[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWWZXF8KYD9YM6CNEHSQQF":3,"skill-same:01M6HWWZXF8KYD9YM6CNEHSQQF":67},{"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":23,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6HWWZXF8KYD9YM6CNEHSQQF","resilient-data-gathering",null,"Fallback pattern when primary tools fail - embed known data in scripts and persist to JSON for auditability","HKUDS\u002FAgentPilot","HKUDS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F118165258?v=4","01M6HW8VRNZP64G0P4MVJW2KKQ","✨Data Intelligence Lab@HKU✨","01M6HW8VWZVHBRHYH3T330PFWV",8029,"MIT","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fresilient-data-gathering\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33],"data","resilient data gathering","Tools","json","fallback","pattern","scripts","embed","persist","for","2026-11-10 10:12:30",false,"---\nname: resilient-data-gathering\ndescription: Fallback pattern when primary tools fail - embed known data in scripts and persist to JSON for auditability\n---\n\n# Resilient Data Gathering Workflow\n\n## Purpose\n\nWhen `search_web`, `shell_agent`, and `execute_code_sandbox` all fail repeatedly with 'unknown error' or similar tool execution failures, fall back to embedding known domain data directly into `run_shell` Python scripts and persisting intermediate data to JSON files for auditability and recovery.\n\n## When to Use This Pattern\n\nApply this pattern when:\n1. **Trigger condition**: 2-3 consecutive failures across multiple tools (`search_web`, `shell_agent`, `execute_code_sandbox`) with 'unknown error' messages\n2. **You have domain knowledge**: The required data is known or can be reasonably estimated from context\n3. **Auditability needed**: Intermediate results must be preserved for verification or rollback\n\n## Step-by-Step Instructions\n\n### Step 1: Recognize Tool Failure Pattern\n\nMonitor for repeated failures across multiple execution tools:\n- `search_web` returns errors or empty results\n- `shell_agent` fails to complete autonomous tasks\n- `execute_code_sandbox` throws 'unknown error' repeatedly\n\n**Decision point**: After 2-3 failures, switch to the fallback pattern rather than continuing to retry failing tools.\n\n### Step 2: Gather Known Domain Data\n\nCollect all data you already know or can reasonably infer:\n- Product specifications, prices, SKUs\n- Competitor information from context\n- Business rules and constraints\n- Historical data from previous task phases\n\nDocument this data in a structured format before embedding.\n\n### Step 3: Embed Data in run_shell Python Script\n\nCreate a Python script that embeds the known data directly as literals or constants:\n\n```python\nimport json\nimport os\nfrom datetime import datetime\n\n# ============================================\n# EMBEDDED DOMAIN DATA (known from context)\n# ============================================\nPRODUCT_DATA = {\n    \"sku_001\": {\n        \"name\": \"Product A\",\n        \"competitor_price\": 29.99,\n        \"weight_oz\": 12,\n        \"category\": \"beverage\"\n    },\n    \"sku_002\": {\n        \"name\": \"Product B\", \n        \"competitor_price\": 34.99,\n        \"weight_oz\": 16,\n        \"category\": \"snack\"\n    }\n}\n\nBUSINESS_RULES = {\n    \"margin_target\": 0.25,\n    \"price_floor\": 19.99,\n    \"price_ceiling\": 99.99\n}\n\n# ============================================\n# ANALYSIS LOGIC\n# ============================================\ndef analyze_products(products, rules):\n    results = {}\n    for sku, data in products.items():\n        price_per_oz = data[\"competitor_price\"] \u002F data[\"weight_oz\"]\n        recommended_price = data[\"competitor_price\"] * (1 + rules[\"margin_target\"])\n        recommended_price = max(rules[\"price_floor\"], min(rules[\"price_ceiling\"], recommended_price))\n        \n        results[sku] = {\n            **data,\n            \"price_per_oz\": round(price_per_oz, 2),\n            \"recommended_price\": round(recommended_price, 2),\n            \"analysis_timestamp\": datetime.now().isoformat()\n        }\n    return results\n\n# Execute analysis\nanalysis_results = analyze_products(PRODUCT_DATA, BUSINESS_RULES)\n\n# ============================================\n# PERSIST INTERMEDIATE DATA (audit trail)\n# ============================================\noutput_file = \"intermediate_analysis.json\"\nwith