[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HY2FDN694201JX3X4YVRM0":3,"skill-same:01M6HY2FDN694201JX3X4YVRM0":60},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M6HY2FDN694201JX3X4YVRM0","web-tool-fallback",null,"Implement fallback strategies when web-reading tools fail simultaneously","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\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fweb-tool-fallback\u002FSKILL.md",[],[19,20,21,22,23,24,25,26],"web","tool","fallback","web tool fallback","implement","Tools","strategies","reading","2026-11-10 10:12:30",false,"---\nname: web-tool-fallback\ndescription: Implement fallback strategies when web-reading tools fail simultaneously\n---\n\n# Web Tool Fallback Strategy\n\n## When to Use This Skill\n\nApply this skill when **all** web-reading tools (`read_webpage`, `search_web`) fail simultaneously with unknown errors during a research or information-gathering task.\n\n## Recognition Criteria\n\nConfirm this pattern before applying fallbacks:\n- Multiple web tool calls have failed (not just one isolated failure)\n- Errors are unknown\u002Funexpected (not expected 404s or rate limits that can be handled normally)\n- The information is still needed to complete the task\n\n## Fallback Procedure\n\n**Critical**: execute_code_sandbox may also fail during system-wide issues. Always be prepared to immediately fall back to run_shell if sandbox execution returns errors.\n\n### Step 1: Attempt Alternative Sources\n\nBefore abandoning web access, try these alternatives:\n\n1. **Alternative URLs**: \n   - Archive.org \u002F Wayback Machine versions\n   - Alternative domains (e.g., .org instead of .com)\n   - Different subdomains or paths\n\n2. **Simplified Requests**:\n   - Try reading just the domain root\n   - Remove query parameters from URLs\n   - Try HTTP instead of HTTPS (or vice versa)\n\n```python\n# Example: Generate alternative URL formats\noriginal_url = \"https:\u002F\u002Fexample.com\u002Fresearch\u002Freport?id=123\"\nalternatives = [\n    \"https:\u002F\u002Fexample.com\u002Fresearch\u002Freport\",\n    \"http:\u002F\u002Fexample.com\u002Fresearch\u002Freport?id=123\",\n    \"https:\u002F\u002Fweb.archive.org\u002Fweb\u002F*\u002Fhttps:\u002F\u002Fexample.com\u002Fresearch\u002Freport\"\n]\n```\n\n### Step 2: Use execute_code_sandbox for Embedded Knowledge\n### Step 2: Use execute_code_sandbox for Embedded Knowledge (May Fail)\n\nWhen web access is unavailable, generate content from reliable embedded knowledge. **Note**: execute_code_sandbox can fail during cascading system issues—if it returns errors, immediately proceed to Step 2b.\n\n```python\ncode = '''\n# Generate structured information from embedded knowledge\nevaluation_frameworks = {\n    \"Kirkpatrick Model\": [\"Reaction\", \"Learning\", \"Behavior\", \"Results\"],\n    \"Bloom's Taxonomy\": [\"Remember\", \"Understand\", \"Apply\", \"Analyze\", \"Evaluate\", \"Create\"],\n    \"SMART Criteria\": [\"Specific\", \"Measurable\", \"Achievable\", \"Relevant\", \"Time-bound\"]\n}\n\n# Create comprehensive reference material\nfor framework, levels in evaluation_frameworks.items():\n    print(f\"## {framework}\\\\n\")\n    for i, level in enumerate(levels, 1):\n        print(f\"{i}. {level}\")\n    print()\n'''\n```\n\n**If execute_code_sandbox returns any error** (unknown error, timeout, execution failure):\n- **Do not retry** execute_code_sandbox multiple times\n- **Immediately proceed to Step 2b** (run_shell fallback)\n- Document the sandbox failure in your Research Access Notes\n\n```python\n- Established frameworks and methodologies\n- Standard best practices\n- Well-documented technical concepts\n- Historical information that doesn't change frequently\n\n### Step 2b: Fall Back to run_shell if execute_code_sandbox Fails\n### Step 2b: Fall Back to run_shell if execute_code_sandbox Fails (REQUIRED)\n\n**When to use**: execute_code_sandbox returns any error OR fails to produce output within reasonable time.\n\n**Action**: Immediately switch to run_shell with direct Python execution. Do not continue attempting execute_code_sandbox.