MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Implement fallback strategies when web-reading tools fail simultaneously
MITAuto-check passed
Install Web Tool Fallback
$ npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/OpenSpace web-tool-fallback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/web-tool-fallback .claude/skills/web-tool-fallback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "web-tool-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/web-tool-fallback into .claude/skills/web-tool-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-tool-fallback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/web-tool-fallbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/OpenSpace web-tool-fallback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/gdpval/skills/web-tool-fallback .agents/skills/web-tool-fallback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "web-tool-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/web-tool-fallback into .agents/skills/web-tool-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-tool-fallback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/OpenSpace web-tool-fallback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/gdpval/skills/web-tool-fallback .cursor/skills/web-tool-fallback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "web-tool-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/web-tool-fallback into .cursor/skills/web-tool-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-tool-fallback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/HKUDS/OpenSpace.git --path benchmarks/gdpval/skills/web-tool-fallback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/OpenSpace web-tool-fallback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/gdpval/skills/web-tool-fallback .gemini/skills/web-tool-fallback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "web-tool-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/web-tool-fallback into .gemini/skills/web-tool-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-tool-fallback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install HKUDS/OpenSpace web-tool-fallbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/gdpval/skills/web-tool-fallback .github/skills/web-tool-fallback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "web-tool-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/web-tool-fallback into .github/skills/web-tool-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-tool-fallback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HKUDS/OpenSpace web-tool-fallback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/gdpval/skills/web-tool-fallback .opencode/skills/web-tool-fallback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "web-tool-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/web-tool-fallback into .opencode/skills/web-tool-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web-tool-fallback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
web-tool-fallback- GitHub stars
- 7.7k
- Token cost
- ~1.9k tokens
- SKILL.md length
- 461 words
- Files
- 2
- Skills in repo
- 199
- Repo updated
- First seen
- Licence
- MIT
At a glance
Implement fallback strategies when web-reading tools fail simultaneously
- Works in 5 steps: Attempt Alternative Sources → Use execute_code_sandbox for Embedded… → Use execute_code_sandbox for Embedded… → …
- SKILL.md covers When to Use This Skill, Recognition Criteria, Fallback Procedure and Decision Tree, plus 3 more sections
- Calls python3; reaches web.archive.org
What it does
Web Tool Fallback is an agent skill from HKUDS/OpenSpace. Implement fallback strategies when web-reading tools fail simultaneously
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.
It works with Python. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.
Example prompts
- “/web-tool-fallback”
Requirements
- Python 3
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3827781. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
web.archive.org
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Web Tool Fallback loads about 1.9k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 461 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 461 words, ~1,898 tokens.
Download SKILL.mdSave it as
.claude/skills/web-tool-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- web-tool-fallback
- description
- Implement fallback strategies when web-reading tools fail simultaneously
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:
bash 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}") EOFCapture output to file for further processing:
bash 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
Show full SKILL.md (199 more words)Show less
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 normallyTask-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
© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in benchmarks/gdpval/skills/web-tool-fallback of HKUDS/OpenSpace.
- SKILL.md
- .skill_id
Open the folder on GitHubat commit 3827781
Compare with similar skills
Web Tool Fallback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Web Tool Fallback this skillHKUDS/OpenSpace | 7.7k | — | ~1.9k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| PDF Processinganthropics/skills | 180k | 48 repos | ~2k | Automated safety check: Pass | Proprietary | |
| NotebookLM Research AssistantPleasePrompto/notebooklm-skill | 7.8k | 13 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Manim Video Productionbrowser-use/video-use | 28k | 6 repos | ~3k | Automated safety check: Pass | MIT | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
PDF Processing
anthropics/skills
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
NotebookLM Research Assistant
PleasePrompto/notebooklm-skill
Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.
Manim Video Production
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
PPT Master
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
More from HKUDS/OpenSpace
All 199 skills in this repoAudio Track Production Workflow
HKUDS/OpenSpace
Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.
Cascade Failure Recovery
HKUDS/OpenSpace
Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
Sandbox Code Execution Fallback
HKUDS/OpenSpace
Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.
Code Execution Fallback
HKUDS/OpenSpace
A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.
Code Execution Fallback and Path Anchoring
HKUDS/OpenSpace
Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.
Code Execution Fallback E81068
HKUDS/OpenSpace
Fallback workflow for executing Python code when executecodesandbox fails repeatedly
Related
Works with
Questions about Web Tool Fallback
What does Web Tool Fallback do?
Implement fallback strategies when web-reading tools fail simultaneously. Web Tool Fallback is an agent skill from HKUDS/OpenSpace.
How do I install Web Tool Fallback in Claude Code?
Run `npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/web-tool-fallback in HKUDS/OpenSpace) into .claude/skills/web-tool-fallback in your project. Claude Code loads it when a task matches its description.
How do I install Web Tool Fallback in Codex?
Run `npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/web-tool-fallback in HKUDS/OpenSpace) into .agents/skills/web-tool-fallback in your project. Codex loads it when a task matches its description.
Can I use Web Tool Fallback in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/OpenSpace --skill web-tool-fallback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/web-tool-fallback, .gemini/skills/web-tool-fallback, .github/skills/web-tool-fallback and .opencode/skills/web-tool-fallback in your project.
What does Web Tool Fallback need to run?
Going by SKILL.md and its folder, Web Tool Fallback needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Web Tool Fallback access the network?
SKILL.md names 1 domain. In commands or code: web.archive.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Web Tool Fallback safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Web Tool Fallback use?
Web Tool Fallback is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Web Tool Fallback use?
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Web Tool Fallback?
Skills that share tags, products or a category with Web Tool Fallback: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Web Tool Fallback?
HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.
Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.