[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78APYNK0M5WXPRPD4K1D80R":3,"skill-same:01M78APYNK0M5WXPRPD4K1D80R":68},{"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":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":40,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M78APYNK0M5WXPRPD4K1D80R","receipt-compiler",null,"Use when compiling phone-camera photos of receipts into an A4 PDF expense-claim pack — straighten, B&W scan look, optional cover\u002Fnumbering\u002Fcaptions.","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\u002Freceipt-compiler\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: receipt-compiler\ndescription: \"Use when compiling phone-camera photos of receipts into an A4 PDF expense-claim pack — straighten, B&W scan look, optional cover\u002Fnumbering\u002Fcaptions.\"\nlicense: MIT\nmetadata:\n  version: 1.0.0\n  author: moonlight-lupin\n  platforms: [linux]\n  tags: [receipts, expense-claims, pdf, ocr, scanify]\n  related_skills: [pdf, document-toolkit]\n---\n\n# Receipt Compiler\n\n## Overview\n\nReceipt Compiler turns a folder of phone-camera receipt photos into one A4 PDF that looks like a\nphotocopied expense-claim pack: each receipt is straightened (perspective warp,\ndeskew), converted to a B&W \"scanned\" look, tiled on A4 with uniform visual scale,\nnumbered, and summarised on an optional cover page.\n\nFour subcommands with an enforced **confirmation gate**:\n\n1. `scan` — straighten + scanify + OCR each photo → `manifest.json`\n2. `review` — print the extracted expense table\n3. `confirm` — stamp user approval + bind the reviewed data (digest)\n4. `pack` — build the A4 PDF (refuses to run until `confirm` has run)\n\n## When to Use\n\n- \"Compile my receipts into a PDF for expense claim\"\n- \"Make a claim pack from these receipt photos\"\n- \"Straighten and B&W these receipts and line them up on A4\"\n- Not for: scanning via flatbed scanner, or PDFs of invoices (use `pdf` skill).\n\n## Prerequisites\n\n```\npip install opencv-python-headless pillow pillow-heif pytesseract reportlab numpy\n# PyMuPDF is needed only to run the self-test (tests\u002F), not the script itself\n```\nPlus system `tesseract-ocr` on PATH. Check with `tesseract --version`.\n\n## Workflow (agent must follow the gate)\n\n### Step 1 — scan\n\n```bash\npython3 ~\u002F.hermes\u002Fskills\u002Fproductivity\u002Freceipt-compiler\u002Fscripts\u002Freceipt_compiler.py \\\n    scan \u003Cphotos_dir> -o \u003Cworkdir> [--mode bw|photo]\n```\n\nDefault `--mode bw` gives the photocopy look the user asked for. Use `--mode photo`\nfor grayscale. Completion criterion: manifest exists with one entry per photo;\n`ocr_confidence` and `needs_review` flags set.\n\n### Step 2 — review + confirm (MANDATORY, user in the loop)\n\n```bash\npython3 ...\u002Freceipt_compiler.py review \u003Cworkdir>\n# ... apply any corrections to manifest.json, THEN re-run review so the user\n# ... sees the corrected table ...\npython3 ...\u002Freceipt_compiler.py review \u003Cworkdir>\n# ... after the user approves the corrected table ...\npython3 ...\u002Freceipt_compiler.py confirm \u003Cworkdir>\n```\n\nPresent the printed table to the user in chat. Ask:\n1. Are the extracted dates\u002Fmerchants\u002Famounts right? Fix `manifest.json` fields.\n2. Optional requirements — ask every time, do not assume:\n   - cover page (with claimant\u002Fperiod\u002Fnotes)\n   - per-receipt numbering badges\n   - per-receipt captions (date · merchant · amount)\n   - currency symbol on totals\n3. Exclusions — any receipt to drop (`\"include\": false`)?\n4. Purpose\u002Fnotes text for the cover.\n\nOnly after the user approves: run `confirm \u003Cworkdir>`. This sets\n`confirmed: true` AND binds a `review_digest` of the exact reviewed fields at\napproval time. Any edit after `confirm` (dates, amounts, currency, inclusion)\nmakes `pack` refuse until you re-run `confirm` — which means showing the user\nthe changed table again. There is no bypass flag. Apply user corrections to\n`manifest.json` BEFORE running `confirm`.\n\n### Step 3 — pack\n\n```bash\npython3 ...\u002Freceipt_compiler.py pack \u003Cworkdir> -o claim.pdf \\\n    [--cover --number --captions] \\\n    --title \"Expense Claim — \u003Cpurpose>\" --claimant \"MH\" --period \"...\" --notes \"...\"\n```\n\nCompletion criterion: PDF exists, page count reported in JSON output.\nThen send the PDF to the user as a document\u002Ffile on the active channel.\n\n## Layout rules (how receipts line up)\n\n- A4 portrait, 15 mm margins, 5 mm gaps.\n- Very tall receipts (aspect ≥ 2.2) are packed 3-per-row full-height;\n  normal receipts 2-per-row, capped at 52% of content height (≈47% of the\n  page). Scale is per-cell\n  (each receipt fills its cell); rows with fewer receipts get wider cells.