open(output_file, \"w\") as f:\n    json.dump({\n        \"metadata\": {\n            \"generated_at\": datetime.now().isoformat(),\n            \"source\": \"embedded_domain_data\",\n            \"fallback_reason\": \"tool_execution_failures\"\n        },\n        \"results\": analysis_results\n    }, f, indent=2)\n\n# Signal artifact location for downstream tools\nprint(f\"ARTIFACT_PATH:{os.path.abspath(output_file)}\")\n\n# Output results for immediate consumption\nprint(\"\\n=== ANALYSIS RESULTS ===\")\nprint(json.dumps(analysis_results, indent=2))\n```\n\n### Step 4: Execute via run_shell\n\nRun the embedded script using `run_shell`:\n\n```bash\npython3 \u003C\u003C 'EOF'\n[paste the full script from Step 3]\nEOF\n```\n\nOr save to a file first:\n\n```bash\ncat > analysis_script.py \u003C\u003C 'SCRIPT'\n[paste script content]\nSCRIPT\n\npython3 analysis_script.py\n```\n\n### Step 5: Persist and Verify Intermediate Results\n\nEnsure JSON files are created and contain valid data:\n\n```python\nimport json\n\n# Verify persistence\nwith open(\"intermediate_analysis.json\", \"r\") as f:\n   验证数据 = json.load(f)\n    assert \"results\" in 验证数据\n    assert \"metadata\" in 验证数据\n    print(f\"✓ Persisted {len(验证数据['results'])} records\")\n```\n\n### Step 6: Chain Subsequent Operations\n\nUse persisted JSON as input for downstream operations:\n\n```python\nimport json\n\n# Load previous intermediate results\nwith open(\"intermediate_analysis.json\", \"r\") as f:\n    previous_results = json.load(f)[\"results\"]\n\n# Build on previous work\nfor sku, data in previous_results.items():\n    # Continue analysis using persisted data\n    pass\n```\n\n## Best Practices\n\n### 1. Data Versioning\nAlways include timestamps and source metadata in persisted JSON:\n```json\n{\n  \"metadata\": {\n    \"generated_at\": \"2024-01-15T10:30:00\",\n    \"source\": \"embedded_domain_data\",\n    \"version\": \"1.0\"\n  },\n  \"results\": {...}\n}\n```\n\n### 2. Incremental Persistence\nSave intermediate results at each major step, not just at the end:\n```python\n# After each significant transformation\nwith open(f\"step_{step_num}_results.json\", \"w\") as f:\n    json.dump(current_state, f, indent=2)\n```\n\n### 3. Clear Artifact Signaling\nUse `ARTIFACT_PATH:` prefix to mark files for downstream tools:\n```python\nprint(f\"ARTIFACT_PATH:{os.path.abspath('output.json')}\")\n```\n\n### 4. Error Boundaries\nWrap operations in try\u002Fexcept to ensure partial results are saved:\n```python\ntry:\n    results = complex_analysis(data)\nexcept Exception as e:\n    print(f\"Warning: {e}, saving partial results\")\n    results = partial_results\n\nwith open(\"results.json\", \"w\") as f:\n    json.dump(results, f, indent=2)\n```\n\n### 5. Documentation Trail\nInclude fallback reason in metadata for post-execution analysis:\n```python\n\"metadata\": {\n    \"fallback_reason\": \"search_web and shell_agent failed 3x\",\n    \"original_approach\": \"web_research_then_analysis\",\n    \"fallback_approach\": \"embedded_data_direct_analysis\"\n}\n```\n\n## Example: Complete Fallback Workflow\n\n```python\n# ===== FALLBACK DATA GATHERING SCRIPT =====\nimport json\nimport os\nfrom datetime import datetime\n\n# Known data embedded directly (no external calls)\nKNOWN_COMPETITORS = {\n    \"competitor_a\": {\"product_x\": 24.99, \"product_y\": 34.99},\n    \"competitor_b\": {\"product_x\": 26.99, \"product_y\": 32.99}\n}\n\nOUR_PRODUCTS = [\"product_x\", \"product_y\"]\n\n# Step 1: Calculate benchmarks\nbenchmarks = {}\nfor product in OUR_PRODUCTS:\n    prices = [KNOWN_COMPETITORS[c][product] for c in KNOWN_COMPETITORS if product in KNOWN_COMPETITORS[c]]\n    benchmarks[product] = {\n        \"min_price\": min(prices),\n        \"max_price\": max(prices),\n        \"avg_price\": sum(prices) \u002F len(prices)\n    }\n\n# Step 2: Persist Step 1 results\nwith open(\"step1_benchmarks.json\", \"w\") as f:\n    json.dump(benchmarks, f, indent=2)\nprint(\"ARTIFACT_PATH:step1_benchmarks.json\")\n\n# Step 3: Generate recommendations\nrecommendations = {}\nfor product, benchmark in benchmarks.items():\n    recommendations[product] = {\n        \"recommended_price\": round(benchmark[\"avg_price\"] * 0.95, 2),\n        \"rationale\": f\"5% below competitor average of ${benchmark['avg_price']:.2f}\"\n    }\n\n# Step 4: Persist final results\nfinal_output = {\n    \"metadata\": {\n        \"created\": datetime.now().isoformat(),\n        \"method\": \"embedded_data_fallback\",\n        \"preceding_artifact\": \"step1_benchmarks.json\"\n    },\n    \"benchmarks\": benchmarks,\n    \"recommendations\": recommendations\n}\n\nwith open(\"final_recommendations.json\", \"w\") as f:\n    json.dump(final_output, f, indent=2)\nprint(\"ARTIFACT_PATH:final_recommendations.json\")\n\nprint(json.dumps(final_output, indent=2))\n```\n\n## Recovery and Audit\n\nAfter execution, verify the audit trail:\n\n```bash\n# List all generated artifacts\nls -la *.json\n\n# Validate JSON structure\npython3 -c \"import json; [json.load(open(f)) for f in ['step1_benchmarks.json', 'final_recommendations.json']]; print('✓ All JSON files valid')\"\n\n# Review metadata for fallback context\npython3 -c \"import json; print(json.load(open('final_recommendations.json'))['metadata'])\"\n```\n\n## When to Return to Primary Tools\n\nAfter completing the task with this fallback pattern:\n1. Document which tools failed and why\n2. Report the successful fallback completion\n3. Suggest investigating root cause of tool failures for future runs\n4. Note that the pattern preserved data integrity despite tool issues","# Resilient Data Gathering Workflow\n\n## Purpose\n\nWhen `search_web`, `shell_agent`, and `execute_code_sandbox` all fail repeatedly with 'unknown error' or similar tool execution failures, fall back to embedding known domain data directly into `run_shell` Python scripts and persisting intermediate data to JSON files for auditability and recovery.\n\n## When to Use This Pattern\n\nApply this pattern when:\n1. **Trigger condition**: 2-3 consecutive failures across multiple tools (`search_web`, `shell_agent`, `execute_code_sandbox`) with 'unknown error' messages\n2. **You have domain knowledge**: The required data is known or can be reasonably estimated from context\n3. **Auditability needed**: Intermediate results must be preserved for verification or rollback\n\n## Step-by-Step Instructions\n\n### Step 1: Recognize Tool Failure Pattern\n\nMonitor for repeated failures across multiple execution tools:\n- `search_web` returns errors or empty results\n- `shell_agent` fails to complete autonomous tasks\n- `execute_code_sandbox` throws 'unknown error' repeatedly\n\n**Decision point**: After 2-3 failures, switch to the fallback pattern rather than continuing to retry failing tools.\n\n### Step 2: Gather Known Domain Data\n\nCollect all data you already know or can reasonably infer:\n- Product specifications, prices, SKUs\n- Competitor information from context\n- Business rules and constraints\n- Historical data from previous task phases\n\nDocument this data in a structured format before embedding.\n\n### Step 3: Embed Data in run_shell Python Script\n\nCreate a Python script that embeds the known data directly as literals or constants:\n\n```python\nimport json\nimport os\nfrom datetime import datetime\n\n# ============================================\n# EMBEDDED DOMAIN DATA (known from context)\n# ============================================\nPRODUCT_DATA = {\n    \"sku_001\": {\n        \"name\": \"Product A\",\n        \"competitor_price\": 29.99,\n        \"weight_oz\": 12,\n        \"category\": \"beverage\"\n    },\n    \"sku_002\": {\n        \"name\": \"Product B\", \n        \"competitor_price\": 34.99,\n        \"weight_oz\": 16,\n        \"category\": \"snack\"\n    }\n}\n\nBUSINESS_RULES = {\n    \"margin_target\": 0.25,\n    \"price_floor\": 19.99,\n    \"price_ceiling\": 99.99\n}\n\n# ============================================\n# ANALYSIS LOGIC\n# ============================================\ndef analyze_products(products, rules):\n    results = {}\n    for sku, data in products.items():\n        price_per_oz = data[\"competitor_price\"] \u002F data[\"weight_oz\"]\n        recommended_price = data[\"competitor_price\"] * (1 + rules[\"margin_target\"])\n        recommended_price = max(rules[\"price_floor\"], min(rules[\"price_ceiling\"], recommended_price))\n        \n        results[sku] = {\n            **data,\n            \"price_per_oz\": round(price_per_oz, 2),\n            \"recommended_price\": round(recommended_price, 2),\n            \"analysis_timestamp\": datetime.now().isoformat()\n        }\n    return results\n\n# Execute analysis\nanalysis_results = analyze_products(PRODUCT_DATA, BUSINESS_RULES)\n\n# ============================================\n# PERSIST