[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78AQ2BP56P9RYPF5TCQSX0D":3,"skill-same:01M78AQ2BP56P9RYPF5TCQSX0D":88},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M78AQ2BP56P9RYPF5TCQSX0D","scheduled-summary",null,"Use when a recurring cross-session digest should be produced and delivered via Hermes cron — aggregates session activity, cron job outputs, memory changes, and tool usage stats into a compact summary for delivery via messaging platforms. Surfaces outstanding tasks and cross-session context that's invisible on chat platforms.","moonlight-lupin\u002Fagent-skills","moonlight-lupin","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F136997773?v=4","01M78AEDSH1N62R0RNWPWMWVQY","01M78AEDT8ZF85MTK6XYBQBTNT",123,"MIT","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Fscheduled-summary\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scheduled-summary\ndescription: \"Use when a recurring cross-session digest should be produced and delivered via Hermes cron — aggregates session activity, cron job outputs, memory changes, and tool usage stats into a compact summary for delivery via messaging platforms. Surfaces outstanding tasks and cross-session context that's invisible on chat platforms.\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: moonlight-lupin\n  platforms: [linux, macos, windows]\n  tags: [summary, digest, cron, sessions, activity, cross-session, notification, scheduled]\n  related_skills: [decision-log, news-monitoring]\n---\n\n# Scheduled Summary\n\n## Overview\n\nMessaging platforms are excellent for one active conversation, but they hide the\nactivity that happened elsewhere: other sessions, scheduled jobs, saved memory,\nand unresolved items from earlier work. This skill creates a periodic digest that\nsurfaces that cross-session activity in a compact format suitable for chat\nmessaging platforms or any notification channel that accepts Markdown or plain\ntext.\n\nThe digest is designed for a cron scheduler. It reads optional local data sources\n(session store, cron output directory, memory JSON files, and log file), filters\nactivity to a configurable time window, and emits Markdown, JSON, or plain text.\nWhen no data sources are configured, it emits a template digest that an agent can\nfill by querying its own platform-specific session history, scheduler status,\nand memory tools.\n\n## Quick start\n\nFrom this skill directory:\n\n```bash\npython scripts\u002Fsummarize.py generate --since 24h\n```\n\nWith explicit data sources:\n\n```bash\npython scripts\u002Fsummarize.py generate \\\n  --since 24h \\\n  --sessions-db \u002Fpath\u002Fto\u002Fsessions.sqlite \\\n  --cron-dir \u002Fpath\u002Fto\u002Fcron-output \\\n  --memory-dir \u002Fpath\u002Fto\u002Fmemory-json \\\n  --log-file \u002Fpath\u002Fto\u002Fagent.log\n```\n\nShow current configuration and skipped sources:\n\n```bash\npython scripts\u002Fsummarize.py config\n```\n\nCreate a config template to fill in:\n\n```bash\npython scripts\u002Fsummarize.py init --output .summary-config.json\n```\n\n## What the digest includes\n\n1. **Session activity** — sessions started or completed inside the time window,\n   plus topic titles where available.\n2. **Cron job status** — jobs that ran successfully, jobs that failed, and jobs\n   marked overdue by their output files.\n3. **Memory changes** — new saved memories and updated facts from JSON records.\n4. **Tool usage** — most-used tools, total calls, and error counts from a text or\n   JSONL log file.\n5. **Outstanding items** — due decision reviews, incomplete tasks, and TODO-like\n   items found in session transcripts.\n6. **Time window** — every section is scoped to `--since` (`24h`, `7d`, `2w`,\n   etc.) unless the source explicitly marks an item overdue.\n\n## Workflow\n\n1. **Pick the delivery cadence.** Daily is a good default. Weekly works for\n   quieter systems. Avoid high-frequency summaries unless the downstream channel\n   has strong threading or batching.\n2. **Choose data sources.** Configure only the stores you trust the digest to\n   read. Start with cron output and logs, then add session and memory stores once\n   you understand their schema.\n3. **Generate once manually.** Run `generate --since 24h` and inspect the result\n   for length, sensitive fields, and duplicate items.\n4. **Tune sections.** Use `--sections sessions,cron,outstanding` to keep the\n   first scheduled digest short. Add `memory` and `tools` if they are useful.\n5. **Schedule the command.