[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70DC6RFKFTWQGMBPRJFPQ46":3,"skill-same:01M70DC6RFKFTWQGMBPRJFPQ46":88},{"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":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M70DC6RFKFTWQGMBPRJFPQ46","project-cleanup-audit",null,"Audit and safely clean local project repositories or workspaces with excessive generated files, old project residue, dirty Git status, stale worktrees, build caches, duplicate nested projects, confusing roots, or agent context\u002Ftoken waste. Use when the user asks to organize a repo, remove useless files, classify valid project files, clean untracked\u002Fdeleted files, reduce disk usage, migrate from an old repo layout to a canonical project, or prepare a repository for future Codex\u002Fagent work.","EthanYoQ\u002FSkill-hub","EthanYoQ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257484394?v=4","01M70C9QKWR1YS0S7V26DNB18H","Ethan","01M70C9QMER047R5ANZZA6KC2P",11,"MIT","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fproject-cleanup-audit\u002F4735bd4d2756b29c\u002Fproject-cleanup-audit\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],"cleanup","project cleanup audit","audit","cleanup audit","project","layout","classify","work","valid","disk","migrate","reduce","when","generated","files","clean","local","workspaces","remove","projects","2026-11-10 10:12:30",false,"---\nname: project-cleanup-audit\ndescription: Audit and safely clean local project repositories or workspaces with excessive generated files, old project residue, dirty Git status, stale worktrees, build caches, duplicate nested projects, confusing roots, or agent context\u002Ftoken waste. Use when the user asks to organize a repo, remove useless files, classify valid project files, clean untracked\u002Fdeleted files, reduce disk usage, migrate from an old repo layout to a canonical project, or prepare a repository for future Codex\u002Fagent work.\n---\n\n# Project Cleanup Audit\n\n## Operating Rules\n\nUse this skill as an evidence-first cleanup workflow for local repositories. Prioritize preserving user work over reclaiming disk.\n\n- Do not delete, reset, or overwrite until the target paths and rationale are explicit.\n- If evidence is insufficient, provide only known facts, candidate hypotheses, validation paths, and temporary mitigations. Mark unverified conclusions clearly.\n- Keep installed applications, user data directories, credentials, and system-wide caches out of scope unless the user explicitly includes them.\n- Before structural cleanup, create a backup outside the workspace containing Git status, remotes, worktrees, patches, and copies of non-generated untracked files.\n- Stop only development processes whose command line clearly points inside the workspace. Do not stop installed app processes just because the product name matches.\n- Never run whole-repo `git clean -fdX` unless every ignored dry-run path has been classified as safe generated residue. If the dry-run includes datasets, release artifacts, local validation output, `.runtime`, `.codex`, `.codegraph`, or other agent context, delete only explicit pathspecs or resolved literal paths.\n- Do not recursively print or quote sensitive local data directories while auditing. Prefer aggregate sizes, file counts, top-level names, and short non-sensitive samples.\n\n## Quick Audit\n\nRun the bundled read-only audit first when PowerShell is available:\n\n```powershell\npowershell -ExecutionPolicy Bypass -File \"\u003Cskill>\u002Fscripts\u002Faudit_repo_cleanup.ps1\" -Root . -Top 25\n```\n\nUse `-IncludeProcesses` when deletion is blocked by locked files or old dev servers:\n\n```powershell\npowershell -ExecutionPolicy Bypass -File \"\u003Cskill>\u002Fscripts\u002Faudit_repo_cleanup.ps1\" -Root . -Top 25 -IncludeProcesses\n```\n\nUse `-HashReleaseArtifacts` only when checking whether local release packages match already-published assets. This can be slow on GB-scale archives:\n\n```powershell\npowershell -ExecutionPolicy Bypass -File \"\u003Cskill>\u002Fscripts\u002Faudit_repo_cleanup.ps1\" -Root . -Top 25 -HashReleaseArtifacts\n```\n\nRead `references\u002Fclassification.md` before classifying ambiguous files, local models, installers, datasets, dirty worktrees, or nested legacy projects.