[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7385WKX88VBVQ254ZQ024RP":3,"skill-same:01M7385WKX88VBVQ254ZQ024RP":50},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7385WKX88VBVQ254ZQ024RP","delete-no-email-contacts",null,"Delete contacts with no email address from a HubSpot CRM instance. These contacts cannot receive any communication and inflate billing. Fully automated via the HubSpot CRM Search and Batch Archive APIs.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fdelete-no-email-contacts\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: delete-no-email-contacts\ndescription: >\n  Delete contacts with no email address from a HubSpot CRM instance.\n  These contacts cannot receive any communication and inflate billing.\n  Fully automated via the HubSpot CRM Search and Batch Archive APIs.\nlicense: MIT\nmetadata:\n  author: tomgranot\n  version: \"1.0\"\n  category: database-hygiene\n---\n\n# Delete Contacts With No Email Address\n\n## Purpose\n\nContacts without an email address serve no functional purpose in a HubSpot Marketing Hub instance. They cannot receive marketing emails, sales sequences, or transactional messages. They inflate the billed contact count. This skill identifies and deletes them via the API.\n\n## Prerequisites\n\n- A HubSpot private app access token with `crm.objects.contacts.read` and `crm.objects.contacts.write` scopes\n- Python 3.10+ with `uv` for package management\n- A `.env` file containing `HUBSPOT_ACCESS_TOKEN`\n\n## Execution Pattern\n\nThis skill follows a 4-stage execution pattern: **Plan -> Before State -> Execute -> After State**.\n\n### Stage 1: Plan\n\nBefore writing any code, confirm these items with the user:\n\n1. **Root cause**: Ask whether any integrations (CRM sync, form tool, import process) are intentionally creating contacts without email. If so, fix the inflow first.\n2. **Threshold**: The default safety abort threshold is 500 contacts. If the user expects more, adjust the threshold in the execute script.\n3. **Recovery window**: Confirm the user understands that deleted contacts are recoverable for 90 days via HubSpot Settings > Data Management > Deleted Objects.\n\n### Stage 2: Before State\n\nRun a count query to establish the baseline. Save results for comparison.\n\n```python\n\"\"\"\nBefore State: Count contacts with no email address.\n\"\"\"\nimport os\nimport json\nimport requests\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\nTOKEN = os.environ[\"HUBSPOT_ACCESS_TOKEN\"]\nBASE = \"https:\u002F\u002Fapi.hubapi.com\"\nheaders = {\n    \"Authorization\": f\"Bearer {TOKEN}\",\n    \"Content-Type\": \"application\u002Fjson\",\n}\n\nsearch_payload = {\n    \"filterGroups\": [\n        {\n            \"filters\": [\n                {\n                    \"propertyName\": \"email\",\n                    \"operator\": \"NOT_HAS_PROPERTY\",\n                }\n            ]\n        }\n    ],\n    \"properties\": [\"firstname\", \"lastname\", \"createdate\", \"hs_object_id\"],\n    \"limit\": 1,  # Only need the total count\n}\n\nurl = f\"{BASE}\u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fsearch\"\nresponse = requests.post(url, headers=headers, json=search_payload)\nresponse.raise_for_status()\n\ndata = response.json()\ntotal = data.get(\"total\", 0)\n\nprint(f\"BEFORE STATE: {total} contacts exist with no email address.\")\n\nif total > 0 and data.get(\"results\"):\n    sample = data[\"results\"][0]\n    props = sample.get(\"properties\", {})\n    print(f\"  Sample: ID {sample['id']}, \"\n          f\"{props.get('firstname', '(empty)')} {props.get('lastname', '(empty)')}, \"\n          f\"created {props.get('createdate', '(unknown)')}\")\n```\n\n**Expected output**: A count of contacts with no email and a sample record for sanity checking.\n\n**Present findings to the user** before proceeding. Ask for explicit confirmation to continue.\n\n### Stage 3: Execute\n\nCollect all contact IDs via paginated search, export a CSV audit trail, then batch-delete.\n\n```python\n\"\"\"\nExecute: Delete all contacts with no email address.