** Run it from a cron scheduler and redirect output to\n   the channel integration or a file consumed by your notifier.\n6. **Review after a week.** Check whether the digest is surfacing actionable\n   items. Remove noisy sections and add missing source paths.\n\nCompletion criterion: the scheduled command produces a digest with a generated\ntimestamp, the requested sections, and no unexpected secrets or full transcripts.\n\n## Cron scheduler setup\n\nGeneric daily cron scheduler entry:\n\n```cron\n0 8 * * * cd \u002Fpath\u002Fto\u002Fscheduled-summary && python scripts\u002Fsummarize.py generate --since 24h --output \u002Ftmp\u002Factivity-digest.md\n```\n\nExample with environment variables instead of flags:\n\n```cron\n0 8 * * * SESSIONS_DB=\u002Fdata\u002Fsessions.sqlite CRON_OUTPUT_DIR=\u002Fdata\u002Fcron MEMORY_DIR=\u002Fdata\u002Fmemory LOG_FILE=\u002Fdata\u002Fagent.log python \u002Fpath\u002Fto\u002Fscheduled-summary\u002Fscripts\u002Fsummarize.py generate --since 24h\n```\n\nTo deliver to a messaging platform, pipe or post the generated file using your\nown notifier:\n\n```bash\npython scripts\u002Fsummarize.py generate --since 24h --output \u002Ftmp\u002Fdigest.md\npython \u002Fpath\u002Fto\u002Fsend_notification.py \u002Ftmp\u002Fdigest.md\n```\n\nKeep the notifier separate from the digest generator so the script remains\nportable across platforms.\n\n## Output format\n\nMarkdown output is optimized for chat platforms:\n\n- Compact `##` \u002F `###` headings.\n- Bullets rather than paragraphs.\n- Emoji status markers for quick scanning.\n- Short quoted topics instead of transcript excerpts.\n- Code blocks only for dense stats when useful.\n- A final generated timestamp in UTC.\n\nSupported formats:\n\n```bash\npython scripts\u002Fsummarize.py generate --format markdown\npython scripts\u002Fsummarize.py generate --format json\npython scripts\u002Fsummarize.py generate --format text\n```\n\nWrite to a file:\n\n```bash\npython scripts\u002Fsummarize.py generate --since 7d --output weekly-digest.md\n```\n\n## Customization\n\nInclude only specific sections:\n\n```bash\npython scripts\u002Fsummarize.py generate --sections sessions,cron,outstanding\n```\n\nCommon section sets:\n\n- **Daily operational digest:** `sessions,cron,outstanding`\n- **Weekly review:** `sessions,cron,memory,tools,outstanding`\n- **Low-noise health check:** `cron,tools`\n- **Agent-filled template:** run with no source paths configured, then fill the\n  placeholders from platform-specific tools.\n\nConfigure paths with flags, environment variables, or a generated config file:\n\n| Source | Flag | Environment variable |\n| --- | --- | --- |\n| Session SQLite database | `--sessions-db` | `SESSIONS_DB` |\n| Cron output directory | `--cron-dir` | `CRON_OUTPUT_DIR` |\n| Memory JSON directory | `--memory-dir` | `MEMORY_DIR` |\n| Tool\u002Flog file | `--log-file` | `LOG_FILE` |\n| Decision records | `--decisions-dir` | `DECISIONS_DIR` |\n\nSee `references\u002Fdata-sources.md` for expected formats and schema notes.\n\n## Integrations\n\n### decision-log\n\nIf a decision record directory is available, pass it with `--decisions-dir` or\n`DECISIONS_DIR`. The digest scans Markdown decision records for accepted or\nproposed decisions whose `Next review: YYYY-MM-DD` is due, then reports the count\nand titles in the Outstanding section.\n\n### news-monitoring\n\nNews monitoring jobs usually write a scheduled output file. Point `--cron-dir` at\nthe directory containing those outputs. The digest will report whether monitoring\nran, succeeded, failed, or marked itself overdue. Keep the full news summary in\nits own file; the scheduled summary should only mention that monitoring ran and\nwhether action is required.\n\n## Common pitfalls\n\n1. **Too verbose for chat.** Do not paste full transcripts or full cron logs into\n   the digest. Surface counts, titles, and one-line action items.\n2. **Sensitive data leakage.** Session titles, memory facts, and log lines may\n   contain secrets or personal data. Review the first outputs manually and redact\n   upstream sources where needed.\n3. **Running too frequently.** Hourly summaries often create notification\n   fatigue and duplicate the active chat. Daily or weekly is usually better.\n4. **No deduplication across summaries.** If the same overdue item appears every\n   day, either resolve it, suppress it upstream, or add a stable decision\u002Ftask\n   owner outside this digest.\n5. **Treating template mode as complete data.** Placeholder output means no data\n   sources were readable. The agent or operator must fill it from platform tools.