Skip to content

Commit 4ec4676

Browse files
committed
Refresh industry collection picks
1 parent b92c947 commit 4ec4676

6 files changed

Lines changed: 60 additions & 4 deletions

File tree

industries/README.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -4,14 +4,14 @@
44
55
| | Collection | Picks | Summary |
66
|---|---|---:|---|
7-
| 🎙️ | [**Media & Publishing Systems**](media-publishing-systems.md) | 12 | Transcription, subtitles, podcast workflows, chaptering, localization, loudness cleanup, and final-mile publishing prep. |
7+
| 🎙️ | [**Media & Publishing Systems**](media-publishing-systems.md) | 14 | Transcription, subtitles, podcast workflows, chaptering, localization, loudness cleanup, and final-mile publishing prep. |
88
| 💼 | [**Finance & Filings**](finance-filings.md) | 15 | Filings research, invoice intake, billing operations, reconciliation, and finance-adjacent reporting. |
99
| 🛒 | [**Ecommerce & Retail Operations**](ecommerce-retail-operations.md) | 12 | Catalog management, storefront automation, orders, inventory sync, marketplace support, and review-driven merchandising. |
10-
| ⚖️ | [**Legal Ops & Compliance**](legal-ops-compliance.md) | 26 | Contract workflows, forms, document review, archive search, and evidence-oriented legal and compliance support. |
11-
| 🩺 | [**Healthcare Documentation & Intake**](healthcare-documentation-intake.md) | 13 | Documentation intake, OCR, transcription, structured extraction, and biomedical literature support for paperwork-heavy workflows. |
10+
| ⚖️ | [**Legal Ops & Compliance**](legal-ops-compliance.md) | 28 | Contract workflows, forms, document review, archive search, and evidence-oriented legal and compliance support. |
11+
| 🩺 | [**Healthcare Documentation & Intake**](healthcare-documentation-intake.md) | 15 | Documentation intake, OCR, transcription, structured extraction, and biomedical literature support for paperwork-heavy workflows. |
1212
| 📈 | [**Product Analytics & Growth Ops**](product-analytics-growth-ops.md) | 12 | Product analytics, feature flags, rollout checks, session replay, privacy-friendly web analytics, and experiment/evaluation workflows. |
1313
| 📚 | [**DevRel & API Documentation**](devrel-api-documentation.md) | 17 | API docs, OpenAPI references, SDK generation, docs-site publishing, prose linting, and developer enablement workflows. |
14-
| 🎧 | [**Customer Support & Success**](customer-support-success.md) | 19 | Helpdesk queues, ticket triage, conversation lookup, knowledge-base workflows, customer context, CRM sync, and reply-drafting support. |
14+
| 🎧 | [**Customer Support & Success**](customer-support-success.md) | 21 | Helpdesk queues, ticket triage, conversation lookup, knowledge-base workflows, customer context, CRM sync, and reply-drafting support. |
1515
| 🏠 | [**Real Estate Workflows**](real-estate-workflows.md) | 13 | Property research support, transaction paperwork, signature routing, document intake, CRM context, and listing follow-up workflows for real-estate operations. |
1616

1717
---

industries/customer-support-success.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,8 @@ Helpdesk queues, ticket triage, conversation lookup, knowledge-base workflows, c
4444
| [Extract structured data and attachments from raw email with MailParser](../skills/extract-structured-data-and-attachments-from-raw-email-mailparser/) | Normalizes inbound email bodies and attachments for ticket creation or routing. | Support automation engineer | Medium | 1.7k |
4545
| [AssemblyAI Real-Time Call Intelligence](../skills/assemblyai-realtime-call-intelligence/) | Captures live call transcripts and speaker context for support QA and follow-up notes. | Call center ops / QA lead | High ||
4646
| [Strip quoted email history and signatures before summarizing inbound replies](../skills/strip-quoted-email-history-and-signatures-before-summarizing-inbound-replies/) | Keeps reply summaries focused on the newest customer message instead of quoted thread noise. | Support agent / inbox triage lead | Low | 78 |
47+
| [Slack MCP Server](../skills/slack-mcp-server/) | Lets support agents inspect Slack escalation threads and customer-adjacent workspace context before drafting handoffs or replies. | Support escalation lead / success ops | Medium | 86.4k |
48+
| [IMAP Inbox Triage Agent](../skills/imap-inbox-triage-agent/) | Adds direct inbox classification and prioritization for teams whose support flow still starts in shared IMAP mailboxes. | Support inbox manager / operations analyst | Medium ||
4749
| [Zapier Multi-Step Lead Enrichment Workflow](../skills/zapier-lead-enrichment-workflow/) | Enriches lead/contact records before support-to-success handoff or account follow-up. | Success ops / CRM automation lead | Medium ||
4850

