[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78AMWG4V72ERKNQDF4J5YK6":3,"skill-same:01M78AMWG4V72ERKNQDF4J5YK6":75},{"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":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M78AMWG4V72ERKNQDF4J5YK6","curator",null,"Use when ingesting memory into the wiki, running wiki_curator.py (run\u002Freport\u002Fvalidate\u002Flint\u002Fsearch), or linting wiki structure.","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\u002Fplugins\u002Flumen\u002Fskills\u002Fcurator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: curator\ndescription: \"Use when ingesting memory into the wiki, running wiki_curator.py (run\u002Freport\u002Fvalidate\u002Flint\u002Fsearch), or linting wiki structure.\"\nlicense: MIT\nmetadata:\n  version: 0.2.0\n  author: moonlight-lupin\n  platforms: [linux, macos, windows]\n  tags: [wiki, curator, knowledge-base, okf]\n  hermes:\n    category: research\n    related_skills: [obsidian, arxiv]\n---\n\n# Wiki Curator\n\n## Overview\n\nThe curator is the operational half of Lumen. It turns memory-source records into conservative Markdown wiki updates, and it lints the wiki for structural decay. It never calls providers, never deletes pages, and never overwrites operator-confirmed facts.\n\nPair it with `lumen:wiki` for methodology (OKF frontmatter, ingest\u002Fquery\u002Flint procedures). This skill is the CLI and adapter layer.\n\n## When to Use\n\nUse this skill when the user wants to:\n\n- Ingest recent memory into the wiki (`run`) or preview that ingest (`report`)\n- Lint or validate wiki structure\n- Search wiki pages by keyword, alias, or tag\n- Configure which memory source the curator reads\n\n## Wiki Location\n\nResolve the wiki path in this order:\n\n1. `--wiki` CLI override\n2. `paths.wiki_path` in plugin config (`shared\u002Fconfig\u002Flumen.yaml` or `--config`)\n3. `$WIKI_PATH` environment variable\n4. Default `~\u002Fwiki`\n\n## Plugin config (`lumen.yaml`)\n\nDefault file: `\u003Cplugin>\u002Fshared\u002Fconfig\u002Flumen.yaml`. Override with `--config` or `LUMEN_CONFIG`.\n\n```yaml\npaths:\n  wiki_path: ~\u002Fwiki          # null → $WIKI_PATH → ~\u002Fwiki\n\ncurator:\n  timezone: Asia\u002FSingapore\n  max_write_pages: 20        # 0 or negative disables the cap\n  memory_source: sessions    # sessions | auto | json-file | mnemosyne | none\n```\n\n`auto` prefers `sessions` when a readable Hermes `state.db` exists (the conversation history is the ground truth; Mnemosyne holds derived notes), then Mnemosyne when `hermes` is on `PATH`, falling back to the json-file adapter if the export fails. `none` disables ingest (file-only lint\u002Fsearch still work).\n\n## Adapter layer\n\n`${HERMES_SKILL_DIR}\u002Fscripts\u002Fadapters.py` is the read-only memory boundary. Adapters emit `SourceItem` records (`source_id`, `source_kind`, `title`, `text`, `timestamp`, `tags`, `people`, `entities`, `projects`, `raw`). Nothing writes back to a memory store.\n\n| Adapter | Source | Notes |\n|---|---|---|\n| `sessions` | Hermes `state.db` (conversation history) | Read-only SQLite; user messages paired with the first assistant reply; gateway-origin JSON envelopes stripped. Default source. |\n| `json-file` | `\u003Cwiki>\u002F.knowledge\u002Fmemory.json` | Tolerant record shapes (`records` map or list). Missing file → `[]`. |\n| `mnemosyne` | `hermes mnemosyne export --output \u003Ctmp>` | Parses `working_memory` + `episodic_memory`. Subprocess failure → `[]`. |\n| `none` | empty | Explicit opt-out. |\n\n**Record fields.** `people` \u002F `entities` \u002F `projects` take a list for several names; a plain string is one name (`\"Acme, Inc.