\nSteps:\n  1. Paginated search to collect all contact IDs\n  2. Export CSV audit log before deletion\n  3. Batch archive in groups of 100\n\"\"\"\nimport os\nimport csv\nimport time\nimport requests\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\nTOKEN = os.environ[\"HUBSPOT_ACCESS_TOKEN\"]\nBASE = \"https:\u002F\u002Fapi.hubapi.com\"\nheaders = {\n    \"Authorization\": f\"Bearer {TOKEN}\",\n    \"Content-Type\": \"application\u002Fjson\",\n}\n\n# --- Step 1: Collect all contact IDs ---\nall_contacts = []\nafter = None\n\nsearch_payload = {\n    \"filterGroups\": [\n        {\n            \"filters\": [\n                {\n                    \"propertyName\": \"email\",\n                    \"operator\": \"NOT_HAS_PROPERTY\",\n                }\n            ]\n        }\n    ],\n    \"properties\": [\"firstname\", \"lastname\", \"createdate\", \"hs_object_id\"],\n    \"limit\": 100,\n}\n\nwhile True:\n    payload = search_payload.copy()\n    if after:\n        payload[\"after\"] = after\n\n    resp = requests.post(\n        f\"{BASE}\u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fsearch\",\n        headers=headers, json=payload,\n    )\n    resp.raise_for_status()\n    data = resp.json()\n\n    for contact in data.get(\"results\", []):\n        props = contact.get(\"properties\", {})\n        all_contacts.append({\n            \"id\": contact[\"id\"],\n            \"firstname\": props.get(\"firstname\", \"\"),\n            \"lastname\": props.get(\"lastname\", \"\"),\n            \"createdate\": props.get(\"createdate\", \"\"),\n        })\n\n    paging = data.get(\"paging\", {})\n    after = paging.get(\"next\", {}).get(\"after\")\n    if not after:\n        break\n    time.sleep(0.2)  # Rate limiting\n\nprint(f\"Total contacts to delete: {len(all_contacts)}\")\n\n# --- Step 2: SAFETY CHECK ---\nABORT_THRESHOLD = 500\nif len(all_contacts) > ABORT_THRESHOLD:\n    print(f\"SAFETY ABORT: Found {len(all_contacts)} contacts, \"\n          f\"exceeds threshold of {ABORT_THRESHOLD}.\")\n    print(\"Review the data and adjust the threshold if this is expected.\")\n    exit(1)\n\n# --- Step 3: Export CSV audit trail ---\nos.makedirs(\"data\u002Faudit-logs\", exist_ok=True)\ncsv_path = \"data\u002Faudit-logs\u002Fdeleted-no-email-contacts.csv\"\n\nwith open(csv_path, \"w\", newline=\"\") as f:\n    writer = csv.DictWriter(f, fieldnames=[\"id\", \"firstname\", \"lastname\", \"createdate\"])\n    writer.writeheader()\n    writer.writerows(all_contacts)\n\nprint(f\"Audit log saved: {csv_path} ({len(all_contacts)} records)\")\n\n# --- Step 4: Batch delete ---\nall_ids = [c[\"id\"] for c in all_contacts]\nBATCH_SIZE = 100\ndeleted_count = 0\nfailed_ids = []\n\nfor i in range(0, len(all_ids), BATCH_SIZE):\n    batch = all_ids[i : i + BATCH_SIZE]\n    delete_payload = {\"inputs\": [{\"id\": cid} for cid in batch]}\n\n    resp = requests.post(\n        f\"{BASE}\u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fbatch\u002Farchive\",\n        headers=headers, json=delete_payload,\n    )\n\n    if resp.status_code == 204:\n        deleted_count += len(batch)\n        print(f\"  Batch {i \u002F\u002F BATCH_SIZE + 1}: deleted {len(batch)} contacts\")\n    else:\n        failed_ids.extend(batch)\n        print(f\"  Batch FAILED: {resp.status_code} — {resp.text[:200]}\")\n\n    time.sleep(0.5)  # Rate limiting between batches\n\nprint(f\"\\nDeleted: {deleted_count}, Failed: {len(failed_ids)}\")\n```\n\n**Key API details**:\n- `POST \u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fsearch` with `NOT_HAS_PROPERTY` filter on `email`\n- Paginate with `after` cursor, 100 results per page\n- `POST \u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fbatch\u002Farchive` accepts up to 100 IDs per call\n- Successful archive returns HTTP 204 (no content)\n\n### Stage 4: After State\n\nRe-run the before-state query to confirm zero contacts remain.\n\n```python\n\"\"\"\nAfter State: Verify no contacts with missing email remain.\n\"\"\"\n# (Same search payload as Before State)\nresponse = requests.post(url, headers=headers, json=search_payload)\nresponse.raise_for_status()\ntotal = response.json().get(\"total\", 0)\n\nif total == 0:\n    print(\"SUCCESS: 0 contacts with no email remain.\")\nelse:\n    print(f\"WARNING: {total} contacts with no email still exist.\")\n    print(\"New contacts may have been created since deletion. Investigate.