklist\n\nRun through `references\u002Fchecklist.md` and note every violation. Group them by category so the user can see the full picture before any edits are made.\n\n### 3. Run Static Analysis\n\n```bash\nuv run ruff check \u003Ctarget>\nuv run mypy \u003Ctarget>\n```\n\nReport all errors as part of the audit — these are additional violations on top of the checklist.\n\n### 4. Apply Fixes\n\nApply all fixes. Prefer the Edit tool over Write for existing files (smaller diffs, easier review). Make all independent edits in parallel.\n\nPriority order (highest impact first):\n\n1. Type safety — enums over bare strings, `from __future__ import annotations`, proper return types\n2. Pydantic — snake_case fields with aliases, `model_config`, field validators (see `references\u002Fpydantic-patterns.md`)\n3. Error handling — replace `assert` with `if`\u002F`raise`, add context to re-raised exceptions\n4. Python best practices — frozen dataclasses, Protocol types, avoid mutable defaults\n5. PyTorch\u002FLightning — only apply if the module contains `torch` or `nn.Module` code (see `references\u002Fpytorch-patterns.md`)\n6. Docs — public functions must have docstrings (see `references\u002Fdocs-patterns.md`)\n\n### 5. Verify\n\n```bash\nuv run ruff check \u003Ctarget>\nuv run ruff format \u003Ctarget>\nuv run mypy \u003Ctarget>\nuv run pytest tests\u002Funit\u002F\u003Ctarget-name>\u002F -v\n```\n\nAll checks must pass before declaring done. If tests fail, fix them — don't skip.\n\n### 6. Summarise\n\nReport a table of every change made, grouped by category. Include file and line references.\n\n---\n\n## Repo-Specific Conventions\n\n- **Python**: 3.12 — use `StrEnum`, `match`, `X | Y` unions, `from __future__ import annotations` in every file\n- **Linter\u002FFormatter**: Ruff (88 char line length)\n- **Type checker**: mypy (strict — all errors must be resolved)\n- **Package manager**: uv (`uv run \u003Ccmd>`)\n- **Tests**: pytest, mirror source structure under `tests\u002Funit\u002F`\n- **Logging**: `from logging_utils import get_logger` then `logger = get_logger(__name__)` — never `logging.getLogger(__name__)` or `print()`\n- **Imports**: stdlib → third-party → local, each group separated by blank line\n- **Config**: TOML or YAML only — never JSON for config files\n\n## When to Apply Each Sub-Skill\n\n| Code contains | Apply |\n|---------------|-------|\n| `BaseModel`, Pydantic fields | `references\u002Fpydantic-patterns.md` |\n| `torch`, `nn.Module`, `LightningModule` | `references\u002Fpytorch-patterns.md` |\n| Public classes \u002F functions without docstrings | `references\u002Fdocs-patterns.md` |\n| All Python files | `references\u002Fchecklist.md` |\n","# Code Refactor Skill\n\nSystematically refactor Python code to match this repo's standards.\n\n## Workflow\n\n### 1. Read Target Code\n\nRead every file in the target module. Never propose changes to code you haven't read.\n\n### 2. Audit Against Checklist\n\nRun through `references\u002Fchecklist.md` and note every violation. Group them by category so the user can see the full picture before any edits are made.\n\n### 3. Run Static Analysis\n\n```bash\nuv run ruff check \u003Ctarget>\nuv run mypy \u003Ctarget>\n```\n\nReport all errors as part of the audit — these are additional violations on top of the checklist.\n\n### 4. Apply Fixes\n\nApply all fixes. Prefer the Edit tool over Write for existing files (smaller diffs, easier review). Make all independent edits in parallel.\n\nPriority order (highest impact first):\n\n1. Type safety — enums over bare strings, `from __future__ import annotations`, proper return types\n2. Pydantic — snake_case fields with aliases, `model_config`, field validators (see `references\u002Fpydantic-patterns.md`)\n3. Error handling — replace `assert` with `if`\u002F`raise`, add context to re-raised exceptions\n4. Python best practices — frozen dataclasses, Protocol types, avoid mutable defaults\n5. PyTorch\u002FLightning — only apply if the module contains `torch` or `nn.Module` code (see `references\u002Fpytorch-patterns.md`)\n6. Docs — public functions must have docstrings (see `references\u002Fdocs-patterns.md`)\n\n### 5. Verify\n\n```bash\nuv run ruff check \u003Ctarget>\nuv run ruff format \u003Ctarget>\nuv run mypy \u003Ctarget>\nuv run pytest tests\u002Funit\u002F\u003Ctarget-name>\u002F -v\n```\n\nAll checks must pass before declaring done. If tests fail, fix them — don't skip.\n\n### 6. Summarise\n\nReport a table of every change made, grouped by category. Include file and line references.\n\n---\n\n## Repo-Specific Conventions\n\n- **Python**: 3.12 — use `StrEnum`, `match`, `X | Y` unions, `from __future__ import annotations` in every file\n- **Linter\u002FFormatter**: Ruff (88 char line length)\n- **Type checker**: mypy (strict — all errors must be resolved)\n- **Package manager**: uv (`uv run \u003Ccmd>`)\n- **Tests**: pytest, mirror source structure under `tests\u002Funit\u002F`\n- **Logging**: `from logging_utils import get_logger` then `logger = get_logger(__name__)` — never `logging.getLogger(__name__)` or `print()`\n- **Imports**: stdlib → third-party → local, each group separated by blank line\n- **Config**: TOML or YAML only — never JSON for config files\n\n## When to Apply Each Sub-Skill\n\n| Code contains | Apply |\n|---------------|-------|\n| `BaseModel`, Pydantic fields | `references\u002Fpydantic-patterns.md` |\n| `torch`, `nn.Module`, `LightningModule` | `references\u002Fpytorch-patterns.md` |\n| Public classes \u002F functions without docstrings | `references\u002Fdocs-patterns.md` |\n| All Python files | `references\u002Fchecklist.md` |\n",{"name":5,"description":7},"main","afc7b6d68a4179af3aed48adbb19456133f8ae06",".claude\u002Fskills\u002Fcode-refactor",0,"https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi","arnabdey.co","Senior research engineer with a PhD in Deep Learning and Computer Vision ","2026-09-17 03:30:40",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add arnabdeypolimi\u002Fclaude_code_setup --skill code-refactor",{"tool":69,"command":70},"bunx","bunx skills add arnabdeypolimi\u002Fclaude_code_setup --skill code-refactor",{"tool":72,"command":73},"pnpm","pnpm dlx skills add arnabdeypolimi\u002Fclaude_code_setup --skill code-refactor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-refactor\u002FSKILL.md",true,[77,83,87,91],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fchecklist.md","REFERENCE","参考文档",3671,"https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-refactor\u002Freferences\u002Fchecklist.