\"` stays one entity). `tags` may be a list or a comma-separated string. Records without an `id` get a content-derived id (`memory_\u003Cdigest>` of timestamp and text), so reordering or inserting records does not re-ingest them. When a record names no people\u002Fentities\u002Fprojects, capitalised words in its title\u002Ftext are used as entity hints; a sentence-initial word (\"Met with…\", \"Sent…\") only counts if the same word also appears capitalised mid-sentence, and the `Untitled` placeholder title is never scanned.\n\n**Extension point (`generic-json`).** Any provider that can emit the json-file `memory.json` shape (a `records` mapping or a list of record objects, with tolerant people\u002Fentities\u002Fprojects keys) can be dropped in as `\u003Cwiki>\u002F.knowledge\u002Fmemory.json` and selected with `memory_source: json-file`. A dedicated `generic-json` adapter that takes an arbitrary export path is the documented next step; do not add provider-specific imports.\n\n## CLI\n\nScript: `${HERMES_SKILL_DIR}\u002Fscripts\u002Fwiki_curator.py` (Hermes substitutes `${HERMES_SKILL_DIR}` with this skill's directory, so the path works from any cwd). Run with system `python3` (stdlib + PyYAML).\n\n```bash\nCURATOR=\"${HERMES_SKILL_DIR}\u002Fscripts\u002Fwiki_curator.py\"\n\npython3 \"$CURATOR\" run --since 24h          # ingest (writes wiki pages)\npython3 \"$CURATOR\" run --since 24h --dry-run\npython3 \"$CURATOR\" report --since 7d        # planned changes, no writes\npython3 \"$CURATOR\" validate                 # lint; exit 1 on ERROR\npython3 \"$CURATOR\" lint                     # same checks\npython3 \"$CURATOR\" lint --summary           # counts only\npython3 \"$CURATOR\" search \"Acme\" --format json --limit 10\npython3 \"$CURATOR\" search \"Acme\" --format text --wiki ~\u002Fwiki\n```\n\nGlobal flags: `--config \u003Clumen.yaml>`, `--wiki \u003Cpath>` (also accepted after the subcommand).\n\n`--since` accepts `90m`, `24h`, `7d`, `2w`; anything else is a usage error (exit 2). Runtime errors such as a wiki subdirectory that is a symlink out of the wiki print `error: …` and exit non-zero.\n\n**Read-only vs mutating:** `lint`, `validate`, `report`, and `search` are read-only. `run` writes. `run --dry-run` previews. The curator never deletes pages.\n\n## Conservative write policy\n\n- Create or update people \u002F project \u002F entity \u002F daily pages from source items only\n- Preserve operator-confirmed facts; append observations with `[source: id]`\n- Refresh only the `\u003C!-- lumen:auto:start -->` … `\u003C!-- lumen:auto:end -->` block of `index.md` and `overview.md` (hand-written content outside the markers is preserved; a file without markers gets a block appended); append `log.md`\n- Record text, titles and names are flattened to one line with `[source:` \u002F `[[` \u002F leading `#` neutralised, so memory content cannot forge sections, source markers or links\n- Never overwrite an existing page `title` or `created` value\n- Skip an existing page whose YAML frontmatter does not parse: it is left byte-for-byte unchanged, a `skip` line naming the page appears in the run report (and a warning on stderr), and the source is retried on the next run once the page is fixed\n- Rewritten files keep their existing permission bits; new files get `0666 & ~umask`\n- Cap source items per run at `curator.max_write_pages` (default 20; 0 or negative disables the cap)\n- Backup the wiki tree to `\u003Cwiki>\u002F.lumen\u002Fbackup\u002F\u003Ctimestamp>\u002F` before large batches (>5 items). `.lumen\u002F` is excluded from index and overview regeneration.