\")\n```\n\n**Present results to the user.** If new contacts appeared, investigate the source (form submissions, integrations, imports).\n\n## Safety Mechanisms\n\n| Mechanism | Detail |\n|-----------|--------|\n| **Abort threshold** | Hard-coded at 500 contacts by default. If the search returns more, the script exits without deleting anything. Adjust only with explicit user confirmation. |\n| **CSV audit trail** | Every contact ID, name, and create date is exported to CSV before any deletion occurs. |\n| **Confirmation prompt** | Always present the Before State count to the user and wait for explicit confirmation before running Execute. |\n| **90-day recovery** | Deleted contacts can be restored via HubSpot Settings > Data Management > Deleted Objects for 90 days. |\n| **Archived contacts audit** | After deletion, you can retrieve deleted contacts via the standard contacts endpoint with `archived=true` parameter to verify what was removed. |\n\n## Technical Gotchas\n\n1. **`NOT_HAS_PROPERTY` vs `EQ \"\"`**: Use `NOT_HAS_PROPERTY` operator, not `EQ` with an empty string. HubSpot treats \"property not set\" differently from \"property set to empty string.\"\n\n2. **Search API pagination limit**: The HubSpot CRM Search API has a hard cap of 10,000 results per query. For this use case (typically a few hundred contacts), this is not an issue. If you encounter it, use segmented queries (e.g., filter by create date ranges).\n\n3. **Rate limiting**: The search API allows ~4 requests\u002Fsecond for a private app. The batch archive API is more restrictive. Use `time.sleep(0.5)` between batch archive calls.\n\n4. **Batch archive returns 204**: A successful batch archive returns HTTP 204 with an empty body, not 200. Check for `status_code == 204`.\n\n5. **Contacts may reappear**: If an integration or form is creating contacts without email, new ones will appear after deletion. Always investigate the root cause.\n\n## Package Setup\n\n```bash\nuv init hubspot-cleanup\ncd hubspot-cleanup\nuv add requests python-dotenv\n```\n\nCreate a `.env` file:\n```\nHUBSPOT_ACCESS_TOKEN=pat-na1-xxxxxxxx\n```\n","# Delete Contacts With No Email Address\n\n## Purpose\n\nContacts without an email address serve no functional purpose in a HubSpot Marketing Hub instance. They cannot receive marketing emails, sales sequences, or transactional messages. They inflate the billed contact count. This skill identifies and deletes them via the API.\n\n## Prerequisites\n\n- A HubSpot private app access token with `crm.objects.contacts.read` and `crm.objects.contacts.write` scopes\n- Python 3.10+ with `uv` for package management\n- A `.env` file containing `HUBSPOT_ACCESS_TOKEN`\n\n## Execution Pattern\n\nThis skill follows a 4-stage execution pattern: **Plan -> Before State -> Execute -> After State**.\n\n### Stage 1: Plan\n\nBefore writing any code, confirm these items with the user:\n\n1. **Root cause**: Ask whether any integrations (CRM sync, form tool, import process) are intentionally creating contacts without email. If so, fix the inflow first.\n2. **Threshold**: The default safety abort threshold is 500 contacts. If the user expects more, adjust the threshold in the execute script.\n3. **Recovery window**: Confirm the user understands that deleted contacts are recoverable for 90 days via HubSpot Settings > Data Management > Deleted Objects.\n\n### Stage 2: Before State\n\nRun a count query to establish the baseline. Save results for comparison.\n\n```python\n\"\"\"\nBefore State: Count contacts with no email address.\n\"\"\"\nimport os\nimport json\nimport requests\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\nTOKEN = os.environ[\"HUBSPOT_ACCESS_TOKEN\"]\nBASE = \"https:\u002F\u002Fapi.hubapi.com\"\nheaders = {\n    \"Authorization\": f\"Bearer {TOKEN}\",\n    \"Content-Type\": \"application\u002Fjson\",\n}\n\nsearch_payload = {\n    \"filterGroups\": [\n        {\n            \"filters\": [\n                {\n                    \"propertyName\": \"email\",\n                    \"operator\": \"NOT_HAS_PROPERTY\",\n                }\n            ]\n        }\n    ],\n    \"properties\": [\"firstname\", \"lastname\", \"createdate\", \"hs_object_id\"],\n    \"limit\": 1,  # Only need the total count\n}\n\nurl = f\"{BASE}\u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fsearch\"\nresponse = requests.post(url, headers=headers, json=search_payload)\nresponse.raise_for_status()\n\ndata = response.json()\ntotal = data.get(\"total\", 0)\n\nprint(f\"BEFORE STATE: {total} contacts exist with no email address.