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fdocs-patterns.md",2557,"https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-refactor\u002Freferences\u002Fdocs-patterns.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fpydantic-patterns.md",3158,"https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-refactor\u002Freferences\u002Fpydantic-patterns.md",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fpytorch-patterns.md",2512,"https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-refactor\u002Freferences\u002Fpytorch-patterns.md",[96,105,113,145,162,193],{"skillNo":97,"name":98,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":49},"01M6P0W3RVYQJEJQN9NB4H99T1","git-operations","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002Fcreate-claude-setup\u002Ftest\u002Ffixtures\u002Fhealthy\u002F.claude\u002Fskills\u002Fgit-operations\u002FSKILL.md",[],[102,103,104],"git operations","operations","git",{"skillNo":106,"name":107,"nameZh":6,"description":6,"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":110,"publishedAt":49},"01M6P0W1AG7EQXZQSCBQJ9RD60","python-best-practices","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002Fcreate-claude-setup\u002Ftest\u002Ffixtures\u002Fdrifted\u002F.claude\u002Fskills\u002Fpython-best-practices\u002FSKILL.md",[],[111,112,48],"python best practices","best practices",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":125,"publishedAt":49},"01M6P0VRDYNE55YYX06G81MJJH","typst-paper","Typst academic paper assistant for existing `.typ` paper projects in English or Chinese. Use this skill whenever the user wants to compile, audit, or improve a Typst paper, including format checks, bibliography validation for BibTeX or Hayagriva, grammar\u002Fsentence\u002Flogic review, expression polishing, translation, title optimization, pseudocode review, algorithm block cleanup, de-AI editing, or experiment-section review. Trigger even when the user only mentions one Typst file, one bibliography issue, one pseudocode block, or one section rewrite. Also trigger when the user mentions \".typ files\", \"typst compile error\", \"typst export\", \"typst bibliography\", `algorithm-figure`, `lovelace`, or `algorithmic` even without saying the word \"Typst\" explicitly.","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002Fcreate-claude-setup\u002Fassets\u002Fskills\u002Ftypst-paper\u002FSKILL.md",[119,122],{"categoryNo":120,"categoryName":121,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,54,142,143,144],"paper","typst","typst paper","title","writing","review","cleanup","Bash","improve","projects","only","pseudocode","uv","files","translation","chinese","english","expression","error",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":49},"01M6P0V8N502GK89FSX4PB3DFB","typeset","Improves typography by fixing font choices, hierarchy, sizing, weight, and readability so text feels intentional. Use when the user mentions fonts, type, readability, text hierarchy, sizing looks off, or wants more polished, intentional typography.","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002Fcreate-claude-setup\u002Fassets\u002Fskills\u002Ftypeset\u002FSKILL.md",[],[147,152,153,154,155,156,157,158,159,160,32,161],"fonts","more","user","true","font","hierarchy","type","readability","text","typography",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":177,"publishedAt":49},"01M6P0V3G89JYZ71PA2FVPGM4F","teach-impeccable","One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002Fcreate-claude-setup\u002Fassets\u002Fskills\u002Fteach-impeccable\u002FSKILL.md",[168,171,174],{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":172,"categoryName":173,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师",{"categoryNo":175,"categoryName":176,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000039","教师与教育",[178,179,180,181,182,183,184,185,186,187,188,189,190,191,155,192],"teach impeccable","impeccable","teach","design","config","setup","guidelines","run","file","context","ai config","time","project","it","for",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":204,"publishedAt":49},"01M6P0TEK3SF2V4Y52RVP86JM2","research-paper-writing","Improve academic paper writing quality for ML\u002FCV\u002FNLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures\u002Ftables; checking claim-support alignment; or performing self-review before submission.","https:\u002F\u002Fgithub.com\u002Farnabdeypolimi\u002Fclaude_code_setup\u002Fblob\u002Fmain\u002Fcreate-claude-setup\u002Fassets\u002Fskills\u002Fresearch-paper-writing\u002FSKILL.md",[199,200,201],{"categoryNo":120,"categoryName":121,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":202,"categoryName":203,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000036","内容创作者",[130,126,205,206,207,131,208,209,210,134,211,212,213,214,215,216,217,218,219,220],"research paper writing","research","Paper Writing","support","experiments","flow","reviewer","work","alignment","claim","structure","self","presentation","figures","papers","tables"]