[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4J260BMY1H0FJ17ECTSPM":3,"skill-same:01M7F4J260BMY1H0FJ17ECTSPM":52},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7F4J260BMY1H0FJ17ECTSPM","session-cleanup",null,"Identify stale and empty Claude Code sessions in the Agent Monitor and explain the cleanup endpoint (POST \u002Fapi\u002Fsettings\u002Fcleanup), always showing the exact list of what WOULD be removed before anything is deleted. Cleanup permanently deletes data, so this skill previews first and requires explicit user confirmation. Use when tidying the monitoring database.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsession-cleanup\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: session-cleanup\ndescription: >\n  Identify stale and empty Claude Code sessions in the Agent Monitor and explain the\n  cleanup endpoint (POST \u002Fapi\u002Fsettings\u002Fcleanup), always showing the exact list of\n  what WOULD be removed before anything is deleted. Cleanup permanently deletes data,\n  so this skill previews first and requires explicit user confirmation. Use when\n  tidying the monitoring database.\n---\n\n# Session Cleanup\n\nFind prune-worthy sessions and explain cleanup — preview first, delete only on\nexplicit confirmation.\n\n## Input\n\nThe user provides: **$ARGUMENTS**\n\n- Empty \u002F `preview` → only show what would be removed (the safe default).\n- `confirm` → the user has reviewed the preview and explicitly authorizes deletion.\n- An optional staleness threshold (e.g. `older than 7d`) for what counts as stale.\n\n## Data Sources\n\n| Endpoint | Returns |\n|----------|---------|\n| `GET \u002Fapi\u002Fsessions?limit=N` | session list: id, status, model, cwd, started_at, ended_at, cost, metadata (turn_count, total_turn_duration_ms) |\n| `GET \u002Fapi\u002Fstats` | totals: total_sessions, active_sessions, total_events, events_today, sessions_by_status, agents_by_status |\n| `POST \u002Fapi\u002Fsettings\u002Fcleanup` | runs the cleanup routine and returns what was removed — DESTRUCTIVE, only after confirmation |\n\n## Report Sections\n\n### 1. Baseline\n`GET \u002Fapi\u002Fstats` — record total_sessions, sessions_by_status, total_events. This is\nthe before-state to compare against.\n\n### 2. Identify candidates\n`GET \u002Fapi\u002Fsessions?limit=1000`. Flag sessions that are:\n- **Empty** — zero events and `turn_count` 0 \u002F null and `cost` 0 (started but never\n  did anything).\n- **Stale active** — `status` active\u002Fworking but last activity older than the\n  threshold (default 24h), i.e. never cleanly stopped.\n- **Truncated** — no `ended_at` and no recent events.\n\n### 3. Preview table (ALWAYS shown)\nList every candidate with the reason it qualifies. State the total count and confirm\nthat **nothing has been deleted yet**.\n\n### 4. Explain the endpoint\nDescribe `POST \u002Fapi\u002Fsettings\u002Fcleanup`: it prunes empty \u002F orphaned sessions and their\ndangling events server-side and returns a summary of removed rows. Make clear this\nis **permanent** and **not reversible** from the dashboard.\n\n### 5. Execute only on confirmation\nIf — and only if — `$ARGUMENTS` is `confirm` (or the user has explicitly approved\nthis run), call `POST \u002Fapi\u002Fsettings\u002Fcleanup`, then re-read `\u002Fapi\u002Fstats` and report\nthe before → after delta. Otherwise stop after the preview and tell the user to\nre-run with `confirm`.\n\n## Output\n\nA preview Markdown table: `id (short) | status | reason | cwd basename | started_at | cost`,\nthen a one-line count and the explicit \"nothing deleted — re-run with `confirm` to\nproceed\" notice. On a confirmed run, add a before → after summary using ▲\u002F▼ on the\ncounts. Currency as USD to 4 decimal places.\n\n## Safety\n\n- This is the ONLY skill in the plugin that mutates data, and only via the one\n  documented endpoint.\n- NEVER call `POST \u002Fapi\u002Fsettings\u002Fcleanup` without an explicit `confirm` from the\n  user in this turn — previewing is the default.