[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7136H42PEPDK0Y4GH7M32BK":3,"skill-same:01M7136H42PEPDK0Y4GH7M32BK":196},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M7136H42PEPDK0Y4GH7M32BK","yq-windows-trash-cleaner",null,"Windows C盘、项目垃圾、Docker\u002FWSL、Git worktree、CodeGraph、Agent 会话或内存异常需要安全审计、清理和验证时使用。","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\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"yq windows trash cleaner","windows","yq","package-manager","windows 11","windows 10","with","artifacts","package","安全","docker","Tools","manager","git","run","worktree","git worktree","when","only","powershell","2026-11-10 10:12:30",false,"---\nname: yq-windows-trash-cleaner\ndescription: Windows C盘、项目垃圾、Docker\u002FWSL、Git worktree、CodeGraph、Agent 会话或内存异常需要安全审计、清理和验证时使用。\nmetadata:\n  compatibility: Windows 10 or Windows 11 x64 with PowerShell 5.1 or newer. Optional Git, Docker, WSL, package-manager, and CodeGraph checks run only when those tools or artifacts exist.\n---\n\n# YQ Windows Trash Cleaner\n\nRun an evidence-first Windows maintenance workflow that is safe to invoke at any time and is not tied to one project, drive, application, or prior incident.\n\n## Route the request\n\nDistinguish storage from RAM before collecting data:\n\n- Storage intent: C drive\u002Ffull disk, rapid GB growth, caches, projects, worktrees, Docker\u002FWSL images, backups, sessions, compression, or cleanup.\n- RAM intent: processes consuming memory, paged\u002Fnonpaged pool, pool tags, startup storms, long-running workload growth, Fast Startup, or suspected leaks.\n- Mixed intent: run the storage and memory tracks separately and reconcile them only in the final report.\n\nClassify authorization:\n\n- `AUDIT_ONLY`: inspect and report. Phrases such as “哪些可以删” do not authorize deletion.\n- `PLAN_ONLY`: produce exact manifest IDs, commands, recovery, and predicted impact without changing state.\n- `APPLY_APPROVED`: execute only the candidate IDs the user explicitly approved or an exact safe-clean scope the user explicitly requested after seeing the classification.\n\nScanning is always read-only. A report, HTML button, color, ignored status, or large size is never authorization.\n\n## Safety contract\n\nProtect user work before reclaiming space:\n\n- Never delete documents, downloads, sessions, databases, credentials, models, evidence, backups, dirty\u002Funmerged worktrees, release artifacts, Docker volumes, system files, or unknown directories by category name alone.\n- Do not run whole-repository `git clean -fdX`, blanket `docker volume prune`, or raw recursive worktree deletion.\n- Do not hand-delete WinSxS, DriverStore, Windows Installer, pagefile, hiberfil, recovery data, or VSS data.\n- Do not follow reparse points while measuring or deleting. Resolve every target and reject a target equal to an approved root, outside it, or sharing only a text prefix.\n- Keep active projects protected. Read repository instructions and current-state documents; check Git state, worktrees, running processes, locks, manifests, lockfiles, evidence paths, and regeneration commands.\n- Prefer semantic maintenance: package-manager prune commands, `git worktree remove`, Docker object IDs, official DISM analysis\u002Fcleanup, transactional SQLite maintenance, or moving a review item to the Recycle Bin.\n- Hard deletion is off by default. It requires a fresh explicit decision, exact paths\u002FIDs, full preflight, and an action log.\n\n## Run layout\n\nCreate a timestamped run directory outside all scanned or cleaned targets:\n\n```text\nrun\u002F\n  scope.json\n  baseline\u002F\n  projects\u002Fprojects.json\n  storage\u002Fstorage.json\n  memory\u002F\n  cleanup-manifest.json\n  changes\u002Faction-log.jsonl\n  verification\u002F\n  report.html\n  final-report.md\n```\n\nRecord timestamps, boot time, scan roots, excluded roots, access failures, commands and exit codes, tool availability, free bytes, and whether sizes are logical, allocated, compressed, sparse, or unknown.\n\n## Whole-computer storage workflow\n\n### 1. Establish current volume state and historical delta\n\nEnumerate fixed volumes, capacity, filesystem, free bytes, BitLocker visibility when available, and prior trustworthy snapshots. Do not call normal variation “rapid growth” without a before\u002Fafter delta.\n\nRun `scripts\u002FGet-ComputerProjectInventory.ps1` with explicit scan roots. Start with every known development root, registered Git worktree root, user Documents\u002FDesktop, temporary development roots, and additional fixed-volume workspace roots. Avoid broad Windows and application-install roots unless the evidence points there.\n\nFor one repository or a small set of known repositories, run `scripts\u002FGet-ProjectCleanupAudit.ps1` first. It adds `git clean -ndX` and `git clean -nd` previews, release\u002Fevidence summaries, active-owner evidence without exporting command lines, and explicit `review_required_ignored_paths`. This is still an audit: it never deletes or stops processes. Read [project-cleanup-classification.md](references\u002Fproject-cleanup-classification.md).