[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AF6Y34097EHME2EN9QDNSG":3,"skill-same:01M6AF6Y34097EHME2EN9QDNSG":105},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M6AF6Y34097EHME2EN9QDNSG","mac-storage-cleaner",null,"Safely reclaim disk space on a Mac — the trustworthy, transparent, reversible alternative to CleanMyMac and similar tools. Use whenever the user says their Mac disk or storage is full or nearly full, gets a \"startup disk almost full\" \u002F low-storage warning, asks to free up space, clean\u002Fclear caches, remove junk, delete leftover files from apps they uninstalled, or find what's eating their disk — in any language (e.g. English \"my mac is out of space\", \"free up disk\", \"clear caches\", \"what's taking up my storage\"; Georgian \"ქეში გაასუფთავე\", \"მეხსიერება გადამევსო\", \"ადგილი აღარ მაქვს\"). Surveys usage first, auto-clears only pure caches, moves anything riskier to the Trash (restorable), asks before anything expensive, logs every deletion, and reports what was freed. Do NOT use for cloud storage, RAM\u002Fmemory-pressure, or a single named app's own in-app cache button.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"storage","mac storage cleaner","mac","my","memory","Cloud Storage","apps","english","free","app","clean","files","reports","up","only","auto","remove","disk","first","Tools","startup","cloud","logs","cache","delete","2026-11-10 10:12:30",false,"---\nname: mac-storage-cleaner\ndescription: Safely reclaim disk space on a Mac — the trustworthy, transparent, reversible alternative to CleanMyMac and similar tools. Use whenever the user says their Mac disk or storage is full or nearly full, gets a \"startup disk almost full\" \u002F low-storage warning, asks to free up space, clean\u002Fclear caches, remove junk, delete leftover files from apps they uninstalled, or find what's eating their disk — in any language (e.g. English \"my mac is out of space\", \"free up disk\", \"clear caches\", \"what's taking up my storage\"; Georgian \"ქეში გაასუფთავე\", \"მეხსიერება გადამევსო\", \"ადგილი აღარ მაქვს\"). Surveys usage first, auto-clears only pure caches, moves anything riskier to the Trash (restorable), asks before anything expensive, logs every deletion, and reports what was freed. Do NOT use for cloud storage, RAM\u002Fmemory-pressure, or a single named app's own in-app cache button.\n---\n\n# Mac Storage Cleaner\n\nFree disk space the way a careful engineer would, and earn the trust one-click\ncleaners lose: **measure first, delete only what provably regenerates, make\nanything riskier reversible, ask before anything expensive, log every action,\nand report honestly.** The differentiator over CleanMyMac-style tools is\njudgment and transparency — the user sees what will go and why, and can undo it.\n\nScripts live in `scripts\u002F`; the full tiered inventory, exact reclaim commands,\nand gotchas are in `references\u002Fcache-catalog.md`. Read the catalog whenever you\nhit something a script didn't classify or you need the precise command.\n\n## Core principles\n\n- **Safe tier → delete outright** (space back immediately). These are pure\n  caches; the only cost is a slower next build\u002Finstall.\n- **Everything else → Trash, not `rm`.** Ask-tier items, app leftovers, big\n  files — move them to the Trash with `trash-items.sh` so the user can restore\n  them. Reversibility is the whole point; never hard-delete a user's data.\n- **When unsure, demote a tier.** A slower rebuild is trivial; deleting a\n  license, an unpushable Xcode archive, or someone's only local backup is not.\n- **Every destructive run is logged** to `~\u002FLibrary\u002FLogs\u002Fmac-storage-cleaner\u002Foperations.log`.\n\n## Workflow\n\n**Locating the scripts.** The commands below resolve `$D` to this skill's own\ndirectory so they work whether the skill was installed as a plugin\n(`$CLAUDE_PLUGIN_ROOT` is set) or as a standalone skill (`~\u002F.claude\u002Fskills\u002F…`).\nShell state doesn't persist between commands, so each block re-resolves `$D`.\n\n### 1. Survey — caches (always first, read-only)\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Fsurvey.sh\"\n```\n\nPrints free space and sizes every cache that exists on *this* machine, grouped\n**safe \u002F ask \u002F never \u002F app-data**. Never skip it — locations and sizes differ on\nevery Mac. Note current free space for the before\u002Fafter report.