\n- Never widen scope to `POST \u002Fapi\u002Fsettings\u002Fclear-data` or any other destructive\n  endpoint; cleanup of stale\u002Fempty sessions only.\n- If the dashboard is unreachable, tell the user to start it with `npm start` from\n  the repo root.\n","# Session Cleanup\n\nFind prune-worthy sessions and explain cleanup — preview first, delete only on\nexplicit confirmation.\n\n## Input\n\nThe user provides: **$ARGUMENTS**\n\n- Empty \u002F `preview` → only show what would be removed (the safe default).\n- `confirm` → the user has reviewed the preview and explicitly authorizes deletion.\n- An optional staleness threshold (e.g. `older than 7d`) for what counts as stale.\n\n## Data Sources\n\n| Endpoint | Returns |\n|----------|---------|\n| `GET \u002Fapi\u002Fsessions?limit=N` | session list: id, status, model, cwd, started_at, ended_at, cost, metadata (turn_count, total_turn_duration_ms) |\n| `GET \u002Fapi\u002Fstats` | totals: total_sessions, active_sessions, total_events, events_today, sessions_by_status, agents_by_status |\n| `POST \u002Fapi\u002Fsettings\u002Fcleanup` | runs the cleanup routine and returns what was removed — DESTRUCTIVE, only after confirmation |\n\n## Report Sections\n\n### 1. Baseline\n`GET \u002Fapi\u002Fstats` — record total_sessions, sessions_by_status, total_events. This is\nthe before-state to compare against.\n\n### 2. Identify candidates\n`GET \u002Fapi\u002Fsessions?limit=1000`. Flag sessions that are:\n- **Empty** — zero events and `turn_count` 0 \u002F null and `cost` 0 (started but never\n  did anything).\n- **Stale active** — `status` active\u002Fworking but last activity older than the\n  threshold (default 24h), i.e. never cleanly stopped.\n- **Truncated** — no `ended_at` and no recent events.\n\n### 3. Preview table (ALWAYS shown)\nList every candidate with the reason it qualifies. State the total count and confirm\nthat **nothing has been deleted yet**.\n\n### 4. Explain the endpoint\nDescribe `POST \u002Fapi\u002Fsettings\u002Fcleanup`: it prunes empty \u002F orphaned sessions and their\ndangling events server-side and returns a summary of removed rows. Make clear this\nis **permanent** and **not reversible** from the dashboard.\n\n### 5. Execute only on confirmation\nIf — and only if — `$ARGUMENTS` is `confirm` (or the user has explicitly approved\nthis run), call `POST \u002Fapi\u002Fsettings\u002Fcleanup`, then re-read `\u002Fapi\u002Fstats` and report\nthe before → after delta. Otherwise stop after the preview and tell the user to\nre-run with `confirm`.\n\n## Output\n\nA preview Markdown table: `id (short) | status | reason | cwd basename | started_at | cost`,\nthen a one-line count and the explicit \"nothing deleted — re-run with `confirm` to\nproceed\" notice. On a confirmed run, add a before → after summary using ▲\u002F▼ on the\ncounts. Currency as USD to 4 decimal places.\n\n## Safety\n\n- This is the ONLY skill in the plugin that mutates data, and only via the one\n  documented endpoint.\n- NEVER call `POST \u002Fapi\u002Fsettings\u002Fcleanup` without an explicit `confirm` from the\n  user in this turn — previewing is the default.\n- Never widen scope to `POST \u002Fapi\u002Fsettings\u002Fclear-data` or any other destructive\n  endpoint; cleanup of stale\u002Fempty sessions only.\n- If the dashboard is unreachable, tell the user to start it with `npm start` from\n  the repo root.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fsession-cleanup",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill session-cleanup",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill session-cleanup",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill session-cleanup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsession-cleanup\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",270,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fsession-cleanup\u002Fagents\u002Fopenai.yaml",[53,60,65,72,79,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":61,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]