[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M758KNX0CPVVZ2WDVC2CY56S":3,"skill-same:01M758KNX0CPVVZ2WDVC2CY56S":61},{"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":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M758KNX0CPVVZ2WDVC2CY56S","orch-weekly-auto-fix",null,"After the weekly opportunity scan identifies issues, run auto-fix patterns — git pull, branch cleanup, Docker restart, permission fixes, disk cleanup — then verify each fix succeeded. Reduces manual intervention for known recurring problems.","lukemcqueen\u002Fsteadfaste-fleet","lukemcqueen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F405240?v=4","01M757MHPAGRXTJAT46SKZP98R","Luke McQueen","01M757MHPZ573KP8DT9GB8SBQ7",4,"MIT","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fweekly-auto-fix\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: orch-weekly-auto-fix\ndescription: \"After the weekly opportunity scan identifies issues, run auto-fix patterns — git pull, branch cleanup, Docker restart, permission fixes, disk cleanup — then verify each fix succeeded. Reduces manual intervention for known recurring problems.\"\nversion: 1.1.0\nauthor: Steadfaste Fleet\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [cron, automation, maintenance, git, docker, security]\n    related_skills: [cron-engineering, public-contribution]\n---\n\n# Weekly Auto-Fix (with Verification)\n\n## When to Use\n\nLoad this skill when:\n- Setting up or modifying the weekly opportunity scan cron job\n- A cron agent needs to auto-fix issues it discovers\n- You want the scan-fix-verify-report pattern instead of scan-only\n\n## How It Works\n\nThe cron runs in four phases:\n\n```\n[Phase 1: Scan]  ← LLM-driven, finds issues across git\u002Fdocker\u002Fperms\u002Fdisk\n    ↓\n[Phase 2: Fix]   ← Agent attempts fixes, then runs companion script\n    ↓\n[Phase 3: Verify] ← Re-check each condition post-fix; PASS\u002FFAIL\u002FWARN per check\n    ↓\n[Phase 4: Report] ← Compact summary: fixed & verified vs needs attention\n```\n\n## Setup\n\n### 1. Deploy the companion script\n\nCopy `scripts\u002Forch-weekly-auto-fix.py` from the steadfaste-fleet repo to `~\u002F.hermes\u002Fscripts\u002F`:\n\n```bash\ncp steadfaste-fleet\u002Fscripts\u002Forch-weekly-auto-fix.py ~\u002F.hermes\u002Fscripts\u002Forch-weekly-auto-fix.py\n```\n\nThe script handles known fix patterns with built-in verification:\n- **git-pull** — pulls upstream changes, then verifies behind count is 0 and no conflicts\n- **branch-delete** — removes stale local branches, then verifies they're gone from git branch\n- **permissions** — chmod 600\u002F644, then stats the file to confirm\n- **disk-cleanup** — cleans bun cache if >100MB, then verifies dir is gone or under threshold\n- **docker-restart** — restarts unhealthy\u002Frestarting containers, then checks docker ps for healthy status\n\n### 2. Create or update the weekly scan cron\n\n```bash\nhermes cron update \u003Cjob-id> \\\n  --prompt \"$(cat \u003C\u003C 'PROMPT'\nYou are Moses. This is your weekly opportunity scan with auto-fix and verification.\n\n## Phase 1: Scan\n\nCheck repos, Docker containers, system files, and cron jobs for issues:\n- Git status (behind origin\u002Fmain? conflicts?)\n- Docker container health (unhealthy\u002Frestarting?)\n- File permissions (world-readable outputs, executable pids?)\n- Disk usage (large caches?)\n- Cron job errors\n\n## Phase 2: Auto-Fix\n\nAttempt fixes for each issue found:\n\n**Git fixes:** `git pull --rebase --autostash` if behind. Delete stale branches. Merge ready PRs.\n\n**Docker fixes:** `docker restart \u003Cname>` for unhealthy containers.\n\n**Permission fixes:** `chmod 600` \u002F `chmod 644`.\n\n**Companion script:** `python3 ~\u002F.hermes\u002Fscripts\u002Forch-weekly-auto-fix.py --verbose` as safety net.