\n\n### 2. Clear the safe tier (no per-item permission needed)\n\nTell the user briefly what the safe tier removes and roughly how much it frees,\nthen:\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Fclean-safe.sh\"\n```\n\nRemoves only the vetted safe allowlist (nothing else — the survey's \"other large\ncaches\" list is for the user to review, not for auto-deletion), handles read-only\nfiles, skips anything macOS protects (reporting rather than failing), runs\n`brew cleanup -s --prune=all` and removes unavailable simulators, logs each\ndeletion, and prints what it reclaimed. If the user only wanted specific items,\ndelete those directly instead.\n\n**Browser & Electron app caches** (Chrome\u002FArc\u002FSlack\u002FVS Code\u002F…) are safe but live\ninside app-data folders — clear only the `Cache`\u002F`Code Cache`\u002F`GPUCache`\nsubfolders the survey lists, ideally with the app quit, and **never** the whole\napp folder. Exact paths: `references\u002Fcache-catalog.md`.\n\n### 3. Surface the \"ask\" tier — recommend, don't delete\n\nBig but not free caches (Docker images, ML models, simulator devices, Xcode\nArchives, module stores). List each with size + a specific recommendation; let\nthe user choose. Use the tool-native command, and prefer Trash for file\ndeletions. Key ones (full detail in the catalog):\n\n- **Docker** — `docker system prune -a`, never `rm` the VM disk.\n- **ML models** (HuggingFace\u002FOllama) — often duplicated variants; offer to remove unused ones.\n- **Simulators** — only `xcrun simctl delete unavailable` is safe; deleting active devices wipes state.\n- **Xcode Archives** — warn: holds dSYMs for crash symbolication and shippable builds.\n\n### 4. Go beyond caches — the space the cleaners miss (read-only scan)\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Ffind-extras.sh\"\n```\n\nSurfaces the real hogs a cache sweep ignores: **leftover data from uninstalled\napps**, **big files (>500MB)**, **stale installers** (.dmg\u002F.pkg), and **old\nDownloads**. Everything here is ask-tier — present candidates, let the user pick,\nthen remove reversibly:\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Ftrash-items.sh\" \"\u002Fpath\u002Fone\" \"\u002Fpath\u002Ftwo\"\n```\n\n**If trashing reports \"could NOT trash (permissions\u002FTCC?)\"** for every item, the\ncontrolling app hasn't been granted Automation control of Finder — a normal\nfirst-run state. Tell the user to allow it in System Settings › Privacy &\nSecurity › Automation (enable Finder for the terminal\u002Fapp), then re-run; or move\nthe item to the Trash manually in Finder. Don't report space as freed when items\nlogged `trash-failed` — nothing was actually removed.\n\n**App leftovers need verification.** The scan lists containers whose owning app a\nquick check couldn't confirm is installed — but Spotlight misses un-indexed apps,\nso some candidates *are* still installed. Before proposing to remove any leftover,\n**confirm the app is really gone** (check `\u002FApplications`, `mdfind`, or just ask\nthe user \"do you still use X?\"), and always Trash it, never `rm`. To also clear a\nconfirmed-uninstalled app's *other* leftovers (Preferences, Application Support,\nLogs, Saved State, etc.), see the leftover-location list in the catalog.\n\n### 5. Report\n\nIn the user's language: before → after free space\n(`df -h \u002FSystem\u002FVolumes\u002FData`), a short list of what was cleared\u002Ftrashed with\nsizes, a one-line note that the first build\u002Finstall afterward will be slower, the\nstill-large \"ask\" items each with a recommendation, and the log path.\n\nIf free space rose less than the reclaimed size suggests, explain **APFS\npurgeable space**: macOS may hold freed space as purgeable (often behind Time\nMachine local snapshots) and release it on demand — the space is genuinely\nrecovered. Don't chase it with `sudo`.