\")\n\nif total > 0 and data.get(\"results\"):\n    sample = data[\"results\"][0]\n    props = sample.get(\"properties\", {})\n    print(f\"  Sample: ID {sample['id']}, \"\n          f\"{props.get('firstname', '(empty)')} {props.get('lastname', '(empty)')}, \"\n          f\"created {props.get('createdate', '(unknown)')}\")\n```\n\n**Expected output**: A count of contacts with no email and a sample record for sanity checking.\n\n**Present findings to the user** before proceeding. Ask for explicit confirmation to continue.\n\n### Stage 3: Execute\n\nCollect all contact IDs via paginated search, export a CSV audit trail, then batch-delete.\n\n```python\n\"\"\"\nExecute: Delete all contacts with no email address.\nSteps:\n  1. Paginated search to collect all contact IDs\n  2. Export CSV audit log before deletion\n  3. Batch archive in groups of 100\n\"\"\"\nimport os\nimport csv\nimport time\nimport requests\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\nTOKEN = os.environ[\"HUBSPOT_ACCESS_TOKEN\"]\nBASE = \"https:\u002F\u002Fapi.hubapi.com\"\nheaders = {\n    \"Authorization\": f\"Bearer {TOKEN}\",\n    \"Content-Type\": \"application\u002Fjson\",\n}\n\n# --- Step 1: Collect all contact IDs ---\nall_contacts = []\nafter = None\n\nsearch_payload = {\n    \"filterGroups\": [\n        {\n            \"filters\": [\n                {\n                    \"propertyName\": \"email\",\n                    \"operator\": \"NOT_HAS_PROPERTY\",\n                }\n            ]\n        }\n    ],\n    \"properties\": [\"firstname\", \"lastname\", \"createdate\", \"hs_object_id\"],\n    \"limit\": 100,\n}\n\nwhile True:\n    payload = search_payload.copy()\n    if after:\n        payload[\"after\"] = after\n\n    resp = requests.post(\n        f\"{BASE}\u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fsearch\",\n        headers=headers, json=payload,\n    )\n    resp.raise_for_status()\n    data = resp.json()\n\n    for contact in data.get(\"results\", []):\n        props = contact.get(\"properties\", {})\n        all_contacts.append({\n            \"id\": contact[\"id\"],\n            \"firstname\": props.get(\"firstname\", \"\"),\n            \"lastname\": props.get(\"lastname\", \"\"),\n            \"createdate\": props.get(\"createdate\", \"\"),\n        })\n\n    paging = data.get(\"paging\", {})\n    after = paging.get(\"next\", {}).get(\"after\")\n    if not after:\n        break\n    time.sleep(0.2)  # Rate limiting\n\nprint(f\"Total contacts to delete: {len(all_contacts)}\")\n\n# --- Step 2: SAFETY CHECK ---\nABORT_THRESHOLD = 500\nif len(all_contacts) > ABORT_THRESHOLD:\n    print(f\"SAFETY ABORT: Found {len(all_contacts)} contacts, \"\n          f\"exceeds threshold of {ABORT_THRESHOLD}.\")\n    print(\"Review the data and adjust the threshold if this is expected.\")\n    exit(1)\n\n# --- Step 3: Export CSV audit trail ---\nos.makedirs(\"data\u002Faudit-logs\", exist_ok=True)\ncsv_path = \"data\u002Faudit-logs\u002Fdeleted-no-email-contacts.csv\"\n\nwith open(csv_path, \"w\", newline=\"\") as f:\n    writer = csv.DictWriter(f, fieldnames=[\"id\", \"firstname\", \"lastname\", \"createdate\"])\n    writer.writeheader()\n    writer.writerows(all_contacts)\n\nprint(f\"Audit log saved: {csv_path} ({len(all_contacts)} records)\")\n\n# --- Step 4: Batch delete ---\nall_ids = [c[\"id\"] for c in all_contacts]\nBATCH_SIZE = 100\ndeleted_count = 0\nfailed_ids = []\n\nfor i in range(0, len(all_ids), BATCH_SIZE):\n    batch = all_ids[i : i + BATCH_SIZE]\n    delete_payload = {\"inputs\": [{\"id\": cid} for cid in batch]}\n\n    resp = requests.post(\n        f\"{BASE}\u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fbatch\u002Farchive\",\n        headers=headers, json=delete_payload,\n    )\n\n    if resp.status_code == 204:\n        deleted_count += len(batch)\n        print(f\"  Batch {i \u002F\u002F BATCH_SIZE + 1}: deleted {len(batch)} contacts\")\n    else:\n        failed_ids.extend(batch)\n        print(f\"  Batch FAILED: {resp.status_code} — {resp.text[:200]}\")\n\n    time.sleep(0.5)  # Rate limiting between batches\n\nprint(f\"\\nDeleted: {deleted_count}, Failed: {len(failed_ids)}\")\n```\n\n**Key API details**:\n- `POST \u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fsearch` with `NOT_HAS_PROPERTY` filter on `email`\n- Paginate with `after` cursor, 100 results per page\n- `POST \u002Fcrm\u002Fv3\u002Fobjects\u002Fcontacts\u002Fbatch\u002Farchive` accepts up to 100 IDs per call\n- Successful archive returns HTTP 204 (no content)\n\n### Stage 4: After State\n\nRe-run the before-state query to confirm zero contacts remain.\n\n```python\n\"\"\"\nAfter State: Verify no contacts with missing email remain.\n\"\"\"\n# (Same search payload as Before State)\nresponse = requests.post(url, headers=headers, json=search_payload)\nresponse.raise_for_status()\ntotal = response.json().get(\"total\", 0)\n\nif total == 0:\n    print(\"SUCCESS: 0 contacts with no email remain.\")\nelse:\n    print(f\"WARNING: {total} contacts with no email still exist.\")\n    print(\"New contacts may have been created since deletion. Investigate.\")\n```\n\n**Present results to the user.** If new contacts appeared, investigate the source (form submissions, integrations, imports).\n\n## Safety Mechanisms\n\n| Mechanism | Detail |\n|-----------|--------|\n| **Abort threshold** | Hard-coded at 500 contacts by default. If the search returns more, the script exits without deleting anything. Adjust only with explicit user confirmation. |\n| **CSV audit trail** | Every contact ID, name, and create date is exported to CSV before any deletion occurs. |\n| **Confirmation prompt** | Always present the Before State count to the user and wait for explicit confirmation before running Execute. |\n| **90-day recovery** | Deleted contacts can be restored via HubSpot Settings > Data Management > Deleted Objects for 90 days. |\n| **Archived contacts audit** | After deletion, you can retrieve deleted contacts via the standard contacts endpoint with `archived=true` parameter to verify what was removed. |\n\n## Technical Gotchas\n\n1. **`NOT_HAS_PROPERTY` vs `EQ \"\"`**: Use `NOT_HAS_PROPERTY` operator, not `EQ` with an empty string. HubSpot treats \"property not set\" differently from \"property set to empty string.\"\n\n2. **Search API pagination limit**: The HubSpot CRM Search API has a hard cap of 10,000 results per query. For this use case (typically a few hundred contacts), this is not an issue. If you encounter it, use segmented queries (e.g., filter by create date ranges).\n\n3. **Rate limiting**: The search API allows ~4 requests\u002Fsecond for a private app. The batch archive API is more restrictive. Use `time.sleep(0.5)` between batch archive calls.\n\n4. **Batch archive returns 204**: A successful batch archive returns HTTP 204 with an empty body, not 200. Check for `status_code == 204`.\n\n5. **Contacts may reappear**: If an integration or form is creating contacts without email, new ones will appear after deletion. Always investigate the root cause.\n\n## Package Setup\n\n```bash\nuv init hubspot-cleanup\ncd hubspot-cleanup\nuv add requests python-dotenv\n```\n\nCreate a `.env` file:\n```\nHUBSPOT_ACCESS_TOKEN=pat-na1-xxxxxxxx\n```\n",{"name":5,"license":14,"metadata":23,"description":27},{"author":24,"version":25,"category":26},"tomgranot","1.0","database-hygiene","Delete contacts with no email address from a HubSpot CRM instance. These contacts cannot receive any communication and inflate billing. Fully automated via the HubSpot CRM Search and Batch Archive APIs.\n","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fdelete-no-email-contacts",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add roohe\u002Fagentic-super-skills --skill delete-no-email-contacts",{"tool":42,"command":43},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill delete-no-email-contacts",{"tool":45,"command":46},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill delete-no-email-contacts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fdelete-no-email-contacts\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]