\n\n1. **Use run_shell with direct Python execution** (simplest, most reliable):\n\n1. **Use run_shell with direct Python execution**:\n   ```bash\n   python3 -c \"print('content from embedded knowledge')\"\n   ```\n\n2. **Use heredoc for multi-line scripts**:\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   # Your Python code here\n   frameworks = {\"Kirkpatrick\": [\"Reaction\", \"Learning\", \"Behavior\", \"Results\"]}\n   for name, levels in frameworks.items():\n       print(f\"## {name}\")\n       for level in levels:\n           print(f\"- {level}\")\n   EOF\n   ```\n\n3. **Capture output to file for further processing**:\n    ```bash\n    python3 -c \"print('structured content')\" > output.txt\n    ```\n\n**Why run_shell works when execute_code_sandbox fails**:\n- Direct system Python execution bypasses sandbox restrictions\n- No additional abstraction layer that could fail\n- More reliable during cascading tool failures\n- Should be your go-to when sandbox is compromised\n\n### Step 3: Create Document with Placeholder Citations\n\nFor tasks requiring formal documentation:\n\n1. **Draft the document** using available knowledge\n2. **Mark uncertain citations** clearly:\n   ```\n   [WEB_ACCESS_LIMITED: URL https:\u002F\u002Fexample.com\u002Fsource could not be accessed]\n   ```\n3. **Use placeholder format** for references:\n   ```\n   [Reference needed: Topic - URL attempted but inaccessible]\n   ```\n\n### Step 4: Document the Limitation for Stakeholders\n\nAlways create a transparent \"Research Access Notes\" section:\n\n```markdown\n## Research Access Notes\n\n**Access Limitation**: All web-reading tools failed simultaneously during research.\n\n**Fallback Actions Taken**:\n- [ ] Attempted alternative URLs: [Yes\u002FNo]\n- [ ] Used embedded knowledge generation: [Yes\u002FNo]\n- [ ] Created placeholders for citations: [Yes\u002FNo]\n\n**Confidence Level**: [High\u002FMedium\u002FLow] - based on reliance on embedded knowledge vs. current web sources\n\n**Recommendation**: Verify critical claims with current web sources when access is restored.\n```\n\n## Decision Tree\n\n```\nAll web tools failed?\n├─ Yes → Try alternative URLs\n│   ├─ Success → Complete task normally\n│   └─ Failed → Can content be generated from embedded knowledge?\n│       ├─ Yes → Try execute_code_sandbox (expect potential failure)\n│       │   ├─ Success → Use output + document limitation\n│       │   └─ Failed\u002FErrors → **IMMEDIATELY** use run_shell + document limitation\n│       └─ No → Create document with placeholders + notify Executive Director\n│       └─ No → Create document with placeholders + notify Executive Director\n└─ No → Handle individual failures normally\n```\n\n## Task-Type Adaptations\n\n| Task Type | Primary Fallback | Documentation Required |\n|-----------|-----------------|----------------------|\n| Research\u002FAnalysis | execute_code_sandbox | Access notes section |\n| Document Creation | Placeholder citations | Limitation notice to Executive Director |\n| Time-Sensitive | Proceed with available methods | Brief limitation note |\n| Compliance\u002FLegal | Escalate immediately | Full access failure report |\n\n## Example Application\n\n```python\n# When gathering reference materials fails\ntry:\n    # Primary: read_webpage attempts (all failed)\n    pass\nexcept:\n    # Fallback 1: Try alternative sources\n    alternative_content = execute_code_sandbox(generate_from_knowledge())\n    \n    # Fallback 2: Create document with transparency\n    document = create_with_placeholders(\n        content=alternative_content,\n        citation_markers=\"[WEB_ACCESS_LIMITED]\",\n        stakeholder_note=\"Executive Director: Web access unavailable, content from embedded knowledge\"\n    )\n```\n\n## Best Practices\n\n1. **Be transparent**: Always document when web access failed\n2. **Preserve attempt records**: Note which URLs\u002Ftools failed for future reference\n3. **Distinguish knowledge types**: Clearly separate embedded knowledge from current web-sourced information\n4. **Prioritize critical info**: If certain information is essential and cannot be generated, escalate rather than guess\n5. **Enable verification**: Make it easy for stakeholders to verify claims when access is restored\n6. **Never stack failures**: If execute_code_sandbox fails once, switch to run_shell immediately—do not retry the sandbox multiple times\n7. **Complete all steps**: Step 4 (Document Limitation) is mandatory, not optional—even if fallback succeeds\n","# Web Tool Fallback Strategy\n\n## When to Use This Skill\n\nApply this skill when **all** web-reading tools (`read_webpage`, `search_web`) fail simultaneously with unknown errors during a research or information-gathering task.\n\n## Recognition Criteria\n\nConfirm this pattern before applying fallbacks:\n- Multiple web tool calls have failed (not just one isolated failure)\n- Errors are unknown\u002Funexpected (not expected 404s or rate limits that can be handled normally)\n- The information is still needed to complete the task\n\n## Fallback Procedure\n\n**Critical**: execute_code_sandbox may also fail during system-wide issues. Always be prepared to immediately fall back to run_shell if sandbox execution returns errors.