\n\n## Safety rules\n\nRead `references\u002Fcache-catalog.md` for the full tiered inventory and gotchas. The essentials:\n\n- **Never delete** user data that looks like storage: iOS backups\n  (`~\u002FLibrary\u002FApplication Support\u002FMobileSync\u002FBackup`), Photos library, Mail\u002FMessages\n  data, whole app-support folders, `~\u002F.ssh`\u002F`~\u002F.aws`\u002Fkeychains, Time Machine\n  snapshots. Report their size so the user knows, but don't touch them.\n- **Messaging-app media is user data, not cache.** Telegram\u002FWhatsApp\u002FSlack store\n  downloaded photos\u002Fvideos in their caches. Don't bulk-delete these; point the\n  user to the app's own \"Clear Cache\" (e.g. Telegram › Settings › Data and\n  Storage › Storage Usage) so they choose what to drop.\n- **Never `sudo`** into `\u002FSystem`, `\u002FLibrary\u002FCaches`, `\u002Fprivate\u002Fvar\u002Ffolders`, or\n  SIP-protected areas — that's macOS's job.\n- **Watch mixed directories**: `~\u002F.cargo` (has installed binaries — only clear\n  `registry\u002F`), `~\u002F.m2` (has `settings.xml` — only clear `repository\u002F`), `~\u002F.gradle`\n  (only `caches\u002F`). `~\u002F.npm` is pure cache so it's fine whole.\n- **Continue past errors and verify** with `du`; `rm -rf` on multiple paths keeps\n  going after a failure, so never assume total success or total failure.\n","# Mac Storage Cleaner\n\nFree disk space the way a careful engineer would, and earn the trust one-click\ncleaners lose: **measure first, delete only what provably regenerates, make\nanything riskier reversible, ask before anything expensive, log every action,\nand report honestly.** The differentiator over CleanMyMac-style tools is\njudgment and transparency — the user sees what will go and why, and can undo it.\n\nScripts live in `scripts\u002F`; the full tiered inventory, exact reclaim commands,\nand gotchas are in `references\u002Fcache-catalog.md`. Read the catalog whenever you\nhit something a script didn't classify or you need the precise command.\n\n## Core principles\n\n- **Safe tier → delete outright** (space back immediately). These are pure\n  caches; the only cost is a slower next build\u002Finstall.\n- **Everything else → Trash, not `rm`.** Ask-tier items, app leftovers, big\n  files — move them to the Trash with `trash-items.sh` so the user can restore\n  them. Reversibility is the whole point; never hard-delete a user's data.\n- **When unsure, demote a tier.** A slower rebuild is trivial; deleting a\n  license, an unpushable Xcode archive, or someone's only local backup is not.\n- **Every destructive run is logged** to `~\u002FLibrary\u002FLogs\u002Fmac-storage-cleaner\u002Foperations.log`.\n\n## Workflow\n\n**Locating the scripts.** The commands below resolve `$D` to this skill's own\ndirectory so they work whether the skill was installed as a plugin\n(`$CLAUDE_PLUGIN_ROOT` is set) or as a standalone skill (`~\u002F.claude\u002Fskills\u002F…`).\nShell state doesn't persist between commands, so each block re-resolves `$D`.\n\n### 1. Survey — caches (always first, read-only)\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Fsurvey.sh\"\n```\n\nPrints free space and sizes every cache that exists on *this* machine, grouped\n**safe \u002F ask \u002F never \u002F app-data**. Never skip it — locations and sizes differ on\nevery Mac. Note current free space for the before\u002Fafter report.\n\n### 2. Clear the safe tier (no per-item permission needed)\n\nTell the user briefly what the safe tier removes and roughly how much it frees,\nthen:\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Fclean-safe.sh\"\n```\n\nRemoves only the vetted safe allowlist (nothing else — the survey's \"other large\ncaches\" list is for the user to review, not for auto-deletion), handles read-only\nfiles, skips anything macOS protects (reporting rather than failing), runs\n`brew cleanup -s --prune=all` and removes unavailable simulators, logs each\ndeletion, and prints what it reclaimed. If the user only wanted specific items,\ndelete those directly instead.\n\n**Browser & Electron app caches** (Chrome\u002FArc\u002FSlack\u002FVS Code\u002F…) are safe but live\ninside app-data folders — clear only the `Cache`\u002F`Code Cache`\u002F`GPUCache`\nsubfolders the survey lists, ideally with the app quit, and **never** the whole\napp folder. Exact paths: `references\u002Fcache-catalog.md`.