[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73FYG2Q7CWA9N59VJ6JS30G":3,"skill-same:01M73FYG2Q7CWA9N59VJ6JS30G":53},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M73FYG2Q7CWA9N59VJ6JS30G","campaign-manager",null,"Goal-oriented binder design campaign planning and health assessment. Use this skill when: (1) Planning a complete binder design campaign, (2) Converting high-level goals into runnable pipelines, (3) Assessing campaign health and pass rates, (4) Diagnosing why designs are failing QC, (5) Estimating time, cost, and expected yields, (6) Selecting between design tools for a specific target.\nThis skill orchestrates the other protein design tools. For individual tool parameters, use the specific tool skills.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fcampaign-manager\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: campaign-manager\ndescription: \"Goal-oriented binder design campaign planning and health assessment. Use this skill when: (1) Planning a complete binder design campaign, (2) Converting high-level goals into runnable pipelines, (3) Assessing campaign health and pass rates, (4) Diagnosing why designs are failing QC, (5) Estimating time, cost, and expected yields, (6) Selecting between design tools for a specific target.\n\n  This skill orchestrates the other protein design tools. For individual tool parameters, use the specific tool skills.\"\nlicense: MIT\ncategory: orchestration\ntags: [planning, campaign, coordination]\n---\n\n# Campaign Manager\n\n## Goal-oriented design\n\n### From goal to pipeline\n\nWhen user says: \"I need 10 good binders for EGFR\"\n\n**Campaign Planning:**\n```\nGoal: 10 high-quality binders for EGFR\n├── Achievable: Yes (standard target)\n├── Recommended pipeline: rfdiffusion → proteinmpnn → chai → protein-qc\n├── Estimated designs needed: 500 backbones (to get ~50 passing QC)\n├── Estimated time: 8-12 hours total\n├── Estimated cost: ~$60 (Modal GPU compute)\n└── Expected yield:\n    ├── After backbone (500): 500 structures\n    ├── After sequence (×8): 4,000 sequences\n    ├── After validation: 4,000 predictions\n    ├── After QC (~10-15%): 400-600 candidates\n    └── After clustering: 10-20 diverse final designs\n```\n\n---\n\n## Complete pipeline generator\n\n### Standard miniprotein binder campaign\n\n```bash\n# Step 1: Fetch and prepare target (5 min)\ncurl -o target.pdb \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F{PDB_ID}.pdb\"\n# Trim to binding region if needed\n\n# Step 2: Generate backbones (2-3h, ~$15)\n# RFdiffusion runs from the official repo, not biomodals\npython run_inference.py \\\n  inference.input_pdb=target.pdb \\\n  contigmap.contigs=[A1-150\u002F0 70-100] \\\n  ppi.hotspot_res=[A45,A67,A89] \\\n  inference.num_designs=500\n\n# Checkpoint: ls output\u002F*.pdb | wc -l  # Should be 500\n\n# Step 3: Design sequences (1-2h, ~$10)\nfor f in output\u002F*.pdb; do\n  modal run modal_ligandmpnn.py \\\n    --input-pdb \"$f\" \\\n    --params-str \"--number_of_batches 8 --temperature 0.1\"\ndone\n\n# Checkpoint: grep -c \"^>\" output\u002Fseqs\u002F*.fa  # Should be ~4000\n\n# Step 4: Quick ESM2 filter (30 min, ~$5, optional)\nmodal run modal_esm2_predict_masked.py --input-faa output\u002Fall_seqs.fa\n# Filter sequences with PLL \u003C 0.0\n\n# Step 5: Structure validation (3-4h, ~$35)\nmodal run modal_alphafold.py \\\n  --input-faa output\u002Ffiltered_seqs.fa \\\n  --out-dir predictions\u002F\n\n# Checkpoint: find predictions -name \"*rank_001.pdb\" | wc -l\n\n# Step 6: Filter and rank (protein-qc skill)\n# Apply thresholds: pLDDT > 0.85, ipTM > 0.5, scRMSD \u003C 2.0\n# Compute