INTERMEDIATE DATA (audit trail)\n# ============================================\noutput_file = \"intermediate_analysis.json\"\nwith open(output_file, \"w\") as f:\n    json.dump({\n        \"metadata\": {\n            \"generated_at\": datetime.now().isoformat(),\n            \"source\": \"embedded_domain_data\",\n            \"fallback_reason\": \"tool_execution_failures\"\n        },\n        \"results\": analysis_results\n    }, f, indent=2)\n\n# Signal artifact location for downstream tools\nprint(f\"ARTIFACT_PATH:{os.path.abspath(output_file)}\")\n\n# Output results for immediate consumption\nprint(\"\\n=== ANALYSIS RESULTS ===\")\nprint(json.dumps(analysis_results, indent=2))\n```\n\n### Step 4: Execute via run_shell\n\nRun the embedded script using `run_shell`:\n\n```bash\npython3 \u003C\u003C 'EOF'\n[paste the full script from Step 3]\nEOF\n```\n\nOr save to a file first:\n\n```bash\ncat > analysis_script.py \u003C\u003C 'SCRIPT'\n[paste script content]\nSCRIPT\n\npython3 analysis_script.py\n```\n\n### Step 5: Persist and Verify Intermediate Results\n\nEnsure JSON files are created and contain valid data:\n\n```python\nimport json\n\n# Verify persistence\nwith open(\"intermediate_analysis.json\", \"r\") as f:\n   验证数据 = json.load(f)\n    assert \"results\" in 验证数据\n    assert \"metadata\" in 验证数据\n    print(f\"✓ Persisted {len(验证数据['results'])} records\")\n```\n\n### Step 6: Chain Subsequent Operations\n\nUse persisted JSON as input for downstream operations:\n\n```python\nimport json\n\n# Load previous intermediate results\nwith open(\"intermediate_analysis.json\", \"r\") as f:\n    previous_results = json.load(f)[\"results\"]\n\n# Build on previous work\nfor sku, data in previous_results.items():\n    # Continue analysis using persisted data\n    pass\n```\n\n## Best Practices\n\n### 1. Data Versioning\nAlways include timestamps and source metadata in persisted JSON:\n```json\n{\n  \"metadata\": {\n    \"generated_at\": \"2024-01-15T10:30:00\",\n    \"source\": \"embedded_domain_data\",\n    \"version\": \"1.0\"\n  },\n  \"results\": {...}\n}\n```\n\n### 2. Incremental Persistence\nSave intermediate results at each major step, not just at the end:\n```python\n# After each significant transformation\nwith open(f\"step_{step_num}_results.json\", \"w\") as f:\n    json.dump(current_state, f, indent=2)\n```\n\n### 3. Clear Artifact Signaling\nUse `ARTIFACT_PATH:` prefix to mark files for downstream tools:\n```python\nprint(f\"ARTIFACT_PATH:{os.path.abspath('output.json')}\")\n```\n\n### 4. Error Boundaries\nWrap operations in try\u002Fexcept to ensure partial results are saved:\n```python\ntry:\n    results = complex_analysis(data)\nexcept Exception as e:\n    print(f\"Warning: {e}, saving partial results\")\n    results = partial_results\n\nwith open(\"results.json\", \"w\") as f:\n    json.dump(results, f, indent=2)\n```\n\n### 5. Documentation Trail\nInclude fallback reason in metadata for post-execution analysis:\n```python\n\"metadata\": {\n    \"fallback_reason\": \"search_web and shell_agent failed 3x\",\n    \"original_approach\": \"web_research_then_analysis\",\n    \"fallback_approach\": \"embedded_data_direct_analysis\"\n}\n```\n\n## Example: Complete Fallback Workflow\n\n```python\n# ===== FALLBACK DATA GATHERING SCRIPT =====\nimport json\nimport os\nfrom datetime import datetime\n\n# Known data embedded directly (no external calls)\nKNOWN_COMPETITORS = {\n    \"competitor_a\": {\"product_x\": 24.99, \"product_y\": 34.99},\n    \"competitor_b\": {\"product_x\": 26.99, \"product_y\": 32.99}\n}\n\nOUR_PRODUCTS = [\"product_x\", \"product_y\"]\n\n# Step 1: Calculate benchmarks\nbenchmarks = {}\nfor product in OUR_PRODUCTS:\n    prices = [KNOWN_COMPETITORS[c][product] for c in KNOWN_COMPETITORS if product in KNOWN_COMPETITORS[c]]\n    benchmarks[product] = {\n        \"min_price\": min(prices),\n        \"max_price\": max(prices),\n        \"avg_price\": sum(prices) \u002F len(prices)\n    }\n\n# Step 2: Persist Step 1 results\nwith open(\"step1_benchmarks.json\", \"w\") as f:\n    json.dump(benchmarks, f, indent=2)\nprint(\"ARTIFACT_PATH:step1_benchmarks.json\")\n\n# Step 3: Generate recommendations\nrecommendations = {}\nfor product, benchmark in benchmarks.items():\n    recommendations[product] = {\n        \"recommended_price\": round(benchmark[\"avg_price\"] * 