\n\nRun `scripts\u002FGet-ComputerStorageInventory.ps1` for system and user storage candidates. Use `scripts\u002FMeasure-PathUsage.ps1` for exact follow-up measurements. Record inaccessible trees instead of silently treating them as zero.\n\nDefault root discovery is heuristic, not proof of complete-computer coverage. For a whole-computer claim, explicitly enumerate all fixed volumes, known workspace roots, and every path returned by `git worktree list --porcelain`; list excluded and inaccessible roots in the report.\n\n### 2. Inventory every project semantically\n\nFor each discovered Git repository, worktree, or manifest-backed project, record:\n\n- canonical root, remote\u002Fdefault branch, branch\u002FHEAD, dirty and untracked state;\n- registered worktrees and whether each HEAD is contained in the verified remote default branch;\n- active process command lines that point inside the root;\n- project instructions and current-state\u002Fevidence documents;\n- manifests and lockfiles that prove a cache can be rebuilt;\n- generated candidates such as `node_modules`, `.venv`, `target`, `.next`, test caches, browser output, CodeGraph databases, and build directories;\n- ambiguous data such as `output`, `dist`, `release`, datasets, models, reports, validation runs, and agent context.\n\nDo not infer that `dist`, `build`, `output`, `.runtime`, `.codex`, `.claude`, or `.codegraph` is disposable. Classify their contents and role first. Read [whole-computer-project-audit.md](references\u002Fwhole-computer-project-audit.md).\n\n### 3. Inventory cross-project and application storage\n\nInspect, when present:\n\n- npm, pnpm, yarn, Bun, pip, uv, Cargo, NuGet, Gradle, Maven, browser, model, and updater caches;\n- Codex\u002FClaude\u002Fother agent sessions, runtimes, plugins, managed caches, and worktrees;\n- Docker logical objects separately from VHDX physical allocation;\n- WSL distributions and VHDX files;\n- Temp, Recycle Bin, WER\u002Fdumps, update delivery, driver installers, application backups, and databases;\n- pagefile, hiberfil, component store, DriverStore, Installer cache, Reserved Storage, VSS, and restore points as system-managed or official-tool-only categories.\n\nUse package managers' own inventory\u002Fprune operations. A cache's total size is an upper bound, not guaranteed reclaimable space. Read [storage-classification.md](references\u002Fstorage-classification.md) and [docker-storage.md](references\u002Fdocker-storage.md).\n\n### 4. Classify decisions, not just directories\n\nUse stable machine classes; colors may mirror them in the human report but never grant permission:\n\n- `SAFE_REBUILDABLE`: exact generated object with a proven regeneration path, inactive owner, contained target, and no evidence\u002Fuser data.\n- `REVIEW_REQUIRED`: useful history, project dependencies, clean but unverified clones, backups, sessions, installers, downloads, models, inactive Docker objects, or anything with judgement cost.\n- `KEEP_USER_OR_EVIDENCE`: source, dirty work, current\u002Farchived evidence, databases, restore volumes, current sessions, and unknown ownership.\n- `SYSTEM_MANAGED_DO_NOT_DELETE`: protected Windows files, component\u002Finstaller\u002Fdriver\u002Frecovery stores, or storage whose official analysis is unavailable.\n- `ADMIN_EVIDENCE_REQUIRED`: DISM, VSS, restore-point, Reserved Storage, VHDX compaction, or other facts not visible without elevation.\n\nThe detailed deletion gates are also summarized in [cleanup-classification.md](references\u002Fcleanup-classification.md).\n\nEvery candidate needs a confidence level, current bytes, owner, activity check, deletion impact, recovery\u002Fregeneration, exact action, expected verification, and approval state.\n\n### 5. Produce both JSON and a local report\n\nKeep scan data separate from analysis. Generate a local static report with `scripts\u002FNew-StorageAuditReport.ps1` after classifications are present. Use this reading order:\n\n1. volume overview and coverage gaps;\n2. top space consumers;\n3. recommended priority;\n4. candidates by class;\n5. retained risks and long-term prevention.\n\nThe report may contain private project names and absolute paths. Keep it local by default and redact before sharing. It must not expose direct hard-delete controls. The report information architecture has documented design provenance; see [design-provenance.md](references\u002Fdesign-provenance.md).\n\n## Manifest and controlled execution\n\nCreate `cleanup-manifest.json` before any state change:\n\n```json\n{\n  \"id\": \"project-cache-001\",\n  \"class\": \"SAFE_REBUILDABLE\",\n  \"action\": \"pnpm-store-prune\",\n  \"target\": \"C:\\\\absolute\\\\path-or-object-id\",\n  \"expected_command_path\": \"C:\\\\absolute\\\\path\\\\to\\\\pnpm.cmd\",\n  \"bytes\": 123,\n  \"owner\": \"tool-or-project\",\n  \"preconditions\": [\"path-contained\", \"size-rechecked\", \"owner-inactive\"],\n  \"recovery\": \"documented regeneration command\",\n  \"approved\": false\n}\n```\n\nBefore applying an approved item:\n\n1. Resolve and contain the exact target; reject reparse escapes.