composite score\n# Cluster at 70% identity, select top from each cluster\n```\n\n**Total estimated time**: 8-12 hours\n**Total estimated cost**: ~$60-70\n\n---\n\n## Campaign size recommendations\n\n| Goal | Backbones | Sequences\u002FBB | Total Seq | Expected Passing |\n|------|-----------|--------------|-----------|------------------|\n| 5 binders | 200 | 8 | 1,600 | 160-240 |\n| 10 binders | 500 | 8 | 4,000 | 400-600 |\n| 20 binders | 1,000 | 8 | 8,000 | 800-1,200 |\n| 50 binders | 2,500 | 8 | 20,000 | 2,000-3,000 |\n\n**Rule of thumb**: Generate 50x more designs than you need (10-15% pass rate × clustering).\n\n---\n\n## Tool selection guide\n\n### When to use each tool\n\n| Scenario | Recommended Tool | Reason |\n|----------|------------------|--------|\n| Standard miniprotein | RFdiffusion + ProteinMPNN | High diversity, proven |\n| Need higher success rate | BindCraft | Integrated design loop |\n| All-atom precision needed | BoltzGen | Side-chain aware |\n| Difficult target | Mosaic | Gradient, multi-model objective |\n| Need fast iteration | ESMFold2 + ESM2 | Quick screening |\n\n### Target difficulty assessment\n\n| Indicator | Easy Target | Difficult Target |\n|-----------|-------------|------------------|\n| Surface type | Concave pocket | Flat or convex |\n| Conservation | High | Low |\n| Known binders | Yes | No |\n| Flexibility | Rigid | Flexible |\n| Expected pass rate | 15-20% | 5-10% |\n\n---\n\n## Campaign health assessment\n\n### Quick metrics check\n\n```python\nimport pandas as pd\n\ndef assess_campaign(csv_path):\n    df = pd.read_csv(csv_path)\n\n    # Calculate pass rates\n    plddt_pass = (df['pLDDT'] > 0.85).mean()\n    iptm_pass = (df['ipTM'] > 0.50).mean()\n    scrmsd_pass = (df['scRMSD'] \u003C 2.0).mean()\n    all_pass = ((df['pLDDT'] > 0.85) & (df['ipTM'] > 0.5) & (df['scRMSD'] \u003C 2.0)).mean()\n\n    # Determine health\n    if all_pass > 0.15:\n        health = \"EXCELLENT\"\n    elif all_pass > 0.10:\n        health = \"GOOD\"\n    elif all_pass > 0.05:\n        health = \"MARGINAL\"\n    else:\n        health = \"POOR\"\n\n    # Identify top issue\n    issues = []\n    if plddt_pass \u003C 0.20:\n        issues.append(\"Low pLDDT - backbone or sequence issue\")\n    if iptm_pass \u003C 0.20:\n        issues.append(\"Low ipTM - hotspot or interface issue\")\n    if scrmsd_pass \u003C 0.50:\n        issues.append(\"High scRMSD - sequence doesn't specify backbone\")\n\n    return {\n        \"health\": health,\n        \"overall_pass_rate\": all_pass,\n        \"plddt_pass_rate\": plddt_pass,\n        \"iptm_pass_rate\": iptm_pass,\n        \"scrmsd_pass_rate\": scrmsd_pass,\n        \"top_issues\": issues\n    }\n```\n\n### Interpreting results\n\n| Health | Pass Rate | Action |\n|--------|-----------|--------|\n| EXCELLENT | > 15% | Proceed to selection |\n| GOOD | 10-15% | Proceed, normal yield |\n| MARGINAL | 5-10% | Review failure tree |\n| POOR | \u003C 5% | Diagnose and restart |\n\n---\n\n## Cost estimation\n\n### Per-tool costs (Modal)\n\n| Tool | GPU | $\u002Fhour | Typical Job | Cost |\n|------|-----|--------|-------------|------|\n| RFdiffusion | A10G | ~$1.20 | 500 designs\u002F2h | ~$2.50 |\n| ProteinMPNN | T4 | ~$0.60 | 4000 seq\u002F1.5h | ~$1.00 |\n| ESM2 (PLL) | A10G | ~$1.20 | 4000 seq\u002F30min | ~$0.60 |\n| AlphaFold | A100 | ~$4.50 | 4000 preds\u002F4h | ~$18.00 |\n| Chai | A100 | ~$4.50 | 500 preds\u002F1h | ~$4.50 |\n\n### Campaign cost estimates\n\n| Campaign Size | Total Cost | Notes |\n|---------------|------------|-------|\n| Small (100 bb) | ~$15 | Quick exploration |\n| Standard (500 bb) | ~$60 | Most campaigns |\n| Large (1000 bb) | ~$120 | Comprehensive |\n| XL (5000 bb) | ~$600 | Very thorough |\n\n---\n\n## Pipeline variants\n\n### High-throughput (maximize diversity)\n\n```bash\n# More backbones, fewer sequences each (RFdiffusion from the official repo)\npython run_inference.py inference.num_designs=2000\nmodal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str \"--number_of_batches 4 --temperature 0.2\"\n```\n\n### High-quality (maximize per-design quality)\n\n```bash\n# Fewer backbones, more sequences each, lower temperature\npython run_inference.py inference.num_designs=200\nmodal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str \"--number_of_batches 32 --temperature 0.1\"\n```\n\n### Quick exploration (fast iteration)\n\n```bash\n# Small batch, ESMFold2 for fast single-sequence folding\n# RFdiffusion runs from the official repo (not biomodals); see the rfdiffusion skill\nmodal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str \"--number_of_batches 8\"\nmodal run modal_esmfold2.py --input-faa all_seqs.fa\n```\n\n---\n\n## See also\n\n- Tool-specific parameters: `rfdiffusion`, `proteinmpnn`, `mosaic`, `chai`, `boltz`, `alphafold`\n- QC thresholds and filtering: `protein-qc`\n- Tool selection guidance: `binder-design`\n","# Campaign Manager\n\n## Goal-oriented design\n\n### From goal to pipeline\n\nWhen user says: \"I need 10 good binders for EGFR\"\n\n**Campaign Planning:**\n```\nGoal: 10 high-quality binders for EGFR\n├── Achievable: Yes (standard target)\n├── Recommended pipeline: rfdiffusion → proteinmpnn → chai → protein-qc\n├── Estimated designs needed: 500 backbones (to get ~50 passing QC)\n├── Estimated time: 8-12 hours total\n├── Estimated cost: ~$60 (Modal GPU compute)\n└── Expected yield:\n    ├── After backbone (500): 500 structures\n    ├── After sequence (×8): 4,000 sequences\n    ├── After validation: 4,000 predictions\n    ├── After QC (~10-15%): 400-600 candidates\n    └── After clustering: 10-20 diverse final designs\n```\n\n---\n\n## Complete pipeline generator\n\n### Standard miniprotein binder campaign\n\n```bash\n# Step 1: Fetch and prepare target (5 min)\ncurl -o target.pdb \"https:\u002F\u002Ffiles.rcsb.org\u002Fdownload\u002F{PDB_ID}.pdb\"\n# Trim to binding region if needed\n\n# Step 2: Generate backbones (2-3h, ~$15)\n# RFdiffusion runs from the official repo, not biomodals\npython run_inference.py \\\n  inference.input_pdb=target.pdb \\\n  contigmap.contigs=[A1-150\u002F0 70-100] \\\n  ppi.hotspot_res=[A45,A67,A89] \\\n  inference.num_designs=500\n\n# Checkpoint: ls output\u002F*.pdb | wc -l  # Should be 500\n\n# Step 3: Design sequences (1-2h, ~$10)\nfor f in output\u002F*.pdb; do\n  modal run modal_ligandmpnn.py \\\n    --input-pdb \"$f\" \\\n    --params-str \"--number_of_batches 8 --temperature 0.1\"\ndone\n\n# Checkpoint: grep -c \"^>\" output\u002Fseqs\u002F*.fa  # Should be ~4000\n\n# Step 4: Quick ESM2 filter (30 min, ~$5, optional)\nmodal run modal_esm2_predict_masked.py --input-faa output\u002Fall_seqs.fa\n# Filter sequences with PLL \u003C 0.0\n\n# Step 5: Structure validation (3-4h, ~$35)\nmodal run modal_alphafold.py \\\n  --input-faa output\u002Ffiltered_seqs.fa \\\n  --out-dir predictions\u002F\n\n# Checkpoint: find predictions -name \"*rank_001.pdb\" | wc -l\n\n# Step 6: Filter and rank (protein-qc skill)\n# Apply thresholds: pLDDT > 0.85, ipTM > 0.5, scRMSD \u003C 2.0\n# Compute composite score\n# Cluster at 70% identity, select top from each cluster\n```\n\n**Total estimated time**: 8-12 hours\n**Total estimated cost**: ~$60-70\n\n---\n\n## Campaign size recommendations\n\n| Goal | Backbones | Sequences\u002FBB | Total Seq | Expected Passing |\n|------|-----------|--------------|-----------|------------------|\n| 5 binders | 200 | 8 | 1,600 | 160-240 |\n| 10 binders | 500 | 8 | 4,000 | 400-600 |\n| 20 binders | 1,000 | 8 | 8,000 | 800-1,200 |\n| 50 binders | 2,500 | 8 | 20,000 | 2,000-3,000 |\n\n**Rule of thumb**: Generate 50x more designs than you need (10-15% pass rate × clustering).