Mysearch
skernelx/MySearch-Proxy
DEFAULT search skill for OpenClaw. An agent skill from skernelx/MySearch-Proxy.
Graceful degradation workflow for continuing tasks when web search tools fail, using internal knowledge with verification caveats
Install Search Fallback Workflow
$ npx skills add HKUDS/OpenSpace --skill search-fallback-workflow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/OpenSpace search-fallback-workflow --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/search-fallback-workflow .claude/skills/search-fallback-workflow && 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 "search-fallback-workflow" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/search-fallback-workflow into .claude/skills/search-fallback-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search-fallback-workflow", 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/search-fallback-workflowType 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 search-fallback-workflow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/OpenSpace search-fallback-workflow --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/search-fallback-workflow .agents/skills/search-fallback-workflow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "search-fallback-workflow" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/search-fallback-workflow into .agents/skills/search-fallback-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search-fallback-workflow", 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 search-fallback-workflow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/OpenSpace search-fallback-workflow --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/search-fallback-workflow .cursor/skills/search-fallback-workflow && 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 "search-fallback-workflow" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/search-fallback-workflow into .cursor/skills/search-fallback-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search-fallback-workflow", 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/search-fallback-workflow--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 search-fallback-workflow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/OpenSpace search-fallback-workflow --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/search-fallback-workflow .gemini/skills/search-fallback-workflow && 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 "search-fallback-workflow" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/search-fallback-workflow into .gemini/skills/search-fallback-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search-fallback-workflow", 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 search-fallback-workflowInstalls 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 search-fallback-workflow -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/search-fallback-workflow .github/skills/search-fallback-workflow && 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 "search-fallback-workflow" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/search-fallback-workflow into .github/skills/search-fallback-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search-fallback-workflow", 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 search-fallback-workflow -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 search-fallback-workflow --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/search-fallback-workflow .opencode/skills/search-fallback-workflow && 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 "search-fallback-workflow" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/search-fallback-workflow into .opencode/skills/search-fallback-workflow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "search-fallback-workflow", 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
search-fallback-workflow- GitHub stars
- 7.7k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 326 words
- Files
- 2
- Skills in repo
- 199
- Repo updated
- First seen
- Licence
- MIT
At a glance
Graceful degradation workflow for continuing tasks when web search tools fail, using internal knowledge with verification caveats
- Works in 5 steps: Detect Search Failure → Assess Feasibility → Proceed with Internal Knowledge → …
- Tasks that involve Error handling
- SKILL.md covers When to Apply, Core Pattern, Implementation Template and Code Pattern for Agents, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Search Fallback Workflow is an agent skill from HKUDS/OpenSpace. Graceful degradation workflow for continuing tasks when web search tools fail, using internal knowledge with verification caveats
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.
It sits in Productivity & Automation, covering Error handling and Web search. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.
When your agent uses it
- Tasks that involve Error handling
- Tasks that involve Web search
Example prompts
- “/search-fallback-workflow”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Detect Search Failure
- Assess Feasibility
- Proceed with Internal Knowledge
- Flag for Verification
- Document Limitations
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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Search Fallback Workflow loads about 1.2k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 326 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). 326 words, ~1,164 tokens.
Download SKILL.mdSave it as
.claude/skills/search-fallback-workflow/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- search-fallback-workflow
- description
- Graceful degradation workflow for continuing tasks when web search tools fail, using internal knowledge with verification caveats
Search Fallback Workflow
When to Apply
Use this workflow when:
search_webtool fails repeatedly (typically 2+ consecutive failures)- External information is needed but unavailable due to tool limitations
- Task completion is still possible with reasonable confidence using internal knowledge
- The output can include appropriate caveats about verification needs
Core Pattern
Detect Search Failure
- Monitor
search_webresponses for errors, empty results, or timeouts - After 2 consecutive failures, assess whether the task can proceed without fresh data
- Monitor
Assess Feasibility
- Determine if internal knowledge is sufficient for the task at hand
- Identify which sections/claims require external verification
- Evaluate risk level: Can the task proceed safely with caveats?
Proceed with Internal Knowledge
- Continue the task using well-established facts, regulations, or principles
- Prioritize accuracy over completeness when uncertain
- Use conservative language for claims that cannot be verified
Flag for Verification
- Clearly mark any claims that should be verified:
markdown [VERIFICATION NEEDED: Search tool unavailable during generation] - Include a verification checklist in the execution summary
- Distinguish between high-confidence and low-confidence assertions
- Clearly mark any claims that should be verified:
Document Limitations
- Include an explicit note in the output about search unavailability
- List specific items requiring follow-up verification
- Provide recommendations for manual verification steps
Implementation Template
## Execution Notes
**Search Tool Status**: Unavailable during generation
**Confidence Levels**:
- ✓ High confidence: Established regulations, well-documented facts
- ⚠ Medium confidence: Industry standards, commonly accepted practices
- ✗ Requires verification: Time-sensitive data, recent changes, specific citations
**Verification Checklist**:
- [ ] Verify citation: [specific reference]
- [ ] Confirm current status: [specific item]
- [ ] Review recent updates: [specific topic]Code Pattern for Agents
# Pseudocode for search fallback detection
search_attempts = 0
max_search_attempts = 2
search_failed = False
for query in required_searches:
result = search_web(query)
if result.success:
process_result(result)
else:
search_attempts += 1
if search_attempts >= max_search_attempts:
search_failed = True
log_warning("Search tool unavailable, proceeding with fallback")
break
if search_failed:
# Apply graceful degradation
content = generate_with_internal_knowledge()
add_verification_flags(content)
document_limitations_in_summary()Example Output Structure
When using this fallback, structure documents with clear sections:
# Document Title
## Disclaimer
This document was generated with limited access to external verification tools.