\n2. Recheck size, owner, Git state, process state, and other drift fields.\n3. Confirm the action type is compatible with the class.\n4. Capture the pre-action free bytes and relevant backup\u002Fstatus evidence.\n5. Execute only this ID. Stop on drift or unexpected output; never widen scope.\n6. Record exit status, released bytes, recovery status, and post-action verification.\n\nFor the built-in semantic allowlist, run `scripts\u002FInvoke-ApprovedCleanupManifest.ps1` first without `-Apply` and pass the exact `-ApprovedId` values. Record its `PreflightToken`. Apply only after the entire batch passes, using the same manifest and IDs plus `-Apply -PreflightToken \u003Ctoken>`; the executor reruns all preflights and rejects a stale token before the first mutation. Package actions must bind `target` to the cache path reported by the owning tool and bind `expected_command_path` to the reviewed `.exe` or `.cmd`. The executor intentionally rejects arbitrary commands, raw recursive deletion, string booleans, unapproved items, non-`SAFE_REBUILDABLE` classes, active or ambiguous owners, reparse paths, and unverified worktrees. Unsupported actions remain manual review items; never broaden the script's allowlist during a cleanup run merely to make an item pass.\n\nFor multiple IDs, complete preflight for the entire batch before the first mutation, then execute in smallest-risk order. A failed later item does not make earlier actions transactional; the action log must say exactly what happened.\n\n## Special storage rules\n\n### Docker and WSL\n\nRun `scripts\u002FGet-DockerStorageAudit.ps1`. Keep logical objects separate from VHDX physical storage. Do not start an auto-restarting container fleet only to obtain inventory without considering impact. VHDX compaction requires a current logical inventory, all consumers stopped, `wsl --shutdown`, detached\u002Fno-handle proof, and administrator access. Never promise the arithmetic sparse difference. Read [docker-storage.md](references\u002Fdocker-storage.md).\n\n### Git worktrees and temporary clones\n\nA worktree becomes eligible only when it is registered, clean including untracked files, inactive, and its HEAD is contained in the verified remote default branch. Remove it with `git worktree remove`, then prune metadata. A standalone temporary clone also needs clean status and remote containment; prefer recoverable removal when value is uncertain.\n\n### CodeGraph\n\nTreat `.codegraph` as rebuildable only after verifying it is an index, not project evidence, and that the project has no active indexing transaction. Separate the main database from WAL\u002FSHM. Prefer fixing `codegraph.json` exclusions and rebuilding rather than repeatedly deleting a growing WAL. Exclusions change semantic search coverage, not project build inputs, unless project code explicitly reads that configuration.\n\n### Sessions, backups, databases, and models\n\nRetain by default. Consider transparent compression or retention review before deletion. Database maintenance requires owner shutdown, a verified recovery copy, integrity checks, transactional changes, and post-checks. Keep at least one current backup and one pre-maintenance recovery point unless the user approves a different retention policy.\n\n## Memory workflow\n\nRun `scripts\u002FCollect-WindowsHealthSnapshot.ps1` at clean login, during representative workload, after it ends, and at long-run milestones. Separate processes, paged\u002Fnonpaged kernel pool, pool tags, cache\u002Fstandby, and pagefile. Never join trends across different boot times.\n\nUse `scripts\u002FGet-LongRunMemoryAssessment.ps1` and these outcome labels:\n\n- `VERIFIED_FIXED`: representative workload plus valid 48-hour same-boot coverage, no warning\u002Fcritical sample, no sustained pool growth, and functional gates pass.\n- `HEALTHY_SO_FAR_PENDING_LONG_RUN`: healthy evidence but less than 48 hours or incomplete representative workload.\n- `ROOT_CAUSE_NOT_PROVEN`: abnormal growth exists but no reproducible component\u002Fdriver A\u002FB proves ownership.\n- `WARNING_REVIEW_REQUIRED`: thresholds or sustained growth are exceeded.\n- `ROLLBACK_REQUIRED`: a change caused functional or event-log regression.\n\nFast Startup affects shutdown plus power-on, not Restart. It can preserve a leaking kernel session but does not create the leak. Restore it only after 24\u002F48-hour stability evidence and an explicit experience tradeoff. Do not disable Defender, storage, network, audio, graphics, or other drivers from one sample or a tag-name association. Read [memory-diagnosis.md](references\u002Fmemory-diagnosis.md) and [quality-gates.md](references\u002Fquality-gates.md).\n\n## Verification and outcome\n\nMeasure actual volume free-byte change; do not sum candidate logical sizes as released bytes. Re-run affected project status, worktree lists, package\u002Fcache status, Docker\u002FWSL inventory, database checks, and application smoke tests. For system changes, verify networking\u002FVPN, audio\u002Fmicrophone, OneDrive, input\u002FFn controls, search, and touched vendor software.