4951
## Editorial Notes

industries/healthcare-documentation-intake.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -39,6 +39,8 @@ Documentation intake, OCR, transcription, structured extraction, and biomedical
3939
| [Parse local PDFs into agent-ready text, JSON, and screenshots with LiteParse](../skills/parse-local-pdfs-into-agent-ready-text-json-and-screenshots-with-liteparse/) | Keeps local PDF extraction inspectable with text, JSON, and screenshots before PHI-sensitive review. | AI ops / documentation QA | Medium | 5.1k |
4040
| [Redact PII from text before sharing or indexing with scrubadub](../skills/redact-pii-from-text-before-sharing-or-indexing-with-scrubadub/) | Removes obvious identifiers before documentation text is shared, indexed, or sent downstream. | Privacy reviewer / documentation ops | Low | 421 |
4141
| [Surya Document OCR with Layout Analysis and Table Recognition](../skills/surya-document-ocr-layout-analysis-table-recognition/) | Adds layout-aware OCR and table recognition for scanned forms, records, and intake packets. | Health records ops / documentation analyst | High | 19.5k |
42+
| [PaddleOCR Multilingual Document OCR and Structured Data Toolkit](../skills/paddleocr-multilingual-document-ocr-toolkit/) | Adds multilingual OCR and structured extraction for scanned intake forms, referral packets, and mixed-language documentation queues. | Healthcare intake ops / document automation engineer | High | 73.7k |
43+
| [MarkItDown Document-to-Markdown Converter by Microsoft](../skills/markitdown-document-to-markdown-converter-microsoft/) | Converts PDFs, Office files, images, and audio notes into Markdown that documentation agents can summarize with human review. | Clinical documentation ops / data intake analyst | Medium | 93.2k |
4244
| [Extract structured text, metadata, tables, and images from mixed documents through an MCP server with Kreuzberg](../skills/extract-structured-text-metadata-tables-and-images-from-mixed-documents-through-an-mcp-server-with-kreuzberg/) | Gives agents one MCP-accessible extraction layer for PDFs, Office files, images, HTML, and other mixed healthcare intake inputs. | Health data engineer / AI documentation ops | High | 7.6k |
4345

4446
## Editorial Notes

industries/legal-ops-compliance.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -54,6 +54,8 @@ Contract workflows, forms, document review, archive search, and evidence-oriente
5454
| [Extract structured data and attachments from raw email with MailParser](../skills/extract-structured-data-and-attachments-from-raw-email-mailparser/) | Normalizes raw email evidence and attachments before archive search or review. | Legal ops / mailbox reviewer | Medium | 1.7k |
5555
| [Strip quoted email history and signatures before summarizing inbound replies](../skills/strip-quoted-email-history-and-signatures-before-summarizing-inbound-replies/) | Separates the newest human reply from long threads so summaries do not duplicate history. | Case manager / legal assistant | Low | 78 |
5656
| [Load .mbox mail archives into SQLite for offline search, audits, and dataset joins](../skills/load-mbox-mail-archives-into-sqlite-for-offline-search-audits-and-dataset-joins/) | Turns mailbox archives into queryable SQLite evidence stores for offline audit work. | Investigator / data analyst | Medium | 39 |
57+
| [MarkItDown Document-to-Markdown Converter by Microsoft](../skills/markitdown-document-to-markdown-converter-microsoft/) | Converts Office files, PDFs, email-like documents, and other matter inputs into Markdown for review packets and audit summaries. | Legal ops analyst / compliance reviewer | Medium | 93.2k |
58+
| [MinerU PDF-to-Markdown Document Parser](../skills/mineru-pdf-to-markdown-document-parser/) | Handles complex PDFs with layout-aware Markdown and JSON output for contract packets, exhibits, and long-form compliance evidence. | eDiscovery engineer / records analyst | High | 57.8k |
5759
| [Put approval gates and audit-ready policy checks between agents and external actions with DashClaw](../skills/put-approval-gates-and-audit-ready-policy-checks-between-agents-and-external-actions-with-dashclaw/) | Adds approval gates and replayable decision evidence when legal AI workflows need human review before external actions. | Legal AI governance lead / compliance ops | High | 241 |
5860