\n\nWhen the audit reports `Review Required Ignored Paths`, treat those entries as a hard stop for whole-repo ignored cleanup. Classify them path by path before any delete.\n\n## Workflow\n\n1. Restate the cleanup target and boundaries.\n   - Identify the intended canonical project, e.g. remote URL, default branch, active package manifest, app name, or repo root.\n   - State explicitly what will not be touched, such as installed software, user profile data, or external archives.\n\n2. Gather read-only facts.\n   - Record `git rev-parse --show-toplevel`, branch, HEAD, remotes, `git status --short`, worktrees, and top-level sizes.\n   - Compare the current root with the canonical upstream when relevant.\n   - Use dry runs: `git clean -ndX` for ignored files and `git clean -nd` for untracked files.\n   - Inspect the audit's `review_required_ignored_paths` before considering any ignored cleanup.\n   - For release-heavy repositories, inspect `release_artifacts`. If available, compare package names, sizes, and SHA256 values against the release host before deleting versioned archives.\n   - Inspect `local_context_paths` before deleting `.codex`, `.codegraph`, `.gstack`, `.venv`, `.pytest_cache`, or `__pycache__`.\n   - Inspect `local_data_evidence_paths` by aggregate counts and extensions; do not recursively print sensitive document names or contents.\n   - Inspect package\u002Fbuild manifests: `package.json`, `Cargo.toml`, `pyproject.toml`, `go.mod`, `pom.xml`, `*.sln`, etc.\n\n3. Classify paths.\n   - `delete after confirmation`: ignored\u002Frebuildable build outputs, dependency installs, logs, test browser profiles, diagnostics.\n   - `backup\u002Farchive first`: untracked source, dirty worktrees, nested old projects, release packages not confirmed uploaded.\n   - `keep`: source, manifests, lockfiles, CI, docs, migrations, public assets, test fixtures.\n   - `needs explicit user confirmation`: local models, datasets, databases, installers, credentials, external user data.\n   - For `build\u002F`, classify tracked packaging configuration separately from ignored `build\u002Fwork`, `build\u002Fruntime`, and generated metadata.\n\n4. Back up before structural changes.\n   - Save status\u002Fremotes\u002Fworktrees\u002Flogs to a backup directory outside the workspace.\n   - Save `git diff --binary` patches for dirty tracked files.\n   - Copy non-generated untracked files, excluding clearly rebuildable caches such as `node_modules`, `target`, `dist`, `.next`, and browser output.\n\n5. Execute the smallest safe cleanup.\n   - Prefer exact path deletion or `git clean -fdX -- \u003Cpathspec...>` for ignored generated files after reviewing `git clean -ndX`.\n   - Use whole-repo `git clean -fdX` only when the ignored dry-run has no review-required paths and all entries are safe generated residue.\n   - Use `git worktree remove` for registered worktrees; do not raw-delete registered worktrees first.\n   - Use native shell deletion with literal paths and resolved workspace-bound checks.\n   - On Windows, verify resolved absolute paths stay inside the workspace before recursive deletion.\n\n6. Handle canonical root migration only after backup.\n   - If the current directory is an old repo shell and the real product repo is another remote\u002Fbranch\u002Flayout, switch or clone to the canonical root only after preserving dirty work.\n   - Do not force-delete unmerged local branches unless the user explicitly accepts losing that history.\n   - Prune stale remote refs and tags only after the remote is correct.\n\n7. Verify.\n   - Show final `git status`, branch\u002Fupstream, remotes, worktrees, top-level tree, and disk usage.\n   - Run a minimal dependency or build dry-run when reasonable, e.g. `npm ci --dry-run --ignore-scripts`.\n   - Report any remaining locked or intentionally retained residue with reason and size.\n\n## Output Format\n\nWhen reporting results, keep the distinction clear:\n\n- Known facts\n- Cleanup actions taken\n- Backups created\n- Remaining risks or unverified assumptions\n- Recommended next action\n\nNever present a destructive cleanup as \"fixed\" if only an audit was completed.\n","# Project Cleanup Audit\n\n## Operating Rules\n\nUse this skill as an evidence-first cleanup workflow for local repositories. Prioritize preserving user work over reclaiming disk.