\n\nLead with the outcome and use these sections:\n\n- Verified facts\n- Cleanup actions taken\n- Actual released bytes\n- Retained and protected items\n- Unverified\u002Fadmin-blocked items\n- Rollback or regeneration\n- Next maintenance milestone\n\nNever call an audit a cleanup, a candidate size released space, or healthy current memory a proven root-cause fix.\n","# YQ Windows Trash Cleaner\n\nRun an evidence-first Windows maintenance workflow that is safe to invoke at any time and is not tied to one project, drive, application, or prior incident.\n\n## Route the request\n\nDistinguish storage from RAM before collecting data:\n\n- Storage intent: C drive\u002Ffull disk, rapid GB growth, caches, projects, worktrees, Docker\u002FWSL images, backups, sessions, compression, or cleanup.\n- RAM intent: processes consuming memory, paged\u002Fnonpaged pool, pool tags, startup storms, long-running workload growth, Fast Startup, or suspected leaks.\n- Mixed intent: run the storage and memory tracks separately and reconcile them only in the final report.\n\nClassify authorization:\n\n- `AUDIT_ONLY`: inspect and report. Phrases such as “哪些可以删” do not authorize deletion.\n- `PLAN_ONLY`: produce exact manifest IDs, commands, recovery, and predicted impact without changing state.\n- `APPLY_APPROVED`: execute only the candidate IDs the user explicitly approved or an exact safe-clean scope the user explicitly requested after seeing the classification.\n\nScanning is always read-only. A report, HTML button, color, ignored status, or large size is never authorization.\n\n## Safety contract\n\nProtect user work before reclaiming space:\n\n- Never delete documents, downloads, sessions, databases, credentials, models, evidence, backups, dirty\u002Funmerged worktrees, release artifacts, Docker volumes, system files, or unknown directories by category name alone.\n- Do not run whole-repository `git clean -fdX`, blanket `docker volume prune`, or raw recursive worktree deletion.\n- Do not hand-delete WinSxS, DriverStore, Windows Installer, pagefile, hiberfil, recovery data, or VSS data.\n- Do not follow reparse points while measuring or deleting. Resolve every target and reject a target equal to an approved root, outside it, or sharing only a text prefix.\n- Keep active projects protected. Read repository instructions and current-state documents; check Git state, worktrees, running processes, locks, manifests, lockfiles, evidence paths, and regeneration commands.\n- Prefer semantic maintenance: package-manager prune commands, `git worktree remove`, Docker object IDs, official DISM analysis\u002Fcleanup, transactional SQLite maintenance, or moving a review item to the Recycle Bin.\n- Hard deletion is off by default. It requires a fresh explicit decision, exact paths\u002FIDs, full preflight, and an action log.\n\n## Run layout\n\nCreate a timestamped run directory outside all scanned or cleaned targets:\n\n```text\nrun\u002F\n  scope.json\n  baseline\u002F\n  projects\u002Fprojects.json\n  storage\u002Fstorage.json\n  memory\u002F\n  cleanup-manifest.json\n  changes\u002Faction-log.jsonl\n  verification\u002F\n  report.html\n  final-report.md\n```\n\nRecord timestamps, boot time, scan roots, excluded roots, access failures, commands and exit codes, tool availability, free bytes, and whether sizes are logical, allocated, compressed, sparse, or unknown.\n\n## Whole-computer storage workflow\n\n### 1. Establish current volume state and historical delta\n\nEnumerate fixed volumes, capacity, filesystem, free bytes, BitLocker visibility when available, and prior trustworthy snapshots. Do not call normal variation “rapid growth” without a before\u002Fafter delta.\n\nRun `scripts\u002FGet-ComputerProjectInventory.ps1` with explicit scan roots. Start with every known development root, registered Git worktree root, user Documents\u002FDesktop, temporary development roots, and additional fixed-volume workspace roots. Avoid broad Windows and application-install roots unless the evidence points there.\n\nFor one repository or a small set of known repositories, run `scripts\u002FGet-ProjectCleanupAudit.ps1` first. It adds `git clean -ndX` and `git clean -nd` previews, release\u002Fevidence summaries, active-owner evidence without exporting command lines, and explicit `review_required_ignored_paths`. This is still an audit: it never deletes or stops processes. Read [project-cleanup-classification.md](references\u002Fproject-cleanup-classification.md).\n\nRun `scripts\u002FGet-ComputerStorageInventory.ps1` for system and user storage candidates. Use `scripts\u002FMeasure-PathUsage.ps1` for exact follow-up measurements. Record inaccessible trees instead of silently treating them as zero.\n\nDefault root discovery is heuristic, not proof of complete-computer coverage. For a whole-computer claim, explicitly enumerate all fixed volumes, known workspace roots, and every path returned by `git worktree list --porcelain`; list excluded and inaccessible roots in the report.