5961
## Editorial Notes

industries/media-publishing-systems.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -37,6 +37,8 @@ Transcription, subtitles, podcast workflows, chaptering, localization, loudness
3737
| [faster-whisper High-Performance Speech Transcription Engine](../skills/faster-whisper-high-performance-speech-transcription/) | Handles high-volume transcription runs where speed and local control matter more than a hosted API. | Media automation engineer | Medium | 21.9k |
3838
| [Deepgram Real-Time Transcription Connector](../skills/deepgram-realtime-transcription-connector/) | Covers live captions and streaming call transcription where batch Whisper-style workflows are too late. | Live production / call intelligence engineer | High | 260 |
3939
| [AssemblyAI Summarization & Chapters Skill](../skills/assemblyai-summarization-chapters-skill/) | Converts transcripts into chapter summaries for show notes, lesson outlines, and archive navigation. | Podcast producer / editorial ops | Medium ||
40+
| [YouTube Chapters Generator with Whisper](../skills/youtube-chapters-generator-whisper/) | Turns YouTube source audio into timestamped chapters so editors can build navigable videos, show notes, and repurposing briefs. | Video producer / publishing ops | Medium | 97.8k |
41+
| [Summarize URLs, files, podcasts, and YouTube sources into agent-ready briefs with Summarize](../skills/summarize-urls-files-podcasts-and-youtube-sources-into-agent-ready-briefs-with-summarize/) | Creates compact briefs from URLs, files, podcasts, and YouTube sources before downstream scripting, clipping, or editorial review. | Content strategist / research producer | Medium | 5.6k |
4042
| [Self-host an OpenAI-compatible speech API for local transcription, translation, and TTS with Speaches](../skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches/) | Lets teams keep OpenAI-compatible speech workflows while self-hosting audio processing. | Platform engineer / privacy-conscious media team | High | 3.2k |
4143
| [yt-dlp Feature-Rich Audio and Video Downloader CLI](../skills/yt-dlp-feature-rich-audio-video-downloader-cli/) | Adds the standard audio/video source acquisition layer before transcription, captioning, chaptering, or repurposing workflows. | Media ops / content producer | Medium | 154.3k |
4244