\n\n- Do not delete, reset, or overwrite until the target paths and rationale are explicit.\n- If evidence is insufficient, provide only known facts, candidate hypotheses, validation paths, and temporary mitigations. Mark unverified conclusions clearly.\n- Keep installed applications, user data directories, credentials, and system-wide caches out of scope unless the user explicitly includes them.\n- Before structural cleanup, create a backup outside the workspace containing Git status, remotes, worktrees, patches, and copies of non-generated untracked files.\n- Stop only development processes whose command line clearly points inside the workspace. Do not stop installed app processes just because the product name matches.\n- Never run whole-repo `git clean -fdX` unless every ignored dry-run path has been classified as safe generated residue. If the dry-run includes datasets, release artifacts, local validation output, `.runtime`, `.codex`, `.codegraph`, or other agent context, delete only explicit pathspecs or resolved literal paths.\n- Do not recursively print or quote sensitive local data directories while auditing. Prefer aggregate sizes, file counts, top-level names, and short non-sensitive samples.\n\n## Quick Audit\n\nRun the bundled read-only audit first when PowerShell is available:\n\n```powershell\npowershell -ExecutionPolicy Bypass -File \"\u003Cskill>\u002Fscripts\u002Faudit_repo_cleanup.ps1\" -Root . -Top 25\n```\n\nUse `-IncludeProcesses` when deletion is blocked by locked files or old dev servers:\n\n```powershell\npowershell -ExecutionPolicy Bypass -File \"\u003Cskill>\u002Fscripts\u002Faudit_repo_cleanup.ps1\" -Root . -Top 25 -IncludeProcesses\n```\n\nUse `-HashReleaseArtifacts` only when checking whether local release packages match already-published assets. This can be slow on GB-scale archives:\n\n```powershell\npowershell -ExecutionPolicy Bypass -File \"\u003Cskill>\u002Fscripts\u002Faudit_repo_cleanup.ps1\" -Root . -Top 25 -HashReleaseArtifacts\n```\n\nRead `references\u002Fclassification.md` before classifying ambiguous files, local models, installers, datasets, dirty worktrees, or nested legacy projects.\n\nWhen the audit reports `Review Required Ignored Paths`, treat those entries as a hard stop for whole-repo ignored cleanup. Classify them path by path before any delete.\n\n## Workflow\n\n1. Restate the cleanup target and boundaries.\n   - Identify the intended canonical project, e.g. remote URL, default branch, active package manifest, app name, or repo root.\n   - State explicitly what will not be touched, such as installed software, user profile data, or external archives.\n\n2. Gather read-only facts.\n   - Record `git rev-parse --show-toplevel`, branch, HEAD, remotes, `git status --short`, worktrees, and top-level sizes.\n   - Compare the current root with the canonical upstream when relevant.\n   - Use dry runs: `git clean -ndX` for ignored files and `git clean -nd` for untracked files.\n   - Inspect the audit's `review_required_ignored_paths` before considering any ignored cleanup.\n   - For release-heavy repositories, inspect `release_artifacts`. If available, compare package names, sizes, and SHA256 values against the release host before deleting versioned archives.\n   - Inspect `local_context_paths` before deleting `.codex`, `.codegraph`, `.gstack`, `.venv`, `.pytest_cache`, or `__pycache__`.\n   - Inspect `local_data_evidence_paths` by aggregate counts and extensions; do not recursively print sensitive document names or contents.\n   - Inspect package\u002Fbuild manifests: `package.json`, `Cargo.toml`, `pyproject.toml`, `go.mod`, `pom.xml`, `*.sln`, etc.\n\n3. Classify paths.\n   - `delete after confirmation`: ignored\u002Frebuildable build outputs, dependency installs, logs, test browser profiles, diagnostics.\n   - `backup\u002Farchive first`: untracked source, dirty worktrees, nested old projects, release packages not confirmed uploaded.\n   - `keep`: source, manifests, lockfiles, CI, docs, migrations, public assets, test fixtures.\n   - `needs explicit user confirmation`: local models, datasets, databases, installers, credentials, external user data.