\n6. **Assuming one universal session schema.** Session stores vary by platform.\n   The script uses best-effort SQLite introspection, but exact counts depend on\n   the available columns.\n7. **Mixing generation and delivery.** Keep the digest generator independent from\n   platform-specific webhook or bot code; this makes testing and migration easier.\n\n## What this skill is not\n\n- Not a session search tool. Use your platform's session search or transcript\n  browser when you need a specific conversation.\n- Not a full transcript exporter. It intentionally summarizes titles, counts,\n  and TODO-like lines only.\n- Not a replacement for session browsing. It helps decide what to inspect next.\n- Not a complete scheduler dashboard. It reads output files and status markers;\n  it does not own or run the scheduler.\n- Not a secrets scanner. It reduces verbosity, but it cannot guarantee that the\n  source data is safe to send to a messaging platform.\n\n## Reference files\n\n- `references\u002Fdigest-format.md` — section contract, output variants, daily and\n  weekly examples.\n- `references\u002Fdata-sources.md` — source configuration, expected formats, and\n  schema examples.\n- `templates\u002Fdigest-template.md` — blank Markdown template for agent-filled or\n  manually curated digests.\n- `scripts\u002Fsummarize.py` — stdlib CLI for generating, configuring, and\n  bootstrapping summary files.\n\n## Verification checklist\n\n- [ ] `python scripts\u002Fsummarize.py --help` shows `generate`, `config`, and `init`.\n- [ ] `python scripts\u002Fsummarize.py generate --since 24h` works without sources\n      and emits template mode output.\n- [ ] A mock run with sources includes only events inside the time window, except\n      explicitly overdue cron jobs.\n- [ ] `--sections` excludes omitted sections from Markdown, JSON, and text.\n- [ ] `--format json` returns parseable JSON.\n- [ ] The first scheduled output has been reviewed for secrets and excessive\n      length before connecting it to a messaging platform.\n","# Scheduled Summary\n\n## Overview\n\nMessaging platforms are excellent for one active conversation, but they hide the\nactivity that happened elsewhere: other sessions, scheduled jobs, saved memory,\nand unresolved items from earlier work. This skill creates a periodic digest that\nsurfaces that cross-session activity in a compact format suitable for chat\nmessaging platforms or any notification channel that accepts Markdown or plain\ntext.\n\nThe digest is designed for a cron scheduler. It reads optional local data sources\n(session store, cron output directory, memory JSON files, and log file), filters\nactivity to a configurable time window, and emits Markdown, JSON, or plain text.\nWhen no data sources are configured, it emits a template digest that an agent can\nfill by querying its own platform-specific session history, scheduler status,\nand memory tools.\n\n## Quick start\n\nFrom this skill directory:\n\n```bash\npython scripts\u002Fsummarize.py generate --since 24h\n```\n\nWith explicit data sources:\n\n```bash\npython scripts\u002Fsummarize.py generate \\\n  --since 24h \\\n  --sessions-db \u002Fpath\u002Fto\u002Fsessions.sqlite \\\n  --cron-dir \u002Fpath\u002Fto\u002Fcron-output \\\n  --memory-dir \u002Fpath\u002Fto\u002Fmemory-json \\\n  --log-file \u002Fpath\u002Fto\u002Fagent.log\n```\n\nShow current configuration and skipped sources:\n\n```bash\npython scripts\u002Fsummarize.py config\n```\n\nCreate a config template to fill in:\n\n```bash\npython scripts\u002Fsummarize.py init --output .summary-config.json\n```\n\n## What the digest includes\n\n1. **Session activity** — sessions started or completed inside the time window,\n   plus topic titles where available.\n2. **Cron job status** — jobs that ran successfully, jobs that failed, and jobs\n   marked overdue by their output files.\n3. **Memory changes** — new saved memories and updated facts from JSON records.\n4. **Tool usage** — most-used tools, total calls, and error counts from a text or\n   JSONL log file.\n5. **Outstanding items** — due decision reviews, incomplete tasks, and TODO-like\n   items found in session transcripts.\n6. **Time window** — every section is scoped to `--since` (`24h`, `7d`, `2w`,\n   etc.) unless the source explicitly marks an item overdue.\n\n## Workflow\n\n1. **Pick the delivery cadence.** Daily is a good default. Weekly works for\n   quieter systems. Avoid high-frequency summaries unless the downstream channel\n   has strong threading or batching.