scripts/industry-collections.json

Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -17,6 +17,8 @@
1717
"faster-whisper-high-performance-speech-transcription",
1818
"deepgram-realtime-transcription-connector",
1919
"assemblyai-summarization-chapters-skill",
20+
"youtube-chapters-generator-whisper",
21+
"summarize-urls-files-podcasts-and-youtube-sources-into-agent-ready-briefs-with-summarize",
2022
"self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches",
2123
"yt-dlp-feature-rich-audio-video-downloader-cli"
2224
],
@@ -120,6 +122,16 @@
120122
"persona": "Podcast producer / editorial ops",
121123
"install_complexity": "Medium"
122124
},
125+
"youtube-chapters-generator-whisper": {
126+
"why_here": "Turns YouTube source audio into timestamped chapters so editors can build navigable videos, show notes, and repurposing briefs.",
127+
"persona": "Video producer / publishing ops",
128+
"install_complexity": "Medium"
129+
},
130+
"summarize-urls-files-podcasts-and-youtube-sources-into-agent-ready-briefs-with-summarize": {
131+
"why_here": "Creates compact briefs from URLs, files, podcasts, and YouTube sources before downstream scripting, clipping, or editorial review.",
132+
"persona": "Content strategist / research producer",
133+
"install_complexity": "Medium"
134+
},
123135
"self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches": {
124136
"why_here": "Lets teams keep OpenAI-compatible speech workflows while self-hosting audio processing.",
125137
"persona": "Platform engineer / privacy-conscious media team",
@@ -450,6 +462,8 @@
450462
"extract-structured-data-and-attachments-from-raw-email-mailparser",
451463
"strip-quoted-email-history-and-signatures-before-summarizing-inbound-replies",
452464
"load-mbox-mail-archives-into-sqlite-for-offline-search-audits-and-dataset-joins",
465+
"markitdown-document-to-markdown-converter-microsoft",
466+
"mineru-pdf-to-markdown-document-parser",
453467
"put-approval-gates-and-audit-ready-policy-checks-between-agents-and-external-actions-with-dashclaw"
454468
],
455469
"who_for": [
@@ -631,6 +645,16 @@
631645
"persona": "Investigator / data analyst",
632646
"install_complexity": "Medium"
633647
},
648+
"markitdown-document-to-markdown-converter-microsoft": {
649+
"why_here": "Converts Office files, PDFs, email-like documents, and other matter inputs into Markdown for review packets and audit summaries.",
650+
"persona": "Legal ops analyst / compliance reviewer",
651+
"install_complexity": "Medium"
652+
},
653+
"mineru-pdf-to-markdown-document-parser": {
654+
"why_here": "Handles complex PDFs with layout-aware Markdown and JSON output for contract packets, exhibits, and long-form compliance evidence.",
655+
"persona": "eDiscovery engineer / records analyst",
656+
"install_complexity": "High"
657+
},
634658
"put-approval-gates-and-audit-ready-policy-checks-between-agents-and-external-actions-with-dashclaw": {
635659
"why_here": "Adds approval gates and replayable decision evidence when legal AI workflows need human review before external actions.",
636660
"persona": "Legal AI governance lead / compliance ops",
@@ -657,6 +681,8 @@
657681
"parse-local-pdfs-into-agent-ready-text-json-and-screenshots-with-liteparse",
658682
"redact-pii-from-text-before-sharing-or-indexing-with-scrubadub",
659683
"surya-document-ocr-layout-analysis-table-recognition",
684+
"paddleocr-multilingual-document-ocr-toolkit",
685+
"markitdown-document-to-markdown-converter-microsoft",
660686
"extract-structured-text-metadata-tables-and-images-from-mixed-documents-through-an-mcp-server-with-kreuzberg"
661687
],
662688
"who_for": [
@@ -768,6 +794,16 @@
768794
"persona": "Health records ops / documentation analyst",
769795
"install_complexity": "High"
770796
},
797+
"paddleocr-multilingual-document-ocr-toolkit": {
798+
"why_here": "Adds multilingual OCR and structured extraction for scanned intake forms, referral packets, and mixed-language documentation queues.",
799+
"persona": "Healthcare intake ops / document automation engineer",
800+
"install_complexity": "High"
801+
},
802+
"markitdown-document-to-markdown-converter-microsoft": {
803+
"why_here": "Converts PDFs, Office files, images, and audio notes into Markdown that documentation agents can summarize with human review.",
804+
"persona": "Clinical documentation ops / data intake analyst",
805+
"install_complexity": "Medium"
806+
},
771807
"extract-structured-text-metadata-tables-and-images-from-mixed-documents-through-an-mcp-server-with-kreuzberg": {
772808
"why_here": "Gives agents one MCP-accessible extraction layer for PDFs, Office files, images, HTML, and other mixed healthcare intake inputs.",
773809
"persona": "Health data engineer / AI documentation ops",
@@ -1094,6 +1130,8 @@
10941130
"extract-structured-data-and-attachments-from-raw-email-mailparser",
10951131
"assemblyai-realtime-call-intelligence",
10961132
"strip-quoted-email-history-and-signatures-before-summarizing-inbound-replies",
1133+
"slack-mcp-server",
1134+
"imap-inbox-triage-agent",
10971135
"zapier-lead-enrichment-workflow"
10981136
],
10991137
"discovery_candidates": [
@@ -1232,6 +1270,16 @@
12321270
"persona": "Support agent / inbox triage lead",
12331271
"install_complexity": "Low"
12341272
},
1273+
"slack-mcp-server": {
1274+
"why_here": "Lets support agents inspect Slack escalation threads and customer-adjacent workspace context before drafting handoffs or replies.",
1275+
"persona": "Support escalation lead / success ops",
1276+
"install_complexity": "Medium"
1277+
},
1278+
"imap-inbox-triage-agent": {
1279+
"why_here": "Adds direct inbox classification and prioritization for teams whose support flow still starts in shared IMAP mailboxes.",
1280+
"persona": "Support inbox manager / operations analyst",
1281+
"install_complexity": "Medium"
1282+
},
12351283
"zapier-lead-enrichment-workflow": {
12361284
"why_here": "Enriches lead/contact records before support-to-success handoff or account follow-up.",
12371285
"persona": "Success ops / CRM automation lead",

0 commit comments

Comments
 (0)