\n   - For `build\u002F`, classify tracked packaging configuration separately from ignored `build\u002Fwork`, `build\u002Fruntime`, and generated metadata.\n\n4. Back up before structural changes.\n   - Save status\u002Fremotes\u002Fworktrees\u002Flogs to a backup directory outside the workspace.\n   - Save `git diff --binary` patches for dirty tracked files.\n   - Copy non-generated untracked files, excluding clearly rebuildable caches such as `node_modules`, `target`, `dist`, `.next`, and browser output.\n\n5. Execute the smallest safe cleanup.\n   - Prefer exact path deletion or `git clean -fdX -- \u003Cpathspec...>` for ignored generated files after reviewing `git clean -ndX`.\n   - Use whole-repo `git clean -fdX` only when the ignored dry-run has no review-required paths and all entries are safe generated residue.\n   - Use `git worktree remove` for registered worktrees; do not raw-delete registered worktrees first.\n   - Use native shell deletion with literal paths and resolved workspace-bound checks.\n   - On Windows, verify resolved absolute paths stay inside the workspace before recursive deletion.\n\n6. Handle canonical root migration only after backup.\n   - If the current directory is an old repo shell and the real product repo is another remote\u002Fbranch\u002Flayout, switch or clone to the canonical root only after preserving dirty work.\n   - Do not force-delete unmerged local branches unless the user explicitly accepts losing that history.\n   - Prune stale remote refs and tags only after the remote is correct.\n\n7. Verify.\n   - Show final `git status`, branch\u002Fupstream, remotes, worktrees, top-level tree, and disk usage.\n   - Run a minimal dependency or build dry-run when reasonable, e.g. `npm ci --dry-run --ignore-scripts`.\n   - Report any remaining locked or intentionally retained residue with reason and size.\n\n## Output Format\n\nWhen reporting results, keep the distinction clear:\n\n- Known facts\n- Cleanup actions taken\n- Backups created\n- Remaining risks or unverified assumptions\n- Recommended next action\n\nNever present a destructive cleanup as \"fixed\" if only an audit was completed.\n",{"name":5,"description":7},"mine","1e7390741dffd3d5041fca4ebc056071ee3ba137","archives\u002Fuser-installed-skills\u002Fproject-cleanup-audit\u002F4735bd4d2756b29c\u002Fproject-cleanup-audit",5,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub","https:\u002F\u002Fgithub.com\u002FEthanYoQ","www.orz.md","Part Marketer, Part AI Explorer.","2026-11-07 14:52:29",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add EthanYoQ\u002FSkill-hub --skill project-cleanup-audit",{"tool":64,"command":65},"bunx","bunx skills add EthanYoQ\u002FSkill-hub --skill project-cleanup-audit",{"tool":67,"command":68},"pnpm","pnpm dlx skills add EthanYoQ\u002FSkill-hub --skill project-cleanup-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fproject-cleanup-audit\u002F4735bd4d2756b29c\u002Fproject-cleanup-audit\u002FSKILL.md",true,[72,78,82],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"agents\u002Fopenai.yaml","REFERENCE","参考文档",255,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fproject-cleanup-audit\u002F4735bd4d2756b29c\u002Fproject-cleanup-audit\u002Fagents\u002Fopenai.yaml",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fclassification.md",4126,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fproject-cleanup-audit\u002F4735bd4d2756b29c\u002Fproject-cleanup-audit\u002Freferences\u002Fclassification.md",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Faudit_repo_cleanup.ps1","SCRIPT","脚本",14492,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fproject-cleanup-audit\u002F4735bd4d2756b29c\u002Fproject-cleanup-audit\u002Fscripts\u002Faudit_repo_cleanup.ps1",[89,116,146,170,188,203],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":96,"publishedAt":44},"01M713CBDSYARG4PXFXK2R2NNN","xhs-pharma-social-listening","Run evidence-disciplined Xiaohongshu social listening for foreign pharma employee pain points. Use when the user asks to collect and analyze notes\u002Fcomments about pharma companies, aliases, roles, compliance, medical affairs, or AI topics, then produce a cited and scored sampled-insight report. Includes independent-evidence counting, MediaCrawler batch collection, and CAPTCHA\u002F461 fallback to Agent Reach\u002FOpenCLI.