\n2. **Choose data sources.** Configure only the stores you trust the digest to\n   read. Start with cron output and logs, then add session and memory stores once\n   you understand their schema.\n3. **Generate once manually.** Run `generate --since 24h` and inspect the result\n   for length, sensitive fields, and duplicate items.\n4. **Tune sections.** Use `--sections sessions,cron,outstanding` to keep the\n   first scheduled digest short. Add `memory` and `tools` if they are useful.\n5. **Schedule the command.** Run it from a cron scheduler and redirect output to\n   the channel integration or a file consumed by your notifier.\n6. **Review after a week.** Check whether the digest is surfacing actionable\n   items. Remove noisy sections and add missing source paths.\n\nCompletion criterion: the scheduled command produces a digest with a generated\ntimestamp, the requested sections, and no unexpected secrets or full transcripts.\n\n## Cron scheduler setup\n\nGeneric daily cron scheduler entry:\n\n```cron\n0 8 * * * cd \u002Fpath\u002Fto\u002Fscheduled-summary && python scripts\u002Fsummarize.py generate --since 24h --output \u002Ftmp\u002Factivity-digest.md\n```\n\nExample with environment variables instead of flags:\n\n```cron\n0 8 * * * SESSIONS_DB=\u002Fdata\u002Fsessions.sqlite CRON_OUTPUT_DIR=\u002Fdata\u002Fcron MEMORY_DIR=\u002Fdata\u002Fmemory LOG_FILE=\u002Fdata\u002Fagent.log python \u002Fpath\u002Fto\u002Fscheduled-summary\u002Fscripts\u002Fsummarize.py generate --since 24h\n```\n\nTo deliver to a messaging platform, pipe or post the generated file using your\nown notifier:\n\n```bash\npython scripts\u002Fsummarize.py generate --since 24h --output \u002Ftmp\u002Fdigest.md\npython \u002Fpath\u002Fto\u002Fsend_notification.py \u002Ftmp\u002Fdigest.md\n```\n\nKeep the notifier separate from the digest generator so the script remains\nportable across platforms.\n\n## Output format\n\nMarkdown output is optimized for chat platforms:\n\n- Compact `##` \u002F `###` headings.\n- Bullets rather than paragraphs.\n- Emoji status markers for quick scanning.\n- Short quoted topics instead of transcript excerpts.\n- Code blocks only for dense stats when useful.\n- A final generated timestamp in UTC.\n\nSupported formats:\n\n```bash\npython scripts\u002Fsummarize.py generate --format markdown\npython scripts\u002Fsummarize.py generate --format json\npython scripts\u002Fsummarize.py generate --format text\n```\n\nWrite to a file:\n\n```bash\npython scripts\u002Fsummarize.py generate --since 7d --output weekly-digest.md\n```\n\n## Customization\n\nInclude only specific sections:\n\n```bash\npython scripts\u002Fsummarize.py generate --sections sessions,cron,outstanding\n```\n\nCommon section sets:\n\n- **Daily operational digest:** `sessions,cron,outstanding`\n- **Weekly review:** `sessions,cron,memory,tools,outstanding`\n- **Low-noise health check:** `cron,tools`\n- **Agent-filled template:** run with no source paths configured, then fill the\n  placeholders from platform-specific tools.\n\nConfigure paths with flags, environment variables, or a generated config file:\n\n| Source | Flag | Environment variable |\n| --- | --- | --- |\n| Session SQLite database | `--sessions-db` | `SESSIONS_DB` |\n| Cron output directory | `--cron-dir` | `CRON_OUTPUT_DIR` |\n| Memory JSON directory | `--memory-dir` | `MEMORY_DIR` |\n| Tool\u002Flog file | `--log-file` | `LOG_FILE` |\n| Decision records | `--decisions-dir` | `DECISIONS_DIR` |\n\nSee `references\u002Fdata-sources.md` for expected formats and schema notes.\n\n## Integrations\n\n### decision-log\n\nIf a decision record directory is available, pass it with `--decisions-dir` or\n`DECISIONS_DIR`. The digest scans Markdown decision records for accepted or\nproposed decisions whose `Next review: YYYY-MM-DD` is due, then reports the count\nand titles in the Outstanding section.\n\n### news-monitoring\n\nNews monitoring jobs usually write a scheduled output file. Point `--cron-dir` at\nthe directory containing those outputs. The digest will report whether monitoring\nran, succeeded, failed, or marked itself overdue. Keep the full news summary in\nits own file; the scheduled summary should only mention that monitoring ran and\nwhether action is required.\n\n## Common pitfalls\n\n1. **Too verbose for chat.** Do not paste full transcripts or full cron logs into\n   the digest. Surface counts, titles, and one-line action items.\n2. **Sensitive data leakage.