\n\n---\n\n## Tool selection guide\n\n### When to use each tool\n\n| Scenario | Recommended Tool | Reason |\n|----------|------------------|--------|\n| Standard miniprotein | RFdiffusion + ProteinMPNN | High diversity, proven |\n| Need higher success rate | BindCraft | Integrated design loop |\n| All-atom precision needed | BoltzGen | Side-chain aware |\n| Difficult target | Mosaic | Gradient, multi-model objective |\n| Need fast iteration | ESMFold2 + ESM2 | Quick screening |\n\n### Target difficulty assessment\n\n| Indicator | Easy Target | Difficult Target |\n|-----------|-------------|------------------|\n| Surface type | Concave pocket | Flat or convex |\n| Conservation | High | Low |\n| Known binders | Yes | No |\n| Flexibility | Rigid | Flexible |\n| Expected pass rate | 15-20% | 5-10% |\n\n---\n\n## Campaign health assessment\n\n### Quick metrics check\n\n```python\nimport pandas as pd\n\ndef assess_campaign(csv_path):\n    df = pd.read_csv(csv_path)\n\n    # Calculate pass rates\n    plddt_pass = (df['pLDDT'] > 0.85).mean()\n    iptm_pass = (df['ipTM'] > 0.50).mean()\n    scrmsd_pass = (df['scRMSD'] \u003C 2.0).mean()\n    all_pass = ((df['pLDDT'] > 0.85) & (df['ipTM'] > 0.5) & (df['scRMSD'] \u003C 2.0)).mean()\n\n    # Determine health\n    if all_pass > 0.15:\n        health = \"EXCELLENT\"\n    elif all_pass > 0.10:\n        health = \"GOOD\"\n    elif all_pass > 0.05:\n        health = \"MARGINAL\"\n    else:\n        health = \"POOR\"\n\n    # Identify top issue\n    issues = []\n    if plddt_pass \u003C 0.20:\n        issues.append(\"Low pLDDT - backbone or sequence issue\")\n    if iptm_pass \u003C 0.20:\n        issues.append(\"Low ipTM - hotspot or interface issue\")\n    if scrmsd_pass \u003C 0.50:\n        issues.append(\"High scRMSD - sequence doesn't specify backbone\")\n\n    return {\n        \"health\": health,\n        \"overall_pass_rate\": all_pass,\n        \"plddt_pass_rate\": plddt_pass,\n        \"iptm_pass_rate\": iptm_pass,\n        \"scrmsd_pass_rate\": scrmsd_pass,\n        \"top_issues\": issues\n    }\n```\n\n### Interpreting results\n\n| Health | Pass Rate | Action |\n|--------|-----------|--------|\n| EXCELLENT | > 15% | Proceed to selection |\n| GOOD | 10-15% | Proceed, normal yield |\n| MARGINAL | 5-10% | Review failure tree |\n| POOR | \u003C 5% | Diagnose and restart |\n\n---\n\n## Cost estimation\n\n### Per-tool costs (Modal)\n\n| Tool | GPU | $\u002Fhour | Typical Job | Cost |\n|------|-----|--------|-------------|------|\n| RFdiffusion | A10G | ~$1.20 | 500 designs\u002F2h | ~$2.50 |\n| ProteinMPNN | T4 | ~$0.60 | 4000 seq\u002F1.5h | ~$1.00 |\n| ESM2 (PLL) | A10G | ~$1.20 | 4000 seq\u002F30min | ~$0.60 |\n| AlphaFold | A100 | ~$4.50 | 4000 preds\u002F4h | ~$18.00 |\n| Chai | A100 | ~$4.50 | 500 preds\u002F1h | ~$4.50 |\n\n### Campaign cost estimates\n\n| Campaign Size | Total Cost | Notes |\n|---------------|------------|-------|\n| Small (100 bb) | ~$15 | Quick exploration |\n| Standard (500 bb) | ~$60 | Most campaigns |\n| Large (1000 bb) | ~$120 | Comprehensive |\n| XL (5000 bb) | ~$600 | Very thorough |\n\n---\n\n## Pipeline variants\n\n### High-throughput (maximize diversity)\n\n```bash\n# More backbones, fewer sequences each (RFdiffusion from the official repo)\npython