\n\n### 2. Inventory every project semantically\n\nFor each discovered Git repository, worktree, or manifest-backed project, record:\n\n- canonical root, remote\u002Fdefault branch, branch\u002FHEAD, dirty and untracked state;\n- registered worktrees and whether each HEAD is contained in the verified remote default branch;\n- active process command lines that point inside the root;\n- project instructions and current-state\u002Fevidence documents;\n- manifests and lockfiles that prove a cache can be rebuilt;\n- generated candidates such as `node_modules`, `.venv`, `target`, `.next`, test caches, browser output, CodeGraph databases, and build directories;\n- ambiguous data such as `output`, `dist`, `release`, datasets, models, reports, validation runs, and agent context.\n\nDo not infer that `dist`, `build`, `output`, `.runtime`, `.codex`, `.claude`, or `.codegraph` is disposable. Classify their contents and role first. Read [whole-computer-project-audit.md](references\u002Fwhole-computer-project-audit.md).\n\n### 3. Inventory cross-project and application storage\n\nInspect, when present:\n\n- npm, pnpm, yarn, Bun, pip, uv, Cargo, NuGet, Gradle, Maven, browser, model, and updater caches;\n- Codex\u002FClaude\u002Fother agent sessions, runtimes, plugins, managed caches, and worktrees;\n- Docker logical objects separately from VHDX physical allocation;\n- WSL distributions and VHDX files;\n- Temp, Recycle Bin, WER\u002Fdumps, update delivery, driver installers, application backups, and databases;\n- pagefile, hiberfil, component store, DriverStore, Installer cache, Reserved Storage, VSS, and restore points as system-managed or official-tool-only categories.\n\nUse package managers' own inventory\u002Fprune operations. A cache's total size is an upper bound, not guaranteed reclaimable space. Read [storage-classification.md](references\u002Fstorage-classification.md) and [docker-storage.md](references\u002Fdocker-storage.md).\n\n### 4. Classify decisions, not just directories\n\nUse stable machine classes; colors may mirror them in the human report but never grant permission:\n\n- `SAFE_REBUILDABLE`: exact generated object with a proven regeneration path, inactive owner, contained target, and no evidence\u002Fuser data.\n- `REVIEW_REQUIRED`: useful history, project dependencies, clean but unverified clones, backups, sessions, installers, downloads, models, inactive Docker objects, or anything with judgement cost.\n- `KEEP_USER_OR_EVIDENCE`: source, dirty work, current\u002Farchived evidence, databases, restore volumes, current sessions, and unknown ownership.\n- `SYSTEM_MANAGED_DO_NOT_DELETE`: protected Windows files, component\u002Finstaller\u002Fdriver\u002Frecovery stores, or storage whose official analysis is unavailable.\n- `ADMIN_EVIDENCE_REQUIRED`: DISM, VSS, restore-point, Reserved Storage, VHDX compaction, or other facts not visible without elevation.\n\nThe detailed deletion gates are also summarized in [cleanup-classification.md](references\u002Fcleanup-classification.md).\n\nEvery candidate needs a confidence level, current bytes, owner, activity check, deletion impact, recovery\u002Fregeneration, exact action, expected verification, and approval state.\n\n### 5. Produce both JSON and a local report\n\nKeep scan data separate from analysis. Generate a local static report with `scripts\u002FNew-StorageAuditReport.ps1` after classifications are present. Use this reading order:\n\n1. volume overview and coverage gaps;\n2. top space consumers;\n3. recommended priority;\n4. candidates by class;\n5. retained risks and long-term prevention.\n\nThe report may contain private project names and absolute paths. Keep it local by default and redact before sharing. It must not expose direct hard-delete controls. The report information architecture has documented design provenance; see [design-provenance.md](references\u002Fdesign-provenance.md).\n\n## Manifest and controlled execution\n\nCreate `cleanup-manifest.json` before any state change:\n\n```json\n{\n  \"id\": \"project-cache-001\",\n  \"class\": \"SAFE_REBUILDABLE\",\n  \"action\": \"pnpm-store-prune\",\n  \"target\": \"C:\\\\absolute\\\\path-or-object-id\",\n  \"expected_command_path\": \"C:\\\\absolute\\\\path\\\\to\\\\pnpm.cmd\",\n  \"bytes\": 123,\n  \"owner\": \"tool-or-project\",\n  \"preconditions\": [\"path-contained\", \"size-rechecked\", \"owner-inactive\"],\n  \"recovery\": \"documented regeneration command\",\n  \"approved\": false\n}\n```\n\nBefore applying an approved item:\n\n1. Resolve and contain the exact target; reject reparse escapes.\n2. Recheck size, owner, Git state, process state, and other drift fields.\n3. Confirm the action type is compatible with the class.\n4. Capture the pre-action free bytes and relevant backup\u002Fstatus evidence.\n5. Execute only this ID. Stop on drift or unexpected output; never widen scope.\n6. Record exit status, released bytes, recovery status, and post-action verification.