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fxhs-pharma-social-listening\u002FSKILL.md",[95],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[97,98,99,100,101,102,36,103,104,105,106,107,108,109,110,111,112,113,114,115],"social","xhs pharma social listening","social listening","xhs","medical","counting","collection","batch","analyze","notes","run","opencli","fallback","captcha","agent reach","evidence","for","collect","produce",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":128,"publishedAt":44},"01M713C8Q76ZP0WXXBRAFKS6EE","healthcare-phi-compliance","Protected Health Information (PHI) and Personally Identifiable Information (PII) compliance patterns for healthcare applications. Covers data classification, access control, audit trails, encryption, and common leak vectors. Use when code touches PHI or PII in a healthcare system, or when auditing access control, audit trails, or leak vectors.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-phi-compliance\u002FSKILL.md",[122,123],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[129,130,131,132,133,134,135,136,36,137,138,139,26,140,141,142,113,143,144,145],"healthcare","phi","compliance","healthcare phi compliance","pii","compliance patterns","information","access","encryption","code","common","data","patterns","Access Control","system","applications","Auditing Access Control",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":153,"publishedAt":44},"01M713C5R2GE43X45T2K75TB76","healthcare-eval-harness","Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures. Use when a healthcare deployment must be gated on patient-safety tests for CDSS accuracy, PHI exposure, and workflow integrity.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-eval-harness\u002FSKILL.md",[152],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[129,154,155,156,157,158,159,36,160,161,162,163,130,113,164,165,166,167,168,169],"eval","harness","healthcare eval harness","eval harness","clinical","patient","workflow","Evaluation","Safety","integrity","deployment","accuracy","tests","deployments","use","super",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":177,"publishedAt":44},"01M713C2J17S91VYR7A8M696VR","healthcare-emr-patterns","EMR\u002FEHR development patterns for healthcare applications. Clinical safety, encounter workflows, prescription generation, clinical decision support integration, and accessibility-first UI for medical data entry. Use when building EMR or EHR features such as encounter workflows, prescription generation, or clinical data entry UI.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-emr-patterns\u002FSKILL.md",[176],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[129,178,141,179,180,101,158,181,36,182,183,184,162,140,185,186,187,113,144,168],"EMR","healthcare emr patterns","decision","workflows","support","clinical decision support","features","ui","as","development",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":44},"01M713BZERTXV0N8X6SW9DDVWZ","healthcare-cdss-patterns","Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows. Use when building clinical decision support — drug interaction checks, dose validation, clinical scoring, or alert severity.","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fhealthcare-cdss-patterns\u002FSKILL.md",[194],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[129,141,196,180,158,178,181,36,197,198,182,183,199,187,143,200,168,201,169,202],"healthcare cdss patterns","scoring","interaction","severity","classification","alert","decision support",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":207,"categories":208,"keywords":210,"publishedAt":44},"01M713BVK3PQR7V4ZKYGMWMXJD","dxy-task-clarify","用户的请求含糊、缺背景、缺资料说明、缺读者或用途时使用。先用少量带选项的追问把任务问清楚，写成任务卡，用户确认后再执行。尤其适用于医生、科研人员和药企各岗位的工作，例如「帮我分析一下这些数据」「帮我准备明天的拜访」「写个总结」「做个 PPT」「回一下这封邮件」「整理一下会议纪要」「整理一下这些文献」「帮我准备下周的讲课」「写个病例汇报」「帮我写个提示词」。用户说「先问我」「帮我理清需求」「我不知道怎么描述」「我不会问 AI」时也使用。用途、资料、读者都已说清的请求，纯翻译，以及写代码、改代码，不使用。","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F10-business-industry\u002Fdxy-task-clarify\u002FSKILL.md",[209],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[211,212,213,214,215,216,217,218],"clarify","dxy task clarify","task","pptx","整理","翻译","数据","总结"]