Agent skill

Research Fallback

Handle web research failures by pivoting to internal knowledge for content generation

MITAuto-check passed

Install Research Fallback

skills CLI

$ npx skills add HKUDS/OpenSpace --skill research-fallback -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace research-fallback --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/research-fallback .claude/skills/research-fallback && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "research-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/research-fallback into .claude/skills/research-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-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

$skill-installer install https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/research-fallback

Type 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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill research-fallback -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace research-fallback --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .agents/skills && cp -r skills-src/benchmarks/gdpval/skills/research-fallback .agents/skills/research-fallback && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "research-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/research-fallback into .agents/skills/research-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill research-fallback -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace research-fallback --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/benchmarks/gdpval/skills/research-fallback .cursor/skills/research-fallback && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "research-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/research-fallback into .cursor/skills/research-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-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

$ gemini skills install https://github.com/HKUDS/OpenSpace.git --path benchmarks/gdpval/skills/research-fallback

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill research-fallback -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace research-fallback --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/benchmarks/gdpval/skills/research-fallback .gemini/skills/research-fallback && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "research-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/research-fallback into .gemini/skills/research-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-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.

GitHub CLI

$ gh skill install HKUDS/OpenSpace research-fallback

Installs 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).

skills CLI

$ npx skills add HKUDS/OpenSpace --skill research-fallback -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .github/skills && cp -r skills-src/benchmarks/gdpval/skills/research-fallback .github/skills/research-fallback && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "research-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/research-fallback into .github/skills/research-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-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.

skills CLI

$ npx skills add HKUDS/OpenSpace --skill research-fallback -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HKUDS/OpenSpace research-fallback --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/benchmarks/gdpval/skills/research-fallback .opencode/skills/research-fallback && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "research-fallback" agent skill from https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/research-fallback into .opencode/skills/research-fallback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-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: research-fallback
GitHub stars: 7.7k
Token cost: ~1.1k tokens
SKILL.md length: 435 words
Files: 2
Skills in repo: 199
Repo updated: Aug 12, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Handle web research failures by pivoting to internal knowledge for content generation

Works in 5 steps: Attempt External Research First → Detect Tool Failure → Pivot to Internal Knowledge → …
SKILL.md covers When to Use, Workflow Steps, Example Decision Flow and Best Practices, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Research Fallback is an agent skill from HKUDS/OpenSpace. Handle web research failures by pivoting to internal knowledge for content generation

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

Example prompts

“/research-fallback”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Attempt External Research First
Detect Tool Failure
Pivot to Internal Knowledge
Generate Content with Appropriate Disclaimers
Complete File Creation

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.
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

Research Fallback loads about 1.1k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 435 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~26
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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). 435 words, ~1,074 tokens.

Download SKILL.mdSave it as .claude/skills/research-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: research-fallback
description: Handle web research failures by pivoting to internal knowledge for content generation

Research Fallback Workflow

This skill provides a workflow for handling tasks that require external research when web search or webpage reading tools fail due to network issues or tool unavailability.

When to Use

Task requires external research (legal analysis, market research, technical documentation, etc.)
Web search or webpage reading tools are failing or unavailable
You have sufficient internal knowledge to proceed with reasonable accuracy
Task completion is prioritized over perfect external sourcing

Workflow Steps

Step 1: Attempt External Research First

Begin by attempting to use available web research tools:

1. Use search_web for current information, statistics, or recent developments
2. Use read_webpage for detailed source material when URLs are provided
3. Document what you attempted to find

Step 2: Detect Tool Failure

Recognize when to pivot:

Web search returns errors, timeouts, or empty results
Page extraction fails repeatedly
Network errors persist after 1-2 retry attempts
Tool explicitly reports unavailability

Do not spend excessive time retrying failed tools. After 1-2 attempts, proceed to Step 3.

Step 3: Pivot to Internal Knowledge

When external tools fail:

Acknowledge the limitation: Note that external research was attempted but tools were unavailable
Assess internal knowledge: Determine what you know from training that covers the topic
Identify gaps: Be transparent about what information may be dated or unavailable
Proceed with available knowledge: Generate content using internal understanding

Step 4: Generate Content with Appropriate Disclaimers

When producing deliverables:

- Include a note that external verification is recommended for time-sensitive information
- Flag any claims that would benefit from current source verification
- Focus on established principles, frameworks, and well-documented facts
- Avoid making specific claims about very recent events or statistics

Step 5: Complete File Creation

Proceed with the original task deliverable:

Create the requested file format (PDF, DOCX, markdown, etc.)
Ensure content meets quality standards despite the research limitation
Stay within any specified constraints (page limits, word counts, etc.)

Example Decision Flow

Task requires research on [TOPIC]
         |
         v
Attempt search_web / read_webpage
         |
    +----+----+
    |         |
 Success    Failure (after 1-2 attempts)
    |         |
    v         v
Use sources  Pivot to internal knowledge
    |         |
    +----+----+
         |
         v
Generate content with appropriate disclaimers
         |
         v
Create deliverable file

Show full SKILL.md (186 more words)Show less

Best Practices

Be transparent: Clearly note when external verification wasn't possible
Prioritize accuracy: Only assert what you're confident about from training
Flag uncertainties: Mark areas where current sources would be valuable
Don't block progress: Tool failures shouldn't prevent task completion
Maintain quality: Internal knowledge can still produce high-quality, useful content

Example Application

Task: Create legal memo on privacy law violations

Workflow:

Attempt search_web for recent COPPA enforcement cases → Tool fails
Attempt read_webpage on provided URLs → Connection timeout
Pivot: Use internal knowledge of COPPA requirements, California privacy laws, established case law principles
Generate memo with note that recent case citations should be verified
Create PDF deliverable within page limits

Outcome: Comprehensive memo produced despite tool failures, with appropriate disclaimers about verification.

When NOT to Use This Skill

Task explicitly requires current, verified external sources (e.g., real-time stock prices, breaking news)
Legal/medical advice where current regulations are critical and disclaimer is insufficient
Client specifically requires cited external sources for the deliverable

In these cases, report the tool failure and request guidance rather than proceeding with internal knowledge alone.

Files

SKILL.md and 1 other file in benchmarks/gdpval/skills/research-fallback of HKUDS/OpenSpace.

SKILL.md
.skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Research 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.

Research Fallback compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Research Fallback this skillHKUDS/OpenSpace	7.7k	—	~1.1k	Automated safety check: Pass	MIT	1 mo ago
Error Handlingaffaan-m/ECC	275k	1 repos	~2.7k	Automated safety check: Pass	MIT	3 days ago
Handle PR CI FailureDataDog/datadog-agent	3.8k	—	~2.9k	Automated safety check: Pass	Apache-2.0	today