0.95, 2),\n        \"rationale\": f\"5% below competitor average of ${benchmark['avg_price']:.2f}\"\n    }\n\n# Step 4: Persist final results\nfinal_output = {\n    \"metadata\": {\n        \"created\": datetime.now().isoformat(),\n        \"method\": \"embedded_data_fallback\",\n        \"preceding_artifact\": \"step1_benchmarks.json\"\n    },\n    \"benchmarks\": benchmarks,\n    \"recommendations\": recommendations\n}\n\nwith open(\"final_recommendations.json\", \"w\") as f:\n    json.dump(final_output, f, indent=2)\nprint(\"ARTIFACT_PATH:final_recommendations.json\")\n\nprint(json.dumps(final_output, indent=2))\n```\n\n## Recovery and Audit\n\nAfter execution, verify the audit trail:\n\n```bash\n# List all generated artifacts\nls -la *.json\n\n# Validate JSON structure\npython3 -c \"import json; [json.load(open(f)) for f in ['step1_benchmarks.json', 'final_recommendations.json']]; print('✓ All JSON files valid')\"\n\n# Review metadata for fallback context\npython3 -c \"import json; print(json.load(open('final_recommendations.json'))['metadata'])\"\n```\n\n## When to Return to Primary Tools\n\nAfter completing the task with this fallback pattern:\n1. Document which tools failed and why\n2. Report the successful fallback completion\n3. Suggest investigating root cause of tool failures for future runs\n4. Note that the pattern preserved data integrity despite tool issues",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fresilient-data-gathering",944,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot","https:\u002F\u002Fgithub.com\u002FHKUDS","https:\u002F\u002Fsites.google.com\u002Fview\u002Fchaoh","2026-11-12 22:26:39",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add HKUDS\u002FAgentPilot --skill resilient-data-gathering",{"tool":53,"command":54},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill resilient-data-gathering",{"tool":56,"command":57},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill resilient-data-gathering","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fresilient-data-gathering\u002FSKILL.md",true,[61],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},".skill_id","OTHER","其他",38,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fresilient-data-gathering\u002F.skill_id",[68,88,107,131,154,177],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":34},"01M6HYB297NDABRERJRVG0K8R0","agentpilot","Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fplugins\u002Fagentpilot\u002Fskills\u002Fagentpilot\u002FSKILL.md",[],[70,75,76,77,78,79,80,81,82,83,84,85,86,87],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"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":34},"01M6HYAYWXTTE1J7DJM0MFNQ4H","remember","Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fskills\u002Fremember\u002FSKILL.md",[],[90,95,96,97,98,99,100,101,102,103,104,105,106],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":118,"publishedAt":34},"01M6HYAVMPM4SBDV60R2B5HPV8","skill-discovery","Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fskill-discovery\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[119,120,121,98,122,123,124,125,126,127,128,129,130,26],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":138,"publishedAt":34},"01M6HYAR811B3RB0M50RBEDGN6","delegate-task","Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fdelegate-task\u002FSKILL.md",[137],{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},[139,140,141,98,142,143,144,145,146,121,97,82,147,148,149,33,150,151,152,153],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","share","tasks","automation","MCP",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":34},"01M6HYAM9FSGV6E52AYENDQXYH","write-special-chars-ts-check","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-ts-check\u002FSKILL.md",[],[161,162,163,164,165,166,167,168,169,170,171,172,173,174,33,175,176],"write special chars ts check","write","check","type","files","filters","only","template","file","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":34},"01M6HYAH05HGV7SVWSVR8PJRQD","write-special-chars-readback","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of \u002Ftmp helper scripts.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-readback\u002FSKILL.md",[],[184,185,162,77,33,176,186,187,188,30,189,168,169,190,191,170],"write special chars readback","readback","helper","post","via","read","verification","cleanup"]