\n\nFor the built-in semantic allowlist, run `scripts\u002FInvoke-ApprovedCleanupManifest.ps1` first without `-Apply` and pass the exact `-ApprovedId` values. Record its `PreflightToken`. Apply only after the entire batch passes, using the same manifest and IDs plus `-Apply -PreflightToken \u003Ctoken>`; the executor reruns all preflights and rejects a stale token before the first mutation. Package actions must bind `target` to the cache path reported by the owning tool and bind `expected_command_path` to the reviewed `.exe` or `.cmd`. The executor intentionally rejects arbitrary commands, raw recursive deletion, string booleans, unapproved items, non-`SAFE_REBUILDABLE` classes, active or ambiguous owners, reparse paths, and unverified worktrees. Unsupported actions remain manual review items; never broaden the script's allowlist during a cleanup run merely to make an item pass.\n\nFor multiple IDs, complete preflight for the entire batch before the first mutation, then execute in smallest-risk order. A failed later item does not make earlier actions transactional; the action log must say exactly what happened.\n\n## Special storage rules\n\n### Docker and WSL\n\nRun `scripts\u002FGet-DockerStorageAudit.ps1`. Keep logical objects separate from VHDX physical storage. Do not start an auto-restarting container fleet only to obtain inventory without considering impact. VHDX compaction requires a current logical inventory, all consumers stopped, `wsl --shutdown`, detached\u002Fno-handle proof, and administrator access. Never promise the arithmetic sparse difference. Read [docker-storage.md](references\u002Fdocker-storage.md).\n\n### Git worktrees and temporary clones\n\nA worktree becomes eligible only when it is registered, clean including untracked files, inactive, and its HEAD is contained in the verified remote default branch. Remove it with `git worktree remove`, then prune metadata. A standalone temporary clone also needs clean status and remote containment; prefer recoverable removal when value is uncertain.\n\n### CodeGraph\n\nTreat `.codegraph` as rebuildable only after verifying it is an index, not project evidence, and that the project has no active indexing transaction. Separate the main database from WAL\u002FSHM. Prefer fixing `codegraph.json` exclusions and rebuilding rather than repeatedly deleting a growing WAL. Exclusions change semantic search coverage, not project build inputs, unless project code explicitly reads that configuration.\n\n### Sessions, backups, databases, and models\n\nRetain by default. Consider transparent compression or retention review before deletion. Database maintenance requires owner shutdown, a verified recovery copy, integrity checks, transactional changes, and post-checks. Keep at least one current backup and one pre-maintenance recovery point unless the user approves a different retention policy.\n\n## Memory workflow\n\nRun `scripts\u002FCollect-WindowsHealthSnapshot.ps1` at clean login, during representative workload, after it ends, and at long-run milestones. Separate processes, paged\u002Fnonpaged kernel pool, pool tags, cache\u002Fstandby, and pagefile. Never join trends across different boot times.\n\nUse `scripts\u002FGet-LongRunMemoryAssessment.ps1` and these outcome labels:\n\n- `VERIFIED_FIXED`: representative workload plus valid 48-hour same-boot coverage, no warning\u002Fcritical sample, no sustained pool growth, and functional gates pass.\n- `HEALTHY_SO_FAR_PENDING_LONG_RUN`: healthy evidence but less than 48 hours or incomplete representative workload.\n- `ROOT_CAUSE_NOT_PROVEN`: abnormal growth exists but no reproducible component\u002Fdriver A\u002FB proves ownership.\n- `WARNING_REVIEW_REQUIRED`: thresholds or sustained growth are exceeded.\n- `ROLLBACK_REQUIRED`: a change caused functional or event-log regression.\n\nFast Startup affects shutdown plus power-on, not Restart. It can preserve a leaking kernel session but does not create the leak. Restore it only after 24\u002F48-hour stability evidence and an explicit experience tradeoff. Do not disable Defender, storage, network, audio, graphics, or other drivers from one sample or a tag-name association. Read [memory-diagnosis.md](references\u002Fmemory-diagnosis.md) and [quality-gates.md](references\u002Fquality-gates.md).\n\n## Verification and outcome\n\nMeasure actual volume free-byte change; do not sum candidate logical sizes as released bytes. Re-run affected project status, worktree lists, package\u002Fcache status, Docker\u002FWSL inventory, database checks, and application smoke tests. For system changes, verify networking\u002FVPN, audio\u002Fmicrophone, OneDrive, input\u002FFn controls, search, and touched vendor software.\n\nLead with the outcome and use these sections:\n\n- Verified facts\n- Cleanup actions taken\n- Actual released bytes\n- Retained and protected items\n- Unverified\u002Fadmin-blocked items\n- Rollback or regeneration\n- Next maintenance milestone\n\nNever call an audit a cleanup, a candidate size released space, or healthy current memory a proven root-cause fix.