web-tool-fallback
Implement fallback strategies when web-reading tools fail simultaneously
- License 许可
- MIT
- 所属仓库
- AG064/OpenSpace
- 最近更新
- 2026-10-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- web-tool-fallback
- description
- Implement fallback strategies when web-reading tools fail simultaneously
02 资源文件 1
- 其他.skill_id31 B
03 SKILL.md 正文
Web Tool Fallback Strategy
When to Use This Skill
Apply this skill when all web-reading tools (read_webpage, search_web) fail simultaneously with unknown errors during a research or information-gathering task.
Recognition Criteria
Confirm this pattern before applying fallbacks:
- Multiple web tool calls have failed (not just one isolated failure)
- Errors are unknown/unexpected (not expected 404s or rate limits that can be handled normally)
- The information is still needed to complete the task
Fallback Procedure
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.
Step 1: Attempt Alternative Sources
Before abandoning web access, try these alternatives:
-
Alternative URLs:
- Archive.org / Wayback Machine versions
- Alternative domains (e.g., .org instead of .com)
- Different subdomains or paths
-
Simplified Requests:
- Try reading just the domain root
- Remove query parameters from URLs
- Try HTTP instead of HTTPS (or vice versa)
# Example: Generate alternative URL formats
original_url = "https://example.com/research/report?id=123"
alternatives = [
"https://example.com/research/report",
"http://example.com/research/report?id=123",
"https://web.archive.org/web/*/https://example.com/research/report"
]
Step 2: Use execute_code_sandbox for Embedded Knowledge
Step 2: Use execute_code_sandbox for Embedded Knowledge (May Fail)
When 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.
code = '''
# Generate structured information from embedded knowledge
evaluation_frameworks = {
"Kirkpatrick Model": ["Reaction", "Learning", "Behavior", "Results"],
"Bloom's Taxonomy": ["Remember", "Understand", "Apply", "Analyze", "Evaluate", "Create"],
"SMART Criteria": ["Specific", "Measurable", "Achievable", "Relevant", "Time-bound"]
}
# Create comprehensive reference material
for framework, levels in evaluation_frameworks.items():
print(f"## {framework}\\n")
for i, level in enumerate(levels, 1):
print(f"{i}. {level}")
print()
'''
If execute_code_sandbox returns any error (unknown error, timeout, execution failure):
- Do not retry execute_code_sandbox multiple times
- Immediately proceed to Step 2b (run_shell fallback)
- Document the sandbox failure in your Research Access Notes
- Established frameworks and methodologies
- Standard best practices
- Well-documented technical concepts
- Historical information that doesn't change frequently
### Step 2b: Fall Back to run_shell if execute_code_sandbox Fails
### Step 2b: Fall Back to run_shell if execute_code_sandbox Fails (REQUIRED)
**When to use**: execute_code_sandbox returns any error OR fails to produce output within reasonable time.
**Action**: Immediately switch to run_shell with direct Python execution. Do not continue attempting execute_code_sandbox.
1. **Use run_shell with direct Python execution** (simplest, most reliable):
1. **Use run_shell with direct Python execution**:
```bash
python3 -c "print('content from embedded knowledge')"
-
Use heredoc for multi-line scripts:
python3 << 'EOF' # Your Python code here frameworks = {"Kirkpatrick": ["Reaction", "Learning", "Behavior", "Results"]} for name, levels in frameworks.items(): print(f"## {name}") for level in levels: print(f"- {level}") EOF -
Capture output to file for further processing:
python3 -c "print('structured content')" > output.txt
Why run_shell works when execute_code_sandbox fails:
- Direct system Python execution bypasses sandbox restrictions
- No additional abstraction layer that could fail
- More reliable during cascading tool failures
- Should be your go-to when sandbox is compromised
Step 3: Create Document with Placeholder Citations
For tasks requiring formal documentation:
- Draft the document using available knowledge
- Mark uncertain citations clearly:
[WEB_ACCESS_LIMITED: URL https://example.com/source could not be accessed] - Use placeholder format for references:
[Reference needed: Topic - URL attempted but inaccessible]
Step 4: Document the Limitation for Stakeholders
Always create a transparent "Research Access Notes" section:
## Research Access Notes
**Access Limitation**: All web-reading tools failed simultaneously during research.
**Fallback Actions Taken**:
- [ ] Attempted alternative URLs: [Yes/No]
- [ ] Used embedded knowledge generation: [Yes/No]
- [ ] Created placeholders for citations: [Yes/No]
**Confidence Level**: [High/Medium/Low] - based on reliance on embedded knowledge vs. current web sources
**Recommendation**: Verify critical claims with current web sources when access is restored.
Decision Tree
All web tools failed?
├─ Yes → Try alternative URLs
│ ├─ Success → Complete task normally
│ └─ Failed → Can content be generated from embedded knowledge?
│ ├─ Yes → Try execute_code_sandbox (expect potential failure)
│ │ ├─ Success → Use output + document limitation
│ │ └─ Failed/Errors → **IMMEDIATELY** use run_shell + document limitation
│ └─ No → Create document with placeholders + notify Executive Director
│ └─ No → Create document with placeholders + notify Executive Director
└─ No → Handle individual failures normally
Task-Type Adaptations
| Task Type | Primary Fallback | Documentation Required |
|---|---|---|
| Research/Analysis | execute_code_sandbox | Access notes section |
| Document Creation | Placeholder citations | Limitation notice to Executive Director |
| Time-Sensitive | Proceed with available methods | Brief limitation note |
| Compliance/Legal | Escalate immediately | Full access failure report |
Example Application
# When gathering reference materials fails
try:
# Primary: read_webpage attempts (all failed)
pass
except:
# Fallback 1: Try alternative sources
alternative_content = execute_code_sandbox(generate_from_knowledge())
# Fallback 2: Create document with transparency
document = create_with_placeholders(
content=alternative_content,
citation_markers="[WEB_ACCESS_LIMITED]",
stakeholder_note="Executive Director: Web access unavailable, content from embedded knowledge"
)
Best Practices
- Be transparent: Always document when web access failed
- Preserve attempt records: Note which URLs/tools failed for future reference
- Distinguish knowledge types: Clearly separate embedded knowledge from current web-sourced information
- Prioritize critical info: If certain information is essential and cannot be generated, escalate rather than guess
- Enable verification: Make it easy for stakeholders to verify claims when access is restored
- Never stack failures: If execute_code_sandbox fails once, switch to run_shell immediately—do not retry the sandbox multiple times
- Complete all steps: Step 4 (Document Limitation) is mandatory, not optional—even if fallback succeeds
04 同仓库更多 Skills
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.
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 /tmp helper scripts.
write-special-chars-heredoc
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) by using a Python heredoc script executed via shell.
worldmonitor-reference
Curated architecture index of the WorldMonitor open-source dashboard. Reference for extracting patterns — vanilla TypeScript, Panel class hierarchy, service layer, CSS grid, API edge functions, refresh scheduler, and 60+ data source integrations.
virtual-list
Implement efficient virtual scrolling for rendering large lists with DOM recycling, chunk-based rendering, and performance optimizations
verify-directory-structure
Diagnose and resolve file access issues by first verifying the directory structure.