[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M758XSPB0P2G71ABRYJ6Q5MD":3,"skill-same:01M758XSPB0P2G71ABRYJ6Q5MD":54},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M758XSPB0P2G71ABRYJ6Q5MD","recurring-reports",null,"Design and run recurring automated reports: define cadence, metrics, sources, and delivery; wire to cron; verify delivery.","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\u002Fresearch\u002Frecurring-reports\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: recurring-reports\nversion: 1.0.0\ndescription: \"Design and run recurring automated reports: define cadence, metrics, sources, and delivery; wire to cron; verify delivery.\"\ntriggers:\n  - \"recurring report\"\n  - \"automated report\"\n  - \"scheduled report\"\n  - \"report cron\"\n  - \"weekly digest\"\n---\n\n## When to Use\nUse when designing a report that must run on a schedule — define what it measures, where data comes from, how often it runs, and how it's delivered — and when wiring it to cron or verifying delivery.\n\n## Report Spec\nWrite a one-page spec before building anything:\n- **Metrics**: exact definitions with formulas (e.g. engagement rate = engagements\u002Fimpressions × 100). Every number must be reproducible.\n- **Period**: lookback window (daily = last 24h, weekly = last 7 days, monthly = calendar month) with an explicit timezone.\n- **Audience**: who reads it and the decision each section supports; put the reader's goal first.\n- **Format**: markdown\u002FHTML\u002FPDF\u002FCSV attachment; max length (e.g. one screen for daily digests).\n\n## Data Sources\n- **SQL**: read-only queries against the warehouse; parameterize the period; add LIMITs and index hints; snapshot timestamps.\n- **APIs**: REST\u002FGraphQL with pagination (see the shopify skill for cursor patterns); handle rate limits with retry\u002Fbackoff.\n- **CSVs**: exported files or bucket paths; validate headers and row counts on every run.\n- Log the source and query version in the report footer so numbers can be traced.\n\n## Scheduling (cron)\n- Daily: `0 7 * * *` (07:00); weekly: `0 7 * * 1` (Monday); monthly: `0 7 1 * *` (1st).\n- In Hermes, create the job with `cronjob action='create'` using a unique, descriptive name; keep the uninstall\u002Fcleanup list in sync.\n- Never run heavy reports more often than hourly; cache intermediate results.\n- Make runs idempotent — re-running the same period must produce the same output.\n\n## Delivery\n- **Email**: SMTP with a stable subject prefix (e.g. \"[Daily] Revenue Digest\"); report as body or attachment.\n- **Telegram**: send as a message or file; keep daily digests under message limits.\n- **Chat-delivered reports**: the cron agent's FINAL RESPONSE is the delivered message. Instruct the\n  prompt to write the report content itself, then `MEDIA:` lines for any attachments; otherwise the\n  agent may emit a build\u002Fverification summary (\"all files generated\") that reaches the reader instead\n  of the report. Never emit `MEDIA:` lines for files you did not actually produce. For generating the\n  `.docx`\u002F`.pdf`\u002F`.md` attachments, see the `office-document-generation` skill.\n- **Files**: write to a dated path (`reports\u002F2026-08-05\u002F`) with a rolling retention policy (e.g. 90 days).\n- Store recipients, channels, and the failure contact with the job, not inside the script.\n\n## Drift Detection\n- Compare key numbers against trailing averages; flag deviations > 2× or outside expected bounds (e.g. revenue down 30% WoW).\n- Detect data-source drift: missing columns, zero rows, schema changes, date gaps — log a warning naming the source.\n- Detect audience drift: report opens\u002Fengagement declining — question whether the metrics still serve the reader.\n\n## Failure Handling\n- On failure: retry once with backoff, then notify the failure contact with the error and a partial report if available.\n- Log every run: start time, duration, rows processed, success\u002Ffailure, delivery status.\n- A report that silently fails for 3 runs is worse than no report — add a heartbeat\u002Fhealth check to the job.\n- When a cron job is renamed or removed, update both the create and uninstall references in the same commit (see AGENTS.md Rule 5).\n\n## Pitfalls\n- Don't hardcode dates — derive the period from run time.\n- Don't email raw SQL dumps to executives; summarize with a link to detail.\n- Don't delete old reports without a retention policy.\n- Always verify one real delivery end-to-end before trusting the schedule.\n","## When to Use\nUse when designing a report that must run on a schedule — define what it measures, where data comes from, how often it runs, and how it's delivered — and when wiring it to cron or verifying delivery.\n\n## Report Spec\nWrite a one-page spec before building anything:\n- **Metrics**: exact definitions with formulas (e.g. engagement rate = engagements\u002Fimpressions × 100). Every number must be reproducible.