\n\n### 3. Surface the \"ask\" tier — recommend, don't delete\n\nBig but not free caches (Docker images, ML models, simulator devices, Xcode\nArchives, module stores). List each with size + a specific recommendation; let\nthe user choose. Use the tool-native command, and prefer Trash for file\ndeletions. Key ones (full detail in the catalog):\n\n- **Docker** — `docker system prune -a`, never `rm` the VM disk.\n- **ML models** (HuggingFace\u002FOllama) — often duplicated variants; offer to remove unused ones.\n- **Simulators** — only `xcrun simctl delete unavailable` is safe; deleting active devices wipes state.\n- **Xcode Archives** — warn: holds dSYMs for crash symbolication and shippable builds.\n\n### 4. Go beyond caches — the space the cleaners miss (read-only scan)\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Ffind-extras.sh\"\n```\n\nSurfaces the real hogs a cache sweep ignores: **leftover data from uninstalled\napps**, **big files (>500MB)**, **stale installers** (.dmg\u002F.pkg), and **old\nDownloads**. Everything here is ask-tier — present candidates, let the user pick,\nthen remove reversibly:\n\n```bash\nD=\"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT\u002Fskills\u002Fmac-storage-cleaner}\"; D=\"${D:-$HOME\u002F.claude\u002Fskills\u002Fmac-storage-cleaner}\"\nbash \"$D\u002Fscripts\u002Ftrash-items.sh\" \"\u002Fpath\u002Fone\" \"\u002Fpath\u002Ftwo\"\n```\n\n**If trashing reports \"could NOT trash (permissions\u002FTCC?)\"** for every item, the\ncontrolling app hasn't been granted Automation control of Finder — a normal\nfirst-run state. Tell the user to allow it in System Settings › Privacy &\nSecurity › Automation (enable Finder for the terminal\u002Fapp), then re-run; or move\nthe item to the Trash manually in Finder. Don't report space as freed when items\nlogged `trash-failed` — nothing was actually removed.\n\n**App leftovers need verification.** The scan lists containers whose owning app a\nquick check couldn't confirm is installed — but Spotlight misses un-indexed apps,\nso some candidates *are* still installed. Before proposing to remove any leftover,\n**confirm the app is really gone** (check `\u002FApplications`, `mdfind`, or just ask\nthe user \"do you still use X?\"), and always Trash it, never `rm`. To also clear a\nconfirmed-uninstalled app's *other* leftovers (Preferences, Application Support,\nLogs, Saved State, etc.), see the leftover-location list in the catalog.\n\n### 5. Report\n\nIn the user's language: before → after free space\n(`df -h \u002FSystem\u002FVolumes\u002FData`), a short list of what was cleared\u002Ftrashed with\nsizes, a one-line note that the first build\u002Finstall afterward will be slower, the\nstill-large \"ask\" items each with a recommendation, and the log path.\n\nIf free space rose less than the reclaimed size suggests, explain **APFS\npurgeable space**: macOS may hold freed space as purgeable (often behind Time\nMachine local snapshots) and release it on demand — the space is genuinely\nrecovered. Don't chase it with `sudo`.\n\n## Safety rules\n\nRead `references\u002Fcache-catalog.md` for the full tiered inventory and gotchas. The essentials:\n\n- **Never delete** user data that looks like storage: iOS backups\n  (`~\u002FLibrary\u002FApplication Support\u002FMobileSync\u002FBackup`), Photos library, Mail\u002FMessages\n  data, whole app-support folders, `~\u002F.ssh`\u002F`~\u002F.aws`\u002Fkeychains, Time Machine\n  snapshots. Report their size so the user knows, but don't touch them.\n- **Messaging-app media is user data, not cache.** Telegram\u002FWhatsApp\u002FSlack store\n  downloaded photos\u002Fvideos in their caches. Don't bulk-delete these; point the\n  user to the app's own \"Clear Cache\" (e.g. Telegram › Settings › Data and\n  Storage › Storage Usage) so they choose what to drop.\n- **Never `sudo`** into `\u002FSystem`, `\u002FLibrary\u002FCaches`, `\u002Fprivate\u002Fvar\u002Ffolders`, or\n  SIP-protected areas — that's macOS's job.\n- **Watch mixed directories**: `~\u002F.cargo` (has installed binaries — only clear\n  `registry\u002F`), `~\u002F.m2` (has `settings.xml` — only clear `repository\u002F`), `~\u002F.gradle`\n  (only `caches\u002F`). `~\u002F.npm` is pure cache so it's fine whole.\n- **Continue past errors and verify** with `du`; `rm -rf` on multiple paths keeps\n  going after a failure, so never assume total success or total failure.