\n\n### Step 1: Attempt Alternative Sources\n\nBefore abandoning web access, try these alternatives:\n\n1. **Alternative URLs**: \n   - Archive.org \u002F Wayback Machine versions\n   - Alternative domains (e.g., .org instead of .com)\n   - Different subdomains or paths\n\n2. **Simplified Requests**:\n   - Try reading just the domain root\n   - Remove query parameters from URLs\n   - Try HTTP instead of HTTPS (or vice versa)\n\n```python\n# Example: Generate alternative URL formats\noriginal_url = \"https:\u002F\u002Fexample.com\u002Fresearch\u002Freport?id=123\"\nalternatives = [\n    \"https:\u002F\u002Fexample.com\u002Fresearch\u002Freport\",\n    \"http:\u002F\u002Fexample.com\u002Fresearch\u002Freport?id=123\",\n    \"https:\u002F\u002Fweb.archive.org\u002Fweb\u002F*\u002Fhttps:\u002F\u002Fexample.com\u002Fresearch\u002Freport\"\n]\n```\n\n### Step 2: Use execute_code_sandbox for Embedded Knowledge\n### Step 2: Use execute_code_sandbox for Embedded Knowledge (May Fail)\n\nWhen web access is unavailable, generate content from reliable embedded knowledge. **Note**: execute_code_sandbox can fail during cascading system issues—if it returns errors, immediately proceed to Step 2b.\n\n```python\ncode = '''\n# Generate structured information from embedded knowledge\nevaluation_frameworks = {\n    \"Kirkpatrick Model\": [\"Reaction\", \"Learning\", \"Behavior\", \"Results\"],\n    \"Bloom's Taxonomy\": [\"Remember\", \"Understand\", \"Apply\", \"Analyze\", \"Evaluate\", \"Create\"],\n    \"SMART Criteria\": [\"Specific\", \"Measurable\", \"Achievable\", \"Relevant\", \"Time-bound\"]\n}\n\n# Create comprehensive reference material\nfor framework, levels in evaluation_frameworks.items():\n    print(f\"## {framework}\\\\n\")\n    for i, level in enumerate(levels, 1):\n        print(f\"{i}. {level}\")\n    print()\n'''\n```\n\n**If execute_code_sandbox returns any error** (unknown error, timeout, execution failure):\n- **Do not retry** execute_code_sandbox multiple times\n- **Immediately proceed to Step 2b** (run_shell fallback)\n- Document the sandbox failure in your Research Access Notes\n\n```python\n- Established frameworks and methodologies\n- Standard best practices\n- Well-documented technical concepts\n- Historical information that doesn't change frequently\n\n### Step 2b: Fall Back to run_shell if execute_code_sandbox Fails\n### Step 2b: Fall Back to run_shell if execute_code_sandbox Fails (REQUIRED)\n\n**When to use**: execute_code_sandbox returns any error OR fails to produce output within reasonable time.\n\n**Action**: Immediately switch to run_shell with direct Python execution. Do not continue attempting execute_code_sandbox.\n\n1. **Use run_shell with direct Python execution** (simplest, most reliable):\n\n1. **Use run_shell with direct Python execution**:\n   ```bash\n   python3 -c \"print('content from embedded knowledge')\"\n   ```\n\n2. **Use heredoc for multi-line scripts**:\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   # Your Python code here\n   frameworks = {\"Kirkpatrick\": [\"Reaction\", \"Learning\", \"Behavior\", \"Results\"]}\n   for name, levels in frameworks.items():\n       print(f\"## {name}\")\n       for level in levels:\n           print(f\"- {level}\")\n   EOF\n   ```\n\n3. **Capture output to file for further processing**:\n    ```bash\n    python3 -c \"print('structured content')\" > output.txt\n    ```\n\n**Why run_shell works when execute_code_sandbox fails**:\n- Direct system Python execution bypasses sandbox restrictions\n- No additional abstraction layer that could fail\n- More reliable during cascading tool failures\n- Should be your go-to when sandbox is compromised\n\n### Step 3: Create Document with Placeholder Citations\n\nFor tasks requiring formal documentation:\n\n1. **Draft the document** using available knowledge\n2. **Mark uncertain citations** clearly:\n   ```\n   [WEB_ACCESS_LIMITED: URL https:\u002F\u002Fexample.com\u002Fsource could not be accessed]\n   ```\n3. **Use placeholder format** for references:\n   ```\n   [Reference needed: Topic - URL attempted but inaccessible]\n   ```\n\n### Step 4: Document the Limitation for Stakeholders\n\nAlways create a transparent \"Research Access Notes\" section:\n\n```markdown\n## Research Access Notes\n\n**Access Limitation**: All web-reading tools failed simultaneously during research.\n\n**Fallback Actions Taken**:\n- [ ] Attempted alternative URLs: [Yes\u002FNo]\n- [ ] Used embedded knowledge generation: [Yes\u002FNo]\n- [ ] Created placeholders for citations: [Yes\u002FNo]\n\n**Confidence Level**: [High\u002FMedium\u002FLow] - based on reliance on embedded knowledge vs. current web sources\n\n**Recommendation**: Verify critical claims with current web sources when access is restored.