\n- Every image is scaled to preserve aspect ratio — no distortion, no cropping.\n- Receipts flow across pages; 30+ receipts pack fine.\n- Tall receipts print before normal ones; re-order via the manifest if needed.\n\n## Common Pitfalls\n\n1. **Skipping the confirmation gate** — `pack` hard-fails on `confirmed: false`,\n   non-boolean confirmation values, and post-confirmation edits (digest check).\n   There is no bypass flag; the user must see the table first.\n2. **Dark\u002Fshadowed photos** — the 2\u002F98 percentile stretch handles most; if OCR\n   confidence is \u003C 55, or no amount was extracted, the entry is flagged\n   `needs_review`; surface these to the user.\n3. **Perspective warp failure** — glossy\u002Fwrinkled receipts may not produce a clean\n   quad; the script falls back to small-angle deskew of the full frame. Check\n   `method` in the manifest; if `deskew` on a receipt that clearly needs\n   cropping, fix the crop manually with PIL or accept the framing.\n4. **HEIC photos** — iPhone photos arrive as .heic; `pillow-heif` handles them if\n   installed. If missing, ask the user for JPGs or install `pillow-heif`.\n5. **Multiple currencies** — totals are grouped per currency (review output and\n   cover page print one line per currency, no combined total). For a cleaner\n   claim, keep one currency per pack; never zero or edit valid amounts to force\n   a combined total.\n6. **Long descriptions in cover table** — descriptions truncate at 70 chars; keep\n   cover notes short or put detail in `notes`.\n\n## Verification Checklist\n\n- [ ] `scan` produced manifest.json with an entry per photo\n- [ ] `review` table shown to user; corrections applied to manifest\n- [ ] Optional requirements asked each time (cover\u002Fnumbering\u002Fcaptions)\n- [ ] `confirm` run only after user approval (never hand-edit `confirmed`)\n- [ ] `pack` output PDF exists, page count matches expectation\n- [ ] PDF sent to the user with the correct output path","# Receipt Compiler\n\n## Overview\n\nReceipt Compiler turns a folder of phone-camera receipt photos into one A4 PDF that looks like a\nphotocopied expense-claim pack: each receipt is straightened (perspective warp,\ndeskew), converted to a B&W \"scanned\" look, tiled on A4 with uniform visual scale,\nnumbered, and summarised on an optional cover page.\n\nFour subcommands with an enforced **confirmation gate**:\n\n1. `scan` — straighten + scanify + OCR each photo → `manifest.json`\n2. `review` — print the extracted expense table\n3. `confirm` — stamp user approval + bind the reviewed data (digest)\n4. `pack` — build the A4 PDF (refuses to run until `confirm` has run)\n\n## When to Use\n\n- \"Compile my receipts into a PDF for expense claim\"\n- \"Make a claim pack from these receipt photos\"\n- \"Straighten and B&W these receipts and line them up on A4\"\n- Not for: scanning via flatbed scanner, or PDFs of invoices (use `pdf` skill).\n\n## Prerequisites\n\n```\npip install opencv-python-headless pillow pillow-heif pytesseract reportlab numpy\n# PyMuPDF is needed only to run the self-test (tests\u002F), not the script itself\n```\nPlus system `tesseract-ocr` on PATH. Check with `tesseract --version`.\n\n## Workflow (agent must follow the gate)\n\n### Step 1 — scan\n\n```bash\npython3 ~\u002F.hermes\u002Fskills\u002Fproductivity\u002Freceipt-compiler\u002Fscripts\u002Freceipt_compiler.py \\\n    scan \u003Cphotos_dir> -o \u003Cworkdir> [--mode bw|photo]\n```\n\nDefault `--mode bw` gives the photocopy look the user asked for. Use `--mode photo`\nfor grayscale. Completion criterion: manifest exists with one entry per photo;\n`ocr_confidence` and `needs_review` flags set.\n\n### Step 2 — review + confirm (MANDATORY, user in the loop)\n\n```bash\npython3 ...\u002Freceipt_compiler.py review \u003Cworkdir>\n# ... apply any corrections to manifest.json, THEN re-run review so the user\n# ... sees the corrected table ...\npython3 ...\u002Freceipt_compiler.py review \u003Cworkdir>\n# ... after the user approves the corrected table ...\npython3 ...\u002Freceipt_compiler.py confirm \u003Cworkdir>\n```\n\nPresent the printed table to the user in chat. Ask:\n1. Are the extracted dates\u002Fmerchants\u002Famounts right? Fix `manifest.json` fields.\n2. Optional requirements — ask every time, do not assume:\n   - cover page (with claimant\u002Fperiod\u002Fnotes)\n   - per-receipt numbering badges\n   - per-receipt captions (date · merchant · amount)\n   - currency symbol on totals\n3. Exclusions — any receipt to drop (`\"include\": false`)?\n4. Purpose\u002Fnotes text for the cover.\n\nOnly after the user approves: run `confirm \u003Cworkdir>`. This sets\n`confirmed: true` AND binds a `review_digest` of the exact reviewed fields at\napproval time. Any edit after `confirm` (dates, amounts, currency, inclusion)\nmakes `pack` refuse until you re-run `confirm` — which means showing the user\nthe changed table again. There is no bypass flag. Apply user corrections to\n`manifest.json` BEFORE running `confirm`.