[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AQRHJEF1TZN2RQBG2M75FP":3,"skill-same:01M7AQRHJEF1TZN2RQBG2M75FP":53},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M7AQRHJEF1TZN2RQBG2M75FP","backup-setup",null,"Set up, check, or restore local claude-mem database snapshots. Use when the user says \"set up backups\", \"back up my memories\", \"backup status\", or \"restore my database\".","ormequ\u002Fclaude-mem","ormequ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F57725831?v=4","01M7AQPDVH41K0QRYM9CETY6R5","Ilya Belokobylsky","01M7AQPDWQAA42TFEPNSDTD3ZK",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fbackup-setup\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: backup-setup\ndescription: Set up, check, or restore local claude-mem database snapshots. Use when the user says \"set up backups\", \"back up my memories\", \"backup status\", or \"restore my database\".\nallowed-tools:\n  - Bash\n  - Read\n  - AskUserQuestion\nargument-hint: [setup|restore|status]\n---\n\n# Backups (local snapshots)\n\nThe installed worker snapshots `~\u002F.claude-mem\u002Fclaude-mem.db` on a schedule\n(`VACUUM INTO`, consistent while sessions run) and keeps the newest N under\n`~\u002F.claude-mem\u002Fbackups\u002Fauto\u002F`. Each snapshot is one standalone SQLite file.\nSnapshots stay on this machine.\n\nPreserve every unrelated setting and keep `~\u002F.claude-mem\u002Fsettings.json` mode\n`0600`. Never print the file's contents: it holds credentials.\n\n## Routing\n\nBased on `$ARGUMENTS`:\n- `setup` or empty: **1. Check status**, then **2. Enable snapshots**\n- `restore`: **3. Restore**\n- `status`: **1. Check status** only\n\n## 1. Check status\n\n```bash\nnpx claude-mem backup status\n```\n\n- Snapshot details printed: backups run. Report the last snapshot time, the\n  snapshot count and any last error; stop unless the user asked for a change\n  or a restore.\n- \"Automatic backups are not enabled\": continue to step 2 if setting up.\n- A \"Last restore\" line reports the outcome of the most recent restore.\n- \"Worker is not running\": start it with `npx claude-mem start` and retry.\n- \"Unknown command: backup\" or \"Backup status failed: HTTP 404\": this\n  claude-mem (CLI or running worker) has no backup support yet, so the\n  worker would ignore the backup settings.\n  Stop. Tell the user that backups are not available in their installed\n  version and that `npx claude-mem update` brings them once a release\n  includes them. Do not write the settings in step 2, and never say backups\n  are on.\n- Any other failure (\"Backup status failed: HTTP\" with another status,\n  \"Backup request failed: ...\", \"Backup status failed: invalid JSON\n  response\", \"Backup status failed: unexpected response\") or any output not\n  listed here: stop. Show the user the exact error line, do not write the\n  settings in step 2, and never say backups are on. Do not suggest an\n  update: this is an error in a version that has backups, not a missing\n  feature.\n\n## 2. Enable snapshots\n\nAsk (or default): interval in hours (default 24, range 1 to 168) and how\nmany snapshots to keep (default 7, range 1 to 100). Then write the settings\nwithout echoing anything else in the file:\n\n```bash\nnode - \u003C\u003C'EOF'\nconst fs = require('fs'), os = require('os'), path = require('path');\nconst intervalHours = 'PASTE_INTERVAL_HOURS_HERE'; \u002F\u002F e.g. '24'\nconst retainCount = 'PASTE_RETAIN_COUNT_HERE';     \u002F\u002F e.g. '7'\nconst dir = path.join(os.homedir(), '.claude-mem');\nconst file = path.join(dir, 'settings.json');\nfs.mkdirSync(dir, { recursive: true });\nconst settings = fs.existsSync(file) ? JSON.parse(fs.readFileSync(file, 'utf8')) : {};\nconst target = settings.env && typeof settings.env === 'object' ? settings.env : settings;\ntarget.CLAUDE_MEM_BACKUP_ENABLED = 'true';\ntarget.CLAUDE_MEM_BACKUP_INTERVAL_HOURS = intervalHours;\ntarget.CLAUDE_MEM_BACKUP_RETAIN_COUNT = retainCount;\nfs.writeFileSync(file, JSON.stringify(settings, null, 2) + '\\n', { mode: 0o600 });\nfs.chmodSync(file, 0o600);\nconsole.log('backups enabled: every ' + intervalHours + 'h, keeping ' + retainCount);\nEOF\n```\n\nRestart the worker so the schedule starts, then confirm with