run_inference.py inference.num_designs=2000\nmodal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str \"--number_of_batches 4 --temperature 0.2\"\n```\n\n### High-quality (maximize per-design quality)\n\n```bash\n# Fewer backbones, more sequences each, lower temperature\npython run_inference.py inference.num_designs=200\nmodal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str \"--number_of_batches 32 --temperature 0.1\"\n```\n\n### Quick exploration (fast iteration)\n\n```bash\n# Small batch, ESMFold2 for fast single-sequence folding\n# RFdiffusion runs from the official repo (not biomodals); see the rfdiffusion skill\nmodal run modal_ligandmpnn.py --input-pdb bb.pdb --params-str \"--number_of_batches 8\"\nmodal run modal_esmfold2.py --input-faa all_seqs.fa\n```\n\n---\n\n## See also\n\n- Tool-specific parameters: `rfdiffusion`, `proteinmpnn`, `mosaic`, `chai`, `boltz`, `alphafold`\n- QC thresholds and filtering: `protein-qc`\n- Tool selection guidance: `binder-design`\n",{"name":5,"tags":24,"license":15,"category":28,"description":7},[25,26,27],"planning","campaign","coordination","orchestration","master","fd76f882a04e445e899d5cfb2732f2105ea054ee","skills\u002Fawesome-skills\u002Fcampaign-manager",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill campaign-manager",{"tool":45,"command":46},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill campaign-manager",{"tool":48,"command":49},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill campaign-manager","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fcampaign-manager\u002FSKILL.md",true,[],[54,64,72,80,88,95],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":63},"01M748668J70YKWKS2VFVZ0ZRF","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fxlsx\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":63},"01M747X09GNGYJ7V4YE3NGGH7A","pptx","Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fpptx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fpptx\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":58,"licenseFileUrl":76,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":63},"01M747QR3VN12KXYDZGRXETTGS","docx","Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fdocx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fskills\u002Fdocx\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":63},"01M76KTXGSTXVVDC7YSBM41ZZS","wxpusher-integration","Use when（适用场景）：用户明确询问、指定或上下文已选定 WxPusher，需要了解、接入或排查通知（含微信 ClawBot\u002FiLink、appToken、UID、Topic、SPT）；仅说“微信通知”、未选服务商，或只出现通用 UID\u002FTopic 时不触发。","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwxpusher-integration\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fwxpusher-integration\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M748C5DS5BQBVBMG22FCGG34","branding","When the user wants to define, audit, or apply brand strategy—purpose, values, positioning, storytelling, voice, narrative (not only visuals). Also use when the user mentions \"brand strategy\", \"brand story\", \"brand storytelling\" or \"brand voice\". For typography, colors, design tokens, and frontend visuals, use brand-visual-generator.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fsuperskills\u002Fbranding\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M748C1GXJ9WRKP18X45DKP6G","brand-visual-generator","When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics). Also use when the user mentions \"brand style guide\", \"visual identity\", \"design system\" or \"typography\". For brand story, positioning, and voice, use branding.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fsuperskills\u002Fbrand-visual-generator\u002FSKILL.md",[],[]]