\n\n### Step 3 — pack\n\n```bash\npython3 ...\u002Freceipt_compiler.py pack \u003Cworkdir> -o claim.pdf \\\n    [--cover --number --captions] \\\n    --title \"Expense Claim — \u003Cpurpose>\" --claimant \"MH\" --period \"...\" --notes \"...\"\n```\n\nCompletion criterion: PDF exists, page count reported in JSON output.\nThen send the PDF to the user as a document\u002Ffile on the active channel.\n\n## Layout rules (how receipts line up)\n\n- A4 portrait, 15 mm margins, 5 mm gaps.\n- Very tall receipts (aspect ≥ 2.2) are packed 3-per-row full-height;\n  normal receipts 2-per-row, capped at 52% of content height (≈47% of the\n  page). Scale is per-cell\n  (each receipt fills its cell); rows with fewer receipts get wider cells.\n- Every image is scaled to preserve aspect ratio — no distortion, no cropping.\n- Receipts flow across pages; 30+ receipts pack fine.\n- Tall receipts print before normal ones; re-order via the manifest if needed.\n\n## Common Pitfalls\n\n1. **Skipping the confirmation gate** — `pack` hard-fails on `confirmed: false`,\n   non-boolean confirmation values, and post-confirmation edits (digest check).\n   There is no bypass flag; the user must see the table first.\n2. **Dark\u002Fshadowed photos** — the 2\u002F98 percentile stretch handles most; if OCR\n   confidence is \u003C 55, or no amount was extracted, the entry is flagged\n   `needs_review`; surface these to the user.\n3. **Perspective warp failure** — glossy\u002Fwrinkled receipts may not produce a clean\n   quad; the script falls back to small-angle deskew of the full frame. Check\n   `method` in the manifest; if `deskew` on a receipt that clearly needs\n   cropping, fix the crop manually with PIL or accept the framing.\n4. **HEIC photos** — iPhone photos arrive as .heic; `pillow-heif` handles them if\n   installed. If missing, ask the user for JPGs or install `pillow-heif`.\n5. **Multiple currencies** — totals are grouped per currency (review output and\n   cover page print one line per currency, no combined total). For a cleaner\n   claim, keep one currency per pack; never zero or edit valid amounts to force\n   a combined total.\n6. **Long descriptions in cover table** — descriptions truncate at 70 chars; keep\n   cover notes short or put detail in `notes`.\n\n## Verification Checklist\n\n- [ ] `scan` produced manifest.json with an entry per photo\n- [ ] `review` table shown to user; corrections applied to manifest\n- [ ] Optional requirements asked each time (cover\u002Fnumbering\u002Fcaptions)\n- [ ] `confirm` run only after user approval (never hand-edit `confirmed`)\n- [ ] `pack` output PDF exists, page count matches expectation\n- [ ] PDF sent to the user with the correct output path",{"name":5,"license":14,"metadata":23,"description":7},{"tags":24,"author":9,"version":30,"platforms":31,"related_skills":33},[25,26,27,28,29],"receipts","expense-claims","pdf","ocr","scanify","1.0.0",[32],"linux",[27,34],"document-toolkit","main","e943e3285cd03c44b2c762a9a52328e3d16444b1","productivity\u002Freceipt-compiler",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":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add moonlight-lupin\u002Fagent-skills --skill receipt-compiler",{"tool":50,"command":51},"bunx","bunx skills add moonlight-lupin\u002Fagent-skills --skill receipt-compiler",{"tool":53,"command":54},"pnpm","pnpm dlx skills add moonlight-lupin\u002Fagent-skills --skill receipt-compiler","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Freceipt-compiler\u002FSKILL.md",true,[58,64],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Freceipt_compiler.py","SCRIPT","脚本",41181,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Freceipt-compiler\u002Fscripts\u002Freceipt_compiler.py",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"tests\u002Freceipt_compiler_selftest.py",17541,"https:\u002F\u002Fgithub.com\u002Fmoonlight-lupin\u002Fagent-skills\u002Fblob\u002Fmain\u002Fproductivity\u002Freceipt-compiler\u002Ftests\u002Freceipt_compiler_selftest.py",[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":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},"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":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},"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":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},"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":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},"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":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},"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",[],[]]