step 1. Tell\nthe user backups are on only when that status reports them enabled:\n\n```bash\nnpx claude-mem restart\nnpx claude-mem backup status\n```\n\nThe first automatic snapshot lands about five minutes after the worker\nstarts. To take one now:\n\n```bash\nnpx claude-mem backup run\n```\n\n## 3. Restore\n\n```bash\nnpx claude-mem backup list\nnpx claude-mem restore \u003Cfile>\nnpx claude-mem backup status\n```\n\n`restore` stages the snapshot and restarts the worker (it also starts a\nworker that is not running). The new worker swaps the database in before it\nopens it, saves the database it replaced in the same folder as\n`claude-mem-\u003Ctimestamp>-pre-restore.db` (restore that file to undo; it counts\ntoward the retain count), and records the outcome. With cloud sync on, the\nrestored database resumes syncing from the snapshot's position and can pull\nback changes that reached the cloud after it. `backup status` then prints a \"Last restore\" line: on success it\nnames the saved copy; on failure it gives the reason, and the worker kept\nthe database it had.\n\n## 4. Report\n\nReport the snapshot count, the last snapshot time, any error, and the last\nrestore outcome if there was one.\n","# Backups (local snapshots)\n\nThe installed worker snapshots `~\u002F.claude-mem\u002Fclaude-mem.db` on a schedule\n(`VACUUM INTO`, consistent while sessions run) and keeps the newest N under\n`~\u002F.claude-mem\u002Fbackups\u002Fauto\u002F`. Each snapshot is one standalone SQLite file.\nSnapshots stay on this machine.\n\nPreserve every unrelated setting and keep `~\u002F.claude-mem\u002Fsettings.json` mode\n`0600`. Never print the file's contents: it holds credentials.\n\n## Routing\n\nBased on `$ARGUMENTS`:\n- `setup` or empty: **1. Check status**, then **2. Enable snapshots**\n- `restore`: **3. Restore**\n- `status`: **1. Check status** only\n\n## 1. Check status\n\n```bash\nnpx claude-mem backup status\n```\n\n- Snapshot details printed: backups run. Report the last snapshot time, the\n  snapshot count and any last error; stop unless the user asked for a change\n  or a restore.\n- \"Automatic backups are not enabled\": continue to step 2 if setting up.\n- A \"Last restore\" line reports the outcome of the most recent restore.\n- \"Worker is not running\": start it with `npx claude-mem start` and retry.\n- \"Unknown command: backup\" or \"Backup status failed: HTTP 404\": this\n  claude-mem (CLI or running worker) has no backup support yet, so the\n  worker would ignore the backup settings.\n  Stop. Tell the user that backups are not available in their installed\n  version and that `npx claude-mem update` brings them once a release\n  includes them. Do not write the settings in step 2, and never say backups\n  are on.\n- Any other failure (\"Backup status failed: HTTP\" with another status,\n  \"Backup request failed: ...\", \"Backup status failed: invalid JSON\n  response\", \"Backup status failed: unexpected response\") or any output not\n  listed here: stop. Show the user the exact error line, do not write the\n  settings in step 2, and never say backups are on. Do not suggest an\n  update: this is an error in a version that has backups, not a missing\n  feature.\n\n## 2. Enable snapshots\n\nAsk (or default): interval in hours (default 24, range 1 to 168) and how\nmany snapshots to keep (default 7, range 1 to 100). Then write the settings\nwithout echoing anything else in the file:\n\n```bash\nnode - \u003C\u003C'EOF'\nconst fs = require('fs'), os = require('os'), path = require('path');\nconst intervalHours = 'PASTE_INTERVAL_HOURS_HERE'; \u002F\u002F e.g. '24'\nconst retainCount = 'PASTE_RETAIN_COUNT_HERE';     \u002F\u002F e.g. '7'\nconst dir = path.join(os.homedir(), '.claude-mem');\nconst file = path.join(dir, 'settings.json');\nfs.mkdirSync(dir, { recursive: true });\nconst settings = fs.existsSync(file) ? JSON.parse(fs.readFileSync(file, 'utf8')) : {};\nconst target = settings.env && typeof settings.env === 'object' ? settings.env : settings;\ntarget.CLAUDE_MEM_BACKUP_ENABLED = 'true';\ntarget.CLAUDE_MEM_BACKUP_INTERVAL_HOURS = intervalHours;\ntarget.CLAUDE_MEM_BACKUP_RETAIN_COUNT = retainCount;\nfs.writeFileSync(file, JSON.stringify(settings, null, 2) + '\\n', { mode: 