\n- **Period**: lookback window (daily = last 24h, weekly = last 7 days, monthly = calendar month) with an explicit timezone.\n- **Audience**: who reads it and the decision each section supports; put the reader's goal first.\n- **Format**: markdown\u002FHTML\u002FPDF\u002FCSV attachment; max length (e.g. one screen for daily digests).\n\n## Data Sources\n- **SQL**: read-only queries against the warehouse; parameterize the period; add LIMITs and index hints; snapshot timestamps.\n- **APIs**: REST\u002FGraphQL with pagination (see the shopify skill for cursor patterns); handle rate limits with retry\u002Fbackoff.\n- **CSVs**: exported files or bucket paths; validate headers and row counts on every run.\n- Log the source and query version in the report footer so numbers can be traced.\n\n## Scheduling (cron)\n- Daily: `0 7 * * *` (07:00); weekly: `0 7 * * 1` (Monday); monthly: `0 7 1 * *` (1st).\n- In Hermes, create the job with `cronjob action='create'` using a unique, descriptive name; keep the uninstall\u002Fcleanup list in sync.\n- Never run heavy reports more often than hourly; cache intermediate results.\n- Make runs idempotent — re-running the same period must produce the same output.\n\n## Delivery\n- **Email**: SMTP with a stable subject prefix (e.g. \"[Daily] Revenue Digest\"); report as body or attachment.\n- **Telegram**: send as a message or file; keep daily digests under message limits.\n- **Chat-delivered reports**: the cron agent's FINAL RESPONSE is the delivered message. Instruct the\n  prompt to write the report content itself, then `MEDIA:` lines for any attachments; otherwise the\n  agent may emit a build\u002Fverification summary (\"all files generated\") that reaches the reader instead\n  of the report. Never emit `MEDIA:` lines for files you did not actually produce. For generating the\n  `.docx`\u002F`.pdf`\u002F`.md` attachments, see the `office-document-generation` skill.\n- **Files**: write to a dated path (`reports\u002F2026-08-05\u002F`) with a rolling retention policy (e.g. 90 days).\n- Store recipients, channels, and the failure contact with the job, not inside the script.\n\n## Drift Detection\n- Compare key numbers against trailing averages; flag deviations > 2× or outside expected bounds (e.g. revenue down 30% WoW).\n- Detect data-source drift: missing columns, zero rows, schema changes, date gaps — log a warning naming the source.\n- Detect audience drift: report opens\u002Fengagement declining — question whether the metrics still serve the reader.\n\n## Failure Handling\n- On failure: retry once with backoff, then notify the failure contact with the error and a partial report if available.\n- Log every run: start time, duration, rows processed, success\u002Ffailure, delivery status.\n- A report that silently fails for 3 runs is worse than no report — add a heartbeat\u002Fhealth check to the job.\n- When a cron job is renamed or removed, update both the create and uninstall references in the same commit (see AGENTS.md Rule 5).\n\n## Pitfalls\n- Don't hardcode dates — derive the period from run time.\n- Don't email raw SQL dumps to executives; summarize with a link to detail.\n- Don't delete old reports without a retention policy.\n- Always verify one real delivery end-to-end before trusting the schedule.\n",{"name":5,"version":24,"triggers":25,"description":7},"1.0.0",[26,27,28,29,30],"recurring report","automated report","scheduled report","report cron","weekly digest","main","2e6aa8d15ab0a366c90be54f61bf9c6e97015e83","skills\u002Fresearch\u002Frecurring-reports",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":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add lukemcqueen\u002Fsteadfaste-fleet --skill recurring-reports",{"tool":46,"command":47},"bunx","bunx skills add lukemcqueen\u002Fsteadfaste-fleet --skill recurring-reports",{"tool":49,"command":50},"pnpm","pnpm dlx skills add lukemcqueen\u002Fsteadfaste-fleet --skill recurring-reports","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flukemcqueen\u002Fsteadfaste-fleet\u002Fblob\u002Fmain\u002Fskills\u002Fresearch\u002Frecurring-reports\u002FSKILL.md",true,[],[55,63,70,77,84,91],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":62},"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":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":62},"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":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":62},"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":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":62},"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":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":62},"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":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":62},"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",[],[]]