\n\n## Phase 3: Verify\n\nFor each fix, verify the fix actually worked:\n- Git: behind count is 0, no conflict markers in git status\n- Docker: container shows \"Up\" or \"healthy\" in docker ps\n- Permissions: stat confirms correct mode\n- Disk: cache dir is removed or under threshold\n\n## Phase 4: Report\n\n- ✅ FIXED if fix + verification passed\n- ❌ FAILED if fix or verification failed\n- Exit silently if nothing needed doing\nPROMPT\n)\" \\\n  --schedule \"0 8 * * 1\" \\\n  --deliver origin\n```\n\n## Fix & Verify Patterns\n\n| Pattern | Detection | Fix | Verification |\n|---------|-----------|-----|--------------|\n| Git behind upstream | `git rev-list --left-right --count HEAD...origin\u002Fmain` | `git pull --rebase --autostash` | Re-check behind count = 0, no `UU`\u002F`AA`\u002F`DD` in `git status --short` |\n| Stale local branches | `git branch -vv` (detect `: gone]`) | `git branch -D \u003Cname>` | Branch absent from `git branch` output |\n| Docker unhealthy | `docker ps` (status \"unhealthy\"\u002F\"restarting\") | `docker restart \u003Cname>` | `docker ps` shows \"Up\" or \"healthy\" after 3s wait |\n| World-readable scorer | `stat -f %p` shows 644 | `chmod 600` | `stat` shows 600 |\n| Executable pid file | `stat -f %p` shows 755 | `chmod 644` | `stat` shows 644 or 600 |\n| Large bun cache | `du -sh ~\u002F.bun\u002Finstall\u002Fcache` >100MB | `rm -rf` | Dir gone or \u003C100MB remaining |\n\n## Companion Script Output\n\nThe script produces structured JSON with verification results:\n\n```json\n{\n  \"actions_taken\": [\"git-pull: pulled 3 commit(s) from origin\u002Fmain\"],\n  \"verify_results\": [\n    {\"check\": \"git-pull\", \"status\": \"PASS\", \"detail\": \"up to date, no conflicts\"},\n    {\"check\": \"perms-scorer\", \"status\": \"PASS\", \"detail\": \"already 600\"},\n    {\"check\": \"perms-pid\", \"status\": \"FAIL\", \"detail\": \"mode is 0o755\"}\n  ],\n  \"summary\": {\"fixed\": 1, \"passed\": 2, \"failed\": 1, \"warned\": 0}\n}\n```\n\nOn success with nothing to do, outputs empty JSON `{}` (silent — watchdog pattern).\n\n## Pitfalls\n\n- **Don't merge PRs during a rebase conflict.** If `git pull --rebase` fails, report it — don't force push.\n- **Don't delete protected branches** (main, master, develop). The script skips them.\n- **Docker restart may cause brief downtime.** Only restart containers clearly marked \"unhealthy\" or \"restarting\" — not healthy ones.\n- **The companion script is a safety net, not the primary fixer.** The LLM agent should attempt reasoning-heavy fixes (git merge, mycortex repair) directly, then use the script for mechanical checks.\n- **If nothing was broken, stay silent.** The watchdog pattern applies — the user should not hear from a cron that found nothing to do.\n- **Verification adds latency.** Docker verification waits 3s; git verification runs 2 extra commands. This is fine for a weekly cron, but don't add heavy verifications to high-frequency crons.\n","# Weekly Auto-Fix (with Verification)\n\n## When to Use\n\nLoad this skill when:\n- Setting up or modifying the weekly opportunity scan cron job\n- A cron agent needs to auto-fix issues it discovers\n- You want the scan-fix-verify-report pattern instead of scan-only\n\n## How It Works\n\nThe cron runs in four phases:\n\n```\n[Phase 1: Scan]  ← LLM-driven, finds issues across git\u002Fdocker\u002Fperms\u002Fdisk\n    ↓\n[Phase 2: Fix]   ← Agent attempts fixes, then runs companion script\n    ↓\n[Phase 3: Verify] ← Re-check each condition post-fix; PASS\u002FFAIL\u002FWARN per check\n    ↓\n[Phase 4: Report] ← Compact summary: fixed & verified vs needs attention\n```\n\n## Setup\n\n### 1. Deploy the companion script\n\nCopy `scripts\u002Forch-weekly-auto-fix.py` from the steadfaste-fleet repo to `~\u002F.hermes\u002Fscripts\u002F`:\n\n```bash\ncp