\n",{"name":5,"metadata":52,"description":7},{"compatibility":53},"Windows 10 or Windows 11 x64 with PowerShell 5.1 or newer. Optional Git, Docker, WSL, package-manager, and CodeGraph checks run only when those tools or artifacts exist.","mine","1e7390741dffd3d5041fca4ebc056071ee3ba137","archives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner",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":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add EthanYoQ\u002FSkill-hub --skill yq-windows-trash-cleaner",{"tool":69,"command":70},"bunx","bunx skills add EthanYoQ\u002FSkill-hub --skill yq-windows-trash-cleaner",{"tool":72,"command":73},"pnpm","pnpm dlx skills add EthanYoQ\u002FSkill-hub --skill yq-windows-trash-cleaner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002FSKILL.md",true,[77,83,87,91,95,101,105,109,114,118,122,126,130,134,138,142,146,150,154,158,164,168,172,176,180,184,188,192],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"agents\u002Fopenai.yaml","REFERENCE","参考文档",320,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fagents\u002Fopenai.yaml",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"evals\u002Fevals.json",8056,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Fevals.json",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"evals\u002Ffiles\u002Fapproved-cleanup-fixture.json",801,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fapproved-cleanup-fixture.json",{"path":92,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":93,"sourceHtmlUrl":94},"evals\u002Ffiles\u002Fdisk-inventory.json",936,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fdisk-inventory.json",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"evals\u002Ffiles\u002Fmemory-longrun-samples.csv","ASSET","资产文件",697,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fmemory-longrun-samples.csv",{"path":102,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":103,"sourceHtmlUrl":104},"evals\u002Ffiles\u002Fproject-dirty-repo\u002Fprocesses.json",238,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fproject-dirty-repo\u002Fprocesses.json",{"path":106,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":107,"sourceHtmlUrl":108},"evals\u002Ffiles\u002Fproject-dirty-repo\u002Fstatus.txt",37,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fproject-dirty-repo\u002Fstatus.txt",{"path":110,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":107,"sourceHtmlUrl":113},"evals\u002Ffiles\u002Fproject-ignored-paths\u002F.gitignore","OTHER","其他","https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fproject-ignored-paths\u002F.gitignore",{"path":115,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":116,"sourceHtmlUrl":117},"evals\u002Ffiles\u002Fproject-ignored-paths\u002F.runtime\u002Fstate.db",70,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fproject-ignored-paths\u002F.runtime\u002Fstate.db",{"path":119,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":120,"sourceHtmlUrl":121},"evals\u002Ffiles\u002Fproject-ignored-paths\u002Ftest_dataset\u002Fuser.csv",29,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fproject-ignored-paths\u002Ftest_dataset\u002Fuser.csv",{"path":123,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":124,"sourceHtmlUrl":125},"evals\u002Ffiles\u002Fwhole-computer-project-inventory.json",2111,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fevals\u002Ffiles\u002Fwhole-computer-project-inventory.json",{"path":127,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Fcleanup-classification.md",1504,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fcleanup-classification.md",{"path":131,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":132,"sourceHtmlUrl":133},"references\u002Fdesign-provenance.md",1092,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fdesign-provenance.md",{"path":135,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":136,"sourceHtmlUrl":137},"references\u002Fdocker-storage.md",1433,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fdocker-storage.md",{"path":139,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":140,"sourceHtmlUrl":141},"references\u002Fmemory-diagnosis.md",2229,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fmemory-diagnosis.md",{"path":143,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":144,"sourceHtmlUrl":145},"references\u002Fproject-cleanup-classification.md",2730,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fproject-cleanup-classification.md",{"path":147,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":148,"sourceHtmlUrl":149},"references\u002Fquality-gates.md",1577,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fquality-gates.md",{"path":151,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":152,"sourceHtmlUrl":153},"references\u002Fstorage-classification.md",1943,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fstorage-classification.md",{"path":155,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":156,"sourceHtmlUrl":157},"references\u002Fwhole-computer-project-audit.md",2416,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Freferences\u002Fwhole-computer-project-audit.md",{"path":159,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":162,"sourceHtmlUrl":163