** Session titles, memory facts, and log lines may\n   contain secrets or personal data. Review the first outputs manually and redact\n   upstream sources where needed.\n3. **Running too frequently.** Hourly summaries often create notification\n   fatigue and duplicate the active chat. Daily or weekly is usually better.\n4. **No deduplication across summaries.** If the same overdue item appears every\n   day, either resolve it, suppress it upstream, or add a stable decision\u002Ftask\n   owner outside this digest.\n5. **Treating template mode as complete data.** Placeholder output means no data\n   sources were readable. The agent or operator must fill it from platform tools.\n6. **Assuming one universal session schema.** Session stores vary by platform.\n   The script uses best-effort SQLite introspection, but exact counts depend on\n   the available columns.\n7. **Mixing generation and delivery.** Keep the digest generator independent from\n   platform-specific webhook or bot code; this makes testing and migration easier.\n\n## What this skill is not\n\n- Not a session search tool. Use your platform's session search or transcript\n  browser when you need a specific conversation.\n- Not a full transcript exporter. It intentionally summarizes titles, counts,\n  and TODO-like lines only.\n- Not a replacement for session browsing. It helps decide what to inspect next.\n- Not a complete scheduler dashboard. It reads output files and status markers;\n  it does not own or run the scheduler.\n- Not a secrets scanner. It reduces verbosity, but it cannot guarantee that the\n  source data is safe to send to a messaging platform.\n\n## Reference files\n\n- `references\u002Fdigest-format.md` — section contract, output variants, daily and\n  weekly examples.\n- `references\u002Fdata-sources.md` — source configuration, expected formats, and\n  schema examples.\n- `templates\u002Fdigest-template.md` — blank Markdown template for agent-filled or\n  manually curated digests.\n- `scripts\u002Fsummarize.py` — stdlib CLI for generating, configuring, and\n  bootstrapping summary files.\n\n## Verification checklist\n\n- [ ] `python scripts\u002Fsummarize.py --help` shows `generate`, `config`, and `init`.\n- [ ] `python scripts\u002Fsummarize.py generate --since 24h` works without sources\n      and emits template mode output.\n- [ ] A mock run with sources includes only events inside the time window, except\n      explicitly overdue cron jobs.\n- [ ] `--sections` excludes omitted sections from Markdown, JSON, and text.\n- [ ] `--format json` returns parseable JSON.\n- [ ] The first scheduled output has been reviewed for secrets and excessive\n      length before connecting it to a messaging platform.\n",{"name":5,"license":14,"metadata":23,"description":7},{"tags":24,"author":9,"version":33,"platforms":34,"related_skills":38},[25,26,27,28,29,30,31,32],"summary","digest","cron","sessions","activity","cross-session","notification","scheduled","1.0.0",[35,36,37],"linux","macos","windows",[39,40],"decision-log","news-monitoring","main","e943e3285cd03c44b2c762a9a52328e3d16444b1","productivity\u002Fscheduled-summary",22,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills","https:\u002F\u002Fhermes-agent.nousresearch.com","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin","Accounting\u002FFP&A\u002FM&A\u002FPERE guy by day, AI\u002Fself-host\u002Fprogramming hobbyist by night. \r\n\r\nPassionate in solving practical business issues.","2026-11-13 19:46:18",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add moonlight-lupin\u002Fagent-skills --skill scheduled-summary",{"tool":56,"command":57},"bunx","bunx skills add moonlight-lupin\u002Fagent-skills --skill scheduled-summary",{"tool":59,"command":60},"pnpm","pnpm dlx skills add moonlight-lupin\u002Fagent-skills --skill scheduled-summary","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Fscheduled-summary\u002FSKILL.md",true,[64,70,74,80,84],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fdata-sources.md","REFERENCE","参考文档",6018,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Fscheduled-summary\u002Freferences\u002Fdata-sources.md",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fdigest-format.md",5654,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Fscheduled-summary\u002Freferences\u002Fdigest-format.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fsummarize.py","SCRIPT","脚本",32255,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Fscheduled-summary\u002Fscripts\u002Fsummarize.py",{"path":81,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":82,"sourceHtmlUrl":83},"templates\u002Fdigest-template.md",710,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Fscheduled-summary\u002Ftemplates\u002Fdigest-template.