steadfaste-fleet\u002Fscripts\u002Forch-weekly-auto-fix.py ~\u002F.hermes\u002Fscripts\u002Forch-weekly-auto-fix.py\n```\n\nThe script handles known fix patterns with built-in verification:\n- **git-pull** — pulls upstream changes, then verifies behind count is 0 and no conflicts\n- **branch-delete** — removes stale local branches, then verifies they're gone from git branch\n- **permissions** — chmod 600\u002F644, then stats the file to confirm\n- **disk-cleanup** — cleans bun cache if >100MB, then verifies dir is gone or under threshold\n- **docker-restart** — restarts unhealthy\u002Frestarting containers, then checks docker ps for healthy status\n\n### 2. Create or update the weekly scan cron\n\n```bash\nhermes cron update \u003Cjob-id> \\\n  --prompt \"$(cat \u003C\u003C 'PROMPT'\nYou are Moses. This is your weekly opportunity scan with auto-fix and verification.\n\n## Phase 1: Scan\n\nCheck repos, Docker containers, system files, and cron jobs for issues:\n- Git status (behind origin\u002Fmain? conflicts?)\n- Docker container health (unhealthy\u002Frestarting?)\n- File permissions (world-readable outputs, executable pids?)\n- Disk usage (large caches?)\n- Cron job errors\n\n## Phase 2: Auto-Fix\n\nAttempt fixes for each issue found:\n\n**Git fixes:** `git pull --rebase --autostash` if behind. Delete stale branches. Merge ready PRs.\n\n**Docker fixes:** `docker restart \u003Cname>` for unhealthy containers.\n\n**Permission fixes:** `chmod 600` \u002F `chmod 644`.\n\n**Companion script:** `python3 ~\u002F.hermes\u002Fscripts\u002Forch-weekly-auto-fix.py --verbose` as safety net.\n\n## Phase 3: Verify\n\nFor each fix, verify the fix actually worked:\n- Git: behind count is 0, no conflict markers in git status\n- Docker: container shows \"Up\" or \"healthy\" in docker ps\n- Permissions: stat confirms correct mode\n- Disk: cache dir is removed or under threshold\n\n## Phase 4: Report\n\n- ✅ FIXED if fix + verification passed\n- ❌ FAILED if fix or verification failed\n- Exit silently if nothing needed doing\nPROMPT\n)\" \\\n  --schedule \"0 8 * * 1\" \\\n  --deliver origin\n```\n\n## Fix & Verify Patterns\n\n| Pattern | Detection | Fix | Verification |\n|---------|-----------|-----|--------------|\n| Git behind upstream | `git rev-list --left-right --count HEAD...origin\u002Fmain` | `git pull --rebase --autostash` | Re-check behind count = 0, no `UU`\u002F`AA`\u002F`DD` in `git status --short` |\n| Stale local branches | `git branch -vv` (detect `: gone]`) | `git branch -D \u003Cname>` | Branch absent from `git branch` output |\n| Docker unhealthy | `docker ps` (status \"unhealthy\"\u002F\"restarting\") | `docker restart \u003Cname>` | `docker ps` shows \"Up\" or \"healthy\" after 3s wait |\n| World-readable scorer | `stat -f %p` shows 644 | `chmod 600` | `stat` shows 600 |\n| Executable pid file | `stat -f %p` shows 755 | `chmod 644` | `stat` shows 644 or 600 |\n| Large bun cache | `du -sh ~\u002F.bun\u002Finstall\u002Fcache` >100MB | `rm -rf` | Dir gone or \u003C100MB remaining |\n\n## Companion Script Output\n\nThe script produces structured JSON with verification results:\n\n```json\n{\n  \"actions_taken\": [\"git-pull: pulled 3 commit(s) from origin\u002Fmain\"],\n  \"verify_results\": [\n    {\"check\": \"git-pull\", \"status\": \"PASS\", \"detail\": \"up to date, no conflicts\"},\n    {\"check\": \"perms-scorer\", \"status\": \"PASS\", \"detail\": \"already 600\"},\n    {\"check\": \"perms-pid\", \"status\": \"FAIL\", \"detail\": \"mode is 0o755\"}\n  ],\n  \"summary\": {\"fixed\": 1, \"passed\": 2, \"failed\": 1, \"warned\": 0}\n}\n```\n\nOn success with nothing to do, outputs empty JSON `{}` (silent — watchdog pattern).\n\n## Pitfalls\n\n- **Don't merge PRs during a rebase conflict.** If `git pull --rebase` fails, report it — don't force push.