0o600 });\nfs.chmodSync(file, 0o600);\nconsole.log('backups enabled: every ' + intervalHours + 'h, keeping ' + retainCount);\nEOF\n```\n\nRestart the worker so the schedule starts, then confirm with step 1. Tell\nthe user backups are on only when that status reports them enabled:\n\n```bash\nnpx claude-mem restart\nnpx claude-mem backup status\n```\n\nThe first automatic snapshot lands about five minutes after the worker\nstarts. To take one now:\n\n```bash\nnpx claude-mem backup run\n```\n\n## 3. Restore\n\n```bash\nnpx claude-mem backup list\nnpx claude-mem restore \u003Cfile>\nnpx claude-mem backup status\n```\n\n`restore` stages the snapshot and restarts the worker (it also starts a\nworker that is not running). The new worker swaps the database in before it\nopens it, saves the database it replaced in the same folder as\n`claude-mem-\u003Ctimestamp>-pre-restore.db` (restore that file to undo; it counts\ntoward the retain count), and records the outcome. With cloud sync on, the\nrestored database resumes syncing from the snapshot's position and can pull\nback changes that reached the cloud after it. `backup status` then prints a \"Last restore\" line: on success it\nnames the saved copy; on failure it gives the reason, and the worker kept\nthe database it had.\n\n## 4. Report\n\nReport the snapshot count, the last snapshot time, any error, and the last\nrestore outcome if there was one.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":28},[25,26,27],"Bash","Read","AskUserQuestion",[29],"setup|restore|status","main","0db123aaccc336d1ffa9d077b8c4e7f7675dfd46","plugin\u002Fskills\u002Fbackup-setup",1,"https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem","https:\u002F\u002Fclaude-mem.ai","https:\u002F\u002Fgithub.com\u002Formequ","Go backend engineer · Kubernetes, distributed systems · LLM agents","2026-11-05 13:51:42",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add ormequ\u002Fclaude-mem --skill backup-setup",{"tool":45,"command":46},"bunx","bunx skills add ormequ\u002Fclaude-mem --skill backup-setup",{"tool":48,"command":49},"pnpm","pnpm dlx skills add ormequ\u002Fclaude-mem --skill backup-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fbackup-setup\u002FSKILL.md",true,[],[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7AQWJQES5XXW6116RFKB6KD","wowerpoint","Turn one document into a kawaii NotebookLM slide deck. Use for \"wowerpoint this\", \"make a deck about \u003Cfile>\", \"turn this report into slides\", or any request to render a single document as shareable narrative slides.","https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fwowerpoint\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7AQWGAYXR5XZXX90T9N5FKQ","what-the","What the? Use when the user wants a plain-English breakdown of something technical — the who, what, where, why, and when.","https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fwhat-the\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7AQWA7FTADR4AWJDZR3HPXX","weekly-digests","Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for \"weekly digests\", \"week-by-week story\", \"serial timeline\", or \"narrative chapters\" of a project's history.","https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fweekly-digests\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AQW6QN3F1Q00QSP1T929TD","version-bump","Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. npm publishing is done by the tag-triggered GitHub Actions workflow through npm trusted publishing.","https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fversion-bump\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AQW38KM9WJHQYRNGK0P26R","timeline-report","Generate a \"Journey Into [Project]\" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.","https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Ftimeline-report\u002FSKILL.md",[],[],{"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":95,"publishedAt":19},"01M7AQW0D3WTYQ4DKC73X1J75G","standup","Facilitate a read-only standup across git worktrees, branches, or PRs to compare changes and produce one consolidation plan.","https:\u002F\u002Fgithub.com\u002Formequ\u002Fclaude-mem\u002Fblob\u002Fmain\u002Fplugin\u002Fskills\u002Fstandup\u002FSKILL.md",[],[]]