},"scripts\u002FCollect-WindowsHealthSnapshot.ps1","SCRIPT","脚本",7025,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FCollect-WindowsHealthSnapshot.ps1",{"path":165,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":166,"sourceHtmlUrl":167},"scripts\u002FGet-ComputerProjectInventory.ps1",11632,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FGet-ComputerProjectInventory.ps1",{"path":169,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":170,"sourceHtmlUrl":171},"scripts\u002FGet-ComputerStorageInventory.ps1",11501,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FGet-ComputerStorageInventory.ps1",{"path":173,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":174,"sourceHtmlUrl":175},"scripts\u002FGet-DockerStorageAudit.ps1",2537,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FGet-DockerStorageAudit.ps1",{"path":177,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":178,"sourceHtmlUrl":179},"scripts\u002FGet-LongRunMemoryAssessment.ps1",5271,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FGet-LongRunMemoryAssessment.ps1",{"path":181,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":182,"sourceHtmlUrl":183},"scripts\u002FGet-ProjectCleanupAudit.ps1",12842,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FGet-ProjectCleanupAudit.ps1",{"path":185,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":186,"sourceHtmlUrl":187},"scripts\u002FInvoke-ApprovedCleanupManifest.ps1",14113,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FInvoke-ApprovedCleanupManifest.ps1",{"path":189,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":190,"sourceHtmlUrl":191},"scripts\u002FMeasure-PathUsage.ps1",2100,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FMeasure-PathUsage.ps1",{"path":193,"resourceType":160,"resourceTypeDesc":161,"sizeBytes":194,"sourceHtmlUrl":195},"scripts\u002FNew-StorageAuditReport.ps1",9224,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Farchives\u002Fuser-installed-skills\u002Fyq-windows-trash-cleaner\u002F84e4d76aed387ae0\u002Fyq-windows-trash-cleaner\u002Fscripts\u002FNew-StorageAuditReport.ps1",[197,223,254,278,296,311],{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":47},"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",[203],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[205,206,207,208,209,210,44,211,212,213,214,41,215,216,217,218,219,220,221,222],"social","xhs pharma social listening","social listening","xhs","medical","counting","collection","batch","analyze","notes","opencli","fallback","captcha","agent reach","evidence","for","collect","produce",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":235,"publishedAt":47},"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",[229,230],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":231,"categoryName":232,"taxonomyType":233,"taxonomyTypeDesc":234},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[236,237,238,239,240,241,242,243,44,244,245,246,247,248,249,250,220,251,252,253],"healthcare","phi","compliance","healthcare phi compliance","pii","compliance patterns","information","access","encryption","code","common","audit","data","patterns","Access Control","system","applications","Auditing Access Control",{"skillNo":255,"name":256,"nameZh":6,"description":257,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":258,"categories":259,"keywords":261,"publishedAt":47},"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",[260],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[236,262,263,264,265,266,267,44,268,269,270,271,237,220,272,273,274,275,276,277],"eval","harness","healthcare eval harness","eval harness","clinical","patient","workflow","Evaluation","Safety","integrity","deployment","accuracy","tests","deployments","use","super",{"skillNo":279,"name":280,"nameZh":6,"description":281,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":282,"categories":283,"keywords":285,"publishedAt":47},"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",[284],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[236,286,249,287,288,209,266,289,44,290,291,292,270,248,293,294,295,220,252,276],"EMR","healthcare emr patterns","decision","workflows","support","clinical decision support","features","ui","as","development",{"skillNo":297,"name":298,"nameZh":6,"description":299,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":300,"categories":301,"keywords":303,"publishedAt":47},"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",[302],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[236,249,304,288,266,286,289,44,305,306,290,291,307,295,251,308,276,309,277,310],"healthcare cdss patterns","scoring","interaction","severity","classification","alert","decision support",{"skillNo":312,"name":313,"nameZh":6,"description":314,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":315,"categories":316,"keywords":318,"publishedAt":47},"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",[317],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[319,320,321,322,323,324,325,326],"clarify","dxy task clarify","task","pptx","整理","翻译","数据","总结"]