\n\n## OKF v0.2\n\nEvery curated `.md` page needs parseable YAML frontmatter with a non-empty `type` field. See `lumen:wiki` for the full schema. The curator assigns `seq` on create and preserves `aliases` \u002F `relations`.\n\n## Lint checks\n\n- Missing or malformed frontmatter (ERROR)\n- Missing `type` (ERROR)\n- Broken `[[wikilinks]]` (WARN)\n- Duplicate titles (WARN)\n- Pages absent from `index.md` (WARN)\n- Orphans with no inbound links (INFO)\n- Stale pages (updated >90 days) (INFO)\n\n## File naming\n\nLowercase hyphenated ASCII slugs: `acme-logistics.md`. Accents are folded (`Zoë` → `zoe.md`); a name with no ASCII letters or digits (`张伟`) gets `untitled-\u003Cfirst 8 hex of sha256(name)>.md`, stable across runs and distinct per name. Wikilinks use the page title, so `[[张伟]]` resolves. Avoid generic names like `notes.md`.\n\n## Common pitfalls\n\n1. Skipping orientation (`purpose.md`, `SCHEMA.md`, `index.md`, recent `log.md`)\n2. Creating duplicate entity pages without searching first\n3. Dumping raw notes as curated knowledge\n4. No frontmatter \u002F missing `type`\n5. Unlinked pages that lint later reports as orphans\n\n## Verification checklist\n\n- [ ] Wiki path resolved from plugin config, then `$WIKI_PATH`, then `~\u002Fwiki`\n- [ ] `memory_source` matches the host install (`auto` \u002F `json-file` \u002F `mnemosyne` \u002F `none`)\n- [ ] `run --dry-run` reviewed before a mutating `run`\n- [ ] Lint reports file paths and severity\n- [ ] Query answers cite wiki pages\n","# Wiki Curator\n\n## Overview\n\nThe curator is the operational half of Lumen. It turns memory-source records into conservative Markdown wiki updates, and it lints the wiki for structural decay. It never calls providers, never deletes pages, and never overwrites operator-confirmed facts.\n\nPair it with `lumen:wiki` for methodology (OKF frontmatter, ingest\u002Fquery\u002Flint procedures). This skill is the CLI and adapter layer.\n\n## When to Use\n\nUse this skill when the user wants to:\n\n- Ingest recent memory into the wiki (`run`) or preview that ingest (`report`)\n- Lint or validate wiki structure\n- Search wiki pages by keyword, alias, or tag\n- Configure which memory source the curator reads\n\n## Wiki Location\n\nResolve the wiki path in this order:\n\n1. `--wiki` CLI override\n2. `paths.wiki_path` in plugin config (`shared\u002Fconfig\u002Flumen.yaml` or `--config`)\n3. `$WIKI_PATH` environment variable\n4. Default `~\u002Fwiki`\n\n## Plugin config (`lumen.yaml`)\n\nDefault file: `\u003Cplugin>\u002Fshared\u002Fconfig\u002Flumen.yaml`. Override with `--config` or `LUMEN_CONFIG`.\n\n```yaml\npaths:\n  wiki_path: ~\u002Fwiki          # null → $WIKI_PATH → ~\u002Fwiki\n\ncurator:\n  timezone: Asia\u002FSingapore\n  max_write_pages: 20        # 0 or negative disables the cap\n  memory_source: sessions    # sessions | auto | json-file | mnemosyne | none\n```\n\n`auto` prefers `sessions` when a readable Hermes `state.db` exists (the conversation history is the ground truth; Mnemosyne holds derived notes), then Mnemosyne when `hermes` is on `PATH`, falling back to the json-file adapter if the export fails. `none` disables ingest (file-only lint\u002Fsearch still work).\n\n## Adapter layer\n\n`${HERMES_SKILL_DIR}\u002Fscripts\u002Fadapters.py` is the read-only memory boundary. Adapters emit `SourceItem` records (`source_id`, `source_kind`, `title`, `text`, `timestamp`, `tags`, `people`, `entities`, `projects`, `raw`). Nothing writes back to a memory store.