\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add davila7\u002Fclaude-code-templates --skill mac-storage-cleaner",{"tool":65,"command":66},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill mac-storage-cleaner",{"tool":68,"command":69},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill mac-storage-cleaner","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002FSKILL.md",true,[73,79,83,89,93,97,101],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"agents\u002Fopenai.yaml","REFERENCE","参考文档",135,"https:\u002F\u002Fgithub.com\u002Ffderuiter\u002FQRCraftly-web\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fto-spec\u002Fagents\u002Fopenai.yaml",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fcache-catalog.md",11618,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002Freferences\u002Fcache-catalog.md",{"path":84,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fclean-safe.sh","SCRIPT","脚本",2919,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002Fscripts\u002Fclean-safe.sh",{"path":90,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Ffind-extras.sh",3703,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002Fscripts\u002Ffind-extras.sh",{"path":94,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Flib.sh",8086,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002Fscripts\u002Flib.sh",{"path":98,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Fsurvey.sh",3397,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002Fscripts\u002Fsurvey.sh",{"path":102,"resourceType":85,"resourceTypeDesc":86,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Ftrash-items.sh",1136,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fmac-storage-cleaner\u002Fscripts\u002Ftrash-items.sh",[106,138,165,197,231,254],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":117,"publishedAt":44},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":145,"publishedAt":44},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[144],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},[146,147,148,149,150,151,152,153,154,155,156,127,157,158,159,160,161,162,163,164],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":180,"publishedAt":44},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[171,174,175],{"categoryNo":172,"categoryName":173,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},{"categoryNo":176,"categoryName":177,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[181,182,183,184,185,186,187,123,188,189,190,191,192,33,193,126,194,195,127,196],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","MCP","access","database","query",{"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":201,"licenseFileUrl":202,"sourceHtmlUrl":203,"categories":204,"keywords":208,"publishedAt":44},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[205],{"categoryNo":206,"categoryName":207,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000009","前端开发",[209,210,211,212,213,214,215,216,217,218,219,220,38,221,222,223,224,225,226,227,228,229,123,230],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":201,"licenseFileUrl":235,"sourceHtmlUrl":236,"categories":237,"keywords":242,"publishedAt":44},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[238,241],{"categoryNo":239,"categoryName":240,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":206,"categoryName":207,"taxonomyType":115,"taxonomyTypeDesc":116},[243,244,245,246,247,210,248,219,220,249,250,41,251,123,252,129,253],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","screenshots","local","behavior",{"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":201,"licenseFileUrl":258,"sourceHtmlUrl":259,"categories":260,"keywords":268,"publishedAt":44},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[261,264,265],{"categoryNo":262,"categoryName":263,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},{"categoryNo":266,"categoryName":267,"taxonomyType":178,"taxonomyTypeDesc":179},"01JBSEEDCAT000000000000036","内容创作者",[269,270,271,272,273,274,275,276,212,277,221,157,278,279,280,281,32,33,282,127,283,284,285,286,287,135,288],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","invoke","you","analysis","claims","argument","assemble","recommendations"]