Items marked with [VERIFICATION NEEDED] should be confirmed before final use.
## Content Sections
[Standard content with internal knowledge]
## Items Requiring Verification
- Topic A: Current regulatory status needs confirmation
- Topic B: Recent policy changes should be checked
- Topic C: Specific citations require source validation
## Recommendations
1. Cross-reference with official sources
2. Verify time-sensitive information
3. Consult subject matter experts for critical decisionsBest Practices
- Don't fabricate citations - Better to flag as unverified than invent sources
- Use conservative language - "Generally," "Typically," "Commonly" instead of absolutes
- Prioritize safety - If misinformation could cause harm, recommend manual verification
- Track what's missing - Maintain a clear list of items needing follow-up
- Be transparent - Clearly communicate limitations to end users
When NOT to Use This Pattern
- Tasks requiring current/real-time data (stock prices, news, weather)
- Legal or medical advice requiring authoritative sources
- Compliance documentation where citations are mandatory
- Situations where incorrect information could cause significant harm
Related Patterns
citation-management: Handling references and sources in documentserror-recovery-workflow: General patterns for tool failure recoveryconfidence-annotation: Marking certainty levels in generated content
© 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/search-fallback-workflow of HKUDS/OpenSpace.
- SKILL.md
- .skill_id
Open the folder on GitHubat commit 3827781
Compare with similar skills
Search Fallback Workflow 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 |
|---|---|---|---|---|---|---|
| Search Fallback Workflow this skillHKUDS/OpenSpace | 7.7k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Mysearchskernelx/MySearch-Proxy | 159 | — | ~1.4k | Automated safety check: Notes | MIT | |
| Z.AI CLInumman-ali/zai-cli | 110 | — | ~528 | Automated safety check: Pass | MIT | |
| A Stock Predictiondigoal/blog | 8.6k | — | ~2.2k | Automated safety check: Pass | GPL-2.0 | |
| Oma Searchfirst-fluke/oh-my-agent | 1.3k | — | ~2k | Automated safety check: Pass | MIT | |
| Us Stock Predictiondigoal/blog | 8.6k | — | ~1.9k | Automated safety check: Warn | GPL-2.0 |
Similar skills
Z.AI CLI
numman-ali/zai-cli
Command-line access to Z.AI vision analysis, web search, page reading and GitHub repo exploration through npx zai-cli, using an API key.
A Stock Prediction
digoal/blog
A股个股次日(T+1)走势预测 skill。当用户输入A股股票代码(如 600519、000858、300750、688981、430090)或公司名称(如"贵州茅台"、"宁德时代"、"比亚迪"),并要求预测次日走势、给出交易计划、评估盈亏概率时,触发本 skill。skill 会用 mcpMiniMaxwebsearch…
Oma Search
first-fluke/oh-my-agent
Intent-based search router with trust scoring. An agent skill from first-fluke/oh-my-agent.
Us Stock Prediction
digoal/blog
美股个股次日走势预测 skill。当用户输入美股股票代码(如 AAPL、TSLA)或公司名称(如 "苹果"、"特斯拉"),并要求预测次日(T+1)走势、给出交易计划、评估盈亏概率时,触发本 skill。skill 会用 mcpMiniMaxwebsearch 搜证盘前 90…
External Reference Research
majiayu000/claude-skill-registry
Specialized agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search.
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
Categories
Questions about Search Fallback Workflow
What does Search Fallback Workflow do?
Graceful degradation workflow for continuing tasks when web search tools fail, using internal knowledge with verification caveats. Search Fallback Workflow is an agent skill from HKUDS/OpenSpace.
When should I use Search Fallback Workflow?
Search Fallback Workflow fits situations like: tasks that involve Error handling; tasks that involve Web search.
How do I install Search Fallback Workflow in Claude Code?
Run `npx skills add HKUDS/OpenSpace --skill search-fallback-workflow -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/search-fallback-workflow in HKUDS/OpenSpace) into .claude/skills/search-fallback-workflow in your project. Claude Code loads it when a task matches its description.
How do I install Search Fallback Workflow in Codex?
Run `npx skills add HKUDS/OpenSpace --skill search-fallback-workflow -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/search-fallback-workflow in HKUDS/OpenSpace) into .agents/skills/search-fallback-workflow in your project. Codex loads it when a task matches its description.
Can I use Search Fallback Workflow 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 search-fallback-workflow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/search-fallback-workflow, .gemini/skills/search-fallback-workflow, .github/skills/search-fallback-workflow and .opencode/skills/search-fallback-workflow in your project.
What does Search Fallback Workflow need to run?
SKILL.md names no scripts, command-line tools or credentials: Search Fallback Workflow is instructions for the agent only. Our summary lists: Python 3.
Does Search Fallback Workflow access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Search Fallback Workflow 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 Search Fallback Workflow use?
Search Fallback Workflow 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 Search Fallback Workflow use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 Search Fallback Workflow?
Skills that share tags, products or a category with Search Fallback Workflow: Mysearch (skernelx/MySearch-Proxy, 159 stars), Z.AI CLI (numman-ali/zai-cli, 110 stars), A Stock Prediction (digoal/blog, 8.6k stars) and Oma Search (first-fluke/oh-my-agent, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Search Fallback Workflow?
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.