\n\n| Adapter | Source | Notes |\n|---|---|---|\n| `sessions` | Hermes `state.db` (conversation history) | Read-only SQLite; user messages paired with the first assistant reply; gateway-origin JSON envelopes stripped. Default source. |\n| `json-file` | `\u003Cwiki>\u002F.knowledge\u002Fmemory.json` | Tolerant record shapes (`records` map or list). Missing file → `[]`. |\n| `mnemosyne` | `hermes mnemosyne export --output \u003Ctmp>` | Parses `working_memory` + `episodic_memory`. Subprocess failure → `[]`. |\n| `none` | empty | Explicit opt-out. |\n\n**Record fields.** `people` \u002F `entities` \u002F `projects` take a list for several names; a plain string is one name (`\"Acme, Inc.\"` stays one entity). `tags` may be a list or a comma-separated string. Records without an `id` get a content-derived id (`memory_\u003Cdigest>` of timestamp and text), so reordering or inserting records does not re-ingest them. When a record names no people\u002Fentities\u002Fprojects, capitalised words in its title\u002Ftext are used as entity hints; a sentence-initial word (\"Met with…\", \"Sent…\") only counts if the same word also appears capitalised mid-sentence, and the `Untitled` placeholder title is never scanned.\n\n**Extension point (`generic-json`).** Any provider that can emit the json-file `memory.json` shape (a `records` mapping or a list of record objects, with tolerant people\u002Fentities\u002Fprojects keys) can be dropped in as `\u003Cwiki>\u002F.knowledge\u002Fmemory.json` and selected with `memory_source: json-file`. A dedicated `generic-json` adapter that takes an arbitrary export path is the documented next step; do not add provider-specific imports.\n\n## CLI\n\nScript: `${HERMES_SKILL_DIR}\u002Fscripts\u002Fwiki_curator.py` (Hermes substitutes `${HERMES_SKILL_DIR}` with this skill's directory, so the path works from any cwd). Run with system `python3` (stdlib + PyYAML).\n\n```bash\nCURATOR=\"${HERMES_SKILL_DIR}\u002Fscripts\u002Fwiki_curator.py\"\n\npython3 \"$CURATOR\" run --since 24h          # ingest (writes wiki pages)\npython3 \"$CURATOR\" run --since 24h --dry-run\npython3 \"$CURATOR\" report --since 7d        # planned changes, no writes\npython3 \"$CURATOR\" validate                 # lint; exit 1 on ERROR\npython3 \"$CURATOR\" lint                     # same checks\npython3 \"$CURATOR\" lint --summary           # counts only\npython3 \"$CURATOR\" search \"Acme\" --format json --limit 10\npython3 \"$CURATOR\" search \"Acme\" --format text --wiki ~\u002Fwiki\n```\n\nGlobal flags: `--config \u003Clumen.yaml>`, `--wiki \u003Cpath>` (also accepted after the subcommand).\n\n`--since` accepts `90m`, `24h`, `7d`, `2w`; anything else is a usage error (exit 2). Runtime errors such as a wiki subdirectory that is a symlink out of the wiki print `error: …` and exit non-zero.\n\n**Read-only vs mutating:** `lint`, `validate`, `report`, and `search` are read-only. `run` writes. `run --dry-run` previews. The curator never deletes pages.\n\n## Conservative write policy\n\n- Create or update people \u002F project \u002F entity \u002F daily pages from source items only\n- Preserve operator-confirmed facts; append observations with `[source: id]`\n- Refresh only the `\u003C!-- lumen:auto:start -->` … `\u003C!-- lumen:auto:end -->` block of `index.md` and `overview.md` (hand-written content outside the markers is preserved; a file without markers gets a block appended); append `log.md`\n- Record text, titles and names are flattened to one line with `[source:` \u002F `[[` \u002F leading `#` neutralised, so memory content cannot forge sections, source markers or links\n- Never overwrite an existing page `title` or `created` value\n- Skip an existing page whose YAML frontmatter does not parse: it is left byte-for-byte unchanged, a `skip` line naming the page appears in the run report (and a warning on stderr), and the source is retried on the next run once the page is fixed\n- Rewritten files keep their existing permission bits; new files get `0666 & ~umask`\n- Cap source items per run at `curator.max_write_pages` (default 20; 0 or negative disables the cap)\n- Backup the wiki tree to `\u003Cwiki>\u002F.lumen\u002Fbackup\u002F\u003Ctimestamp>\u002F` before large batches (>5 items). `.lumen\u002F` is excluded from index and overview regeneration.