\n```\n\n## Decision Tree\n\n```\nAll web tools failed?\n├─ Yes → Try alternative URLs\n│   ├─ Success → Complete task normally\n│   └─ Failed → Can content be generated from embedded knowledge?\n│       ├─ Yes → Try execute_code_sandbox (expect potential failure)\n│       │   ├─ Success → Use output + document limitation\n│       │   └─ Failed\u002FErrors → **IMMEDIATELY** use run_shell + document limitation\n│       └─ No → Create document with placeholders + notify Executive Director\n│       └─ No → Create document with placeholders + notify Executive Director\n└─ No → Handle individual failures normally\n```\n\n## Task-Type Adaptations\n\n| Task Type | Primary Fallback | Documentation Required |\n|-----------|-----------------|----------------------|\n| Research\u002FAnalysis | execute_code_sandbox | Access notes section |\n| Document Creation | Placeholder citations | Limitation notice to Executive Director |\n| Time-Sensitive | Proceed with available methods | Brief limitation note |\n| Compliance\u002FLegal | Escalate immediately | Full access failure report |\n\n## Example Application\n\n```python\n# When gathering reference materials fails\ntry:\n    # Primary: read_webpage attempts (all failed)\n    pass\nexcept:\n    # Fallback 1: Try alternative sources\n    alternative_content = execute_code_sandbox(generate_from_knowledge())\n    \n    # Fallback 2: Create document with transparency\n    document = create_with_placeholders(\n        content=alternative_content,\n        citation_markers=\"[WEB_ACCESS_LIMITED]\",\n        stakeholder_note=\"Executive Director: Web access unavailable, content from embedded knowledge\"\n    )\n```\n\n## Best Practices\n\n1. **Be transparent**: Always document when web access failed\n2. **Preserve attempt records**: Note which URLs\u002Ftools failed for future reference\n3. **Distinguish knowledge types**: Clearly separate embedded knowledge from current web-sourced information\n4. **Prioritize critical info**: If certain information is essential and cannot be generated, escalate rather than guess\n5. **Enable verification**: Make it easy for stakeholders to verify claims when access is restored\n6. **Never stack failures**: If execute_code_sandbox fails once, switch to run_shell immediately—do not retry the sandbox multiple times\n7. **Complete all steps**: Step 4 (Document Limitation) is mandatory, not optional—even if fallback succeeds\n",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fweb-tool-fallback",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":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add HKUDS\u002FAgentPilot --skill web-tool-fallback",{"tool":46,"command":47},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill web-tool-fallback",{"tool":49,"command":50},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill web-tool-fallback","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fweb-tool-fallback\u002FSKILL.md",true,[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},".skill_id","OTHER","其他",31,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fweb-tool-fallback\u002F.skill_id",[61,81,100,124,147,170],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":27},"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",[],[63,68,69,70,71,72,73,74,75,76,77,78,79,80],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":27},"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",[],[83,88,89,90,91,92,93,94,95,96,97,98,99],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":111,"publishedAt":27},"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",[106],{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[112,113,114,91,115,116,117,118,119,120,121,122,123,24],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":131,"publishedAt":27},"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",[130],{"categoryNo":107,"categoryName":108,"taxonomyType":109,"taxonomyTypeDesc":110},[132,133,134,91,135,136,137,138,139,114,90,75,140,20,141,142,143,144,145,146],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","stack","for","share","tasks","automation","MCP",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":27},"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",[],[154,155,156,157,158,159,160,161,162,163,164,165,166,167,142,168,169],"write special chars ts check","write","check","type","files","filters","only","template","file","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":27},"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",[],[177,178,155,70,142,169,179,180,181,182,183,161,162,184,185,163],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]