\n- **Don't delete protected branches** (main, master, develop). The script skips them.\n- **Docker restart may cause brief downtime.** Only restart containers clearly marked \"unhealthy\" or \"restarting\" — not healthy ones.\n- **The companion script is a safety net, not the primary fixer.** The LLM agent should attempt reasoning-heavy fixes (git merge, mycortex repair) directly, then use the script for mechanical checks.\n- **If nothing was broken, stay silent.** The watchdog pattern applies — the user should not hear from a cron that found nothing to do.\n- **Verification adds latency.** Docker verification waits 3s; git verification runs 2 extra commands. This is fine for a weekly cron, but don't add heavy verifications to high-frequency crons.\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"description":7},"Steadfaste Fleet","1.1.0",{"hermes":27},{"tags":28,"related_skills":35},[29,30,31,32,33,34],"cron","automation","maintenance","git","docker","security",[36,37],"cron-engineering","public-contribution","main","2e6aa8d15ab0a366c90be54f61bf9c6e97015e83","skills\u002Fdevops\u002Fweekly-auto-fix",1,"https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet","steadfaste.com","https:\u002F\u002Fgithub.com\u002Flukemcqueen","AI Architect | Building Hermes Cortex: governed multi-agent AI for autonomous software engineering | Enterprise Tech Consultant","2026-11-14 22:33:34",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add lukemcqueen\u002Fsteadfaste-fleet --skill orch-weekly-auto-fix",{"tool":53,"command":54},"bunx","bunx skills add lukemcqueen\u002Fsteadfaste-fleet --skill orch-weekly-auto-fix",{"tool":56,"command":57},"pnpm","pnpm dlx skills add lukemcqueen\u002Fsteadfaste-fleet --skill orch-weekly-auto-fix","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fweekly-auto-fix\u002FSKILL.md",true,[],[62,70,77,84,91,98],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":69},"01M7DXY4G8NSVB59K8B6S2AQNP","macbook-linux-maintenance","Legacy MacBook Linux fixes: GPU wedge, reboot hang, thermal.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fmacbook-linux-maintenance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":69},"01M7DXXYJCXFJ3TGB84ZQ8KFE6","governance-regression-triage","Triage a host's governance issues: what changed.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fgovernance-regression-triage\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":69},"01M7DXXSAP1G8FDRJAMXQGBBMK","enforcement-immutability","Use when enforcement files lose their immutable flag.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fenforcement-immutability\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":69},"01M78SSDQVRYX64Y16X32TC0NS","steadfaste-fleet-repo-deploy","Use when committing to the steadfaste-fleet repo.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-repo-deploy\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":69},"01M78SS928F3R2RJAYVW4E30CE","steadfaste-fleet-maintenance","Maintain an installed Steadfaste Fleet instance — update both the upstream Hermes Agent and the fleet repo layer, merge diverged histories, sync skills safely, and troubleshoot common issues. Covers the dual-update workflow (hermes update + fleet-update.sh), encrypted brain data backup, mycortex import, and recovery techniques.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Fsteadfaste-fleet-maintenance\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":69},"01M78SP1CHW0T0BWE5ZT6JBPX8","fleet-preflight","DEPRECATED alias — merged into survey-before-action (2026-08-20). Load survey-before-action instead; its \"Repo-Specific Pre-Flight\" section covers git search, Hermes boundary, and deployment verification.","https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fdevops\u002Ffleet-preflight\u002FSKILL.md",[],[]]