\n\n## OKF v0.2\n\nEvery curated `.md` page needs parseable YAML frontmatter with a non-empty `type` field. See `lumen:wiki` for the full schema. The curator assigns `seq` on create and preserves `aliases` \u002F `relations`.\n\n## Lint checks\n\n- Missing or malformed frontmatter (ERROR)\n- Missing `type` (ERROR)\n- Broken `[[wikilinks]]` (WARN)\n- Duplicate titles (WARN)\n- Pages absent from `index.md` (WARN)\n- Orphans with no inbound links (INFO)\n- Stale pages (updated >90 days) (INFO)\n\n## File naming\n\nLowercase hyphenated ASCII slugs: `acme-logistics.md`. Accents are folded (`Zoë` → `zoe.md`); a name with no ASCII letters or digits (`张伟`) gets `untitled-\u003Cfirst 8 hex of sha256(name)>.md`, stable across runs and distinct per name. Wikilinks use the page title, so `[[张伟]]` resolves. Avoid generic names like `notes.md`.\n\n## Common pitfalls\n\n1. Skipping orientation (`purpose.md`, `SCHEMA.md`, `index.md`, recent `log.md`)\n2. Creating duplicate entity pages without searching first\n3. Dumping raw notes as curated knowledge\n4. No frontmatter \u002F missing `type`\n5. Unlinked pages that lint later reports as orphans\n\n## Verification checklist\n\n- [ ] Wiki path resolved from plugin config, then `$WIKI_PATH`, then `~\u002Fwiki`\n- [ ] `memory_source` matches the host install (`auto` \u002F `json-file` \u002F `mnemosyne` \u002F `none`)\n- [ ] `run --dry-run` reviewed before a mutating `run`\n- [ ] Lint reports file paths and severity\n- [ ] Query answers cite wiki pages\n",{"name":5,"license":14,"metadata":23,"description":7},{"tags":24,"author":9,"hermes":28,"version":33,"platforms":34},[25,5,26,27],"wiki","knowledge-base","okf",{"category":29,"related_skills":30},"research",[31,32],"obsidian","arxiv","0.2.0",[35,36,37],"linux","macos","windows","main","e943e3285cd03c44b2c762a9a52328e3d16444b1","plugins\u002Flumen\u002Fskills\u002Fcurator",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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add moonlight-lupin\u002Fagent-skills --skill curator",{"tool":53,"command":54},"bunx","bunx skills add moonlight-lupin\u002Fagent-skills --skill curator",{"tool":56,"command":57},"pnpm","pnpm dlx skills add moonlight-lupin\u002Fagent-skills --skill curator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fplugins\u002Flumen\u002Fskills\u002Fcurator\u002FSKILL.md",true,[61,67,71],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fadapters.py","SCRIPT","脚本",28115,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fplugins\u002Flumen\u002Fskills\u002Fcurator\u002Fscripts\u002Fadapters.py",{"path":68,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fconfig_loader.py",8961,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fplugins\u002Flumen\u002Fskills\u002Fcurator\u002Fscripts\u002Fconfig_loader.py",{"path":72,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fwiki_curator.py",78948,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fplugins\u002Flumen\u002Fskills\u002Fcurator\u002Fscripts\u002Fwiki_curator.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":18},"01M78ASTJVZ9G5JY6GM40SF909","news-monitoring","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",[],[]]