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"tests\u002Ftest_summarize.py",10322,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Fscheduled-summary\u002Ftests\u002Ftest_summarize.py",[89,96,103,110,117,124],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M78ATNRV7RYQ8M314V0QZX18","website-scraping","Generic playbook for extracting structured data from any website — hotel prices, flight fares, e-commerce listings, real estate, jobs, competitor product catalogues, anything where the goal is to turn one or more URLs into clean records on disk. Use this skill whenever the user mentions scraping, harvesting, extracting, or pulling data from a website; names a specific site or competitor they want data from; asks how to handle JavaScript-rendered pages, Cloudflare blocks, bot detection, Turnstile challenges, or Playwright; wants to monitor prices over time; needs to automate a copy-paste research task; or says things like \"just get the data from X\" or \"I need a script that grabs N from site Y\". Covers recon, picking the lightest extraction tool that works, surviving anti-bot defences, and writing clean JSONL output with a run manifest. Scope is scraping only — landing data in a database, scheduling, and downstream pipeline work are explicitly out of scope and live in other tools.","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fweb-scraping\u002Fwebsite-scraping\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M78ATK9XGEKSH3QRN7P2MEER","greet","Greets a named person warmly.","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fclaude_plugin_sample\u002Fskills\u002Fgreet\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M78ATEAQB5CK2D4MKPCW4YHQ","skill-quality-review","Use when auditing or reviewing skill quality — batch checks across a library, deep per-skill grep methodology, usage stats, efficacy testing, or fix planning. Single consolidated home for the writing-for-agents review framework and the 3-surface review methodology.","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fskill-quality-review\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":18},"01M78AT58EM57023QSC79S8R6D","people-enrichment","Use when the user has a list of names or companies and wants their job, employer, work history, LinkedIn URLs or company profiles looked up, or wants to find people or companies matching criteria — trigger on phrases like \"enrich these contacts\", \"find their LinkedIn\", \"look up these people\", \"who works at X\", \"find directors at Y\", \"enrich these companies\", or \"get firmographics for\". Enrich and search People Data Labs (PDL) Person and Company data, writing results to .xlsx. Five operations: enrich named PEOPLE into a profile, employment history and LinkedIn URL; IDENTIFY an ambiguous person as several scored candidates; SEARCH people by criteria (company, title, location); enrich COMPANIES into firmographics (industry, size, employees, HQ, founded, LinkedIn); and SEARCH companies by criteria. Do not scrape LinkedIn directly — this uses a licensed data aggregator (PDL) instead, for legal and reliability reasons.","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fresearch\u002Fpeople-enrichment\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":18},"01M78AT0AZJ7WFY73766NBA1EC","notebooklm-mode","Source-grounded research pipeline inspired by NotebookLM. Collect verbatim source extracts into a temporary workspace, then answer questions and create deliverables grounded in those sources. Two grounding modes: strict (vault-only) and augmented (vault + labeled [background] knowledge). Trigger when the user asks to research a topic from sources, wants NotebookLM-style grounded answers, asks to build a resource vault, or says \"notebooklm mode\".","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fresearch\u002Fnotebooklm-mode\u002FSKILL.md",[],[],{"skillNo":125,"name":40,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":18},"01M78ASTJVZ9G5JY6GM40SF909","Use when a topic or news stream needs recurring monitoring — cover it with web search, multi-language sources, digest formatting, and automated delivery via Hermes cron jobs. Covers search strategy, source selection, Chinese-language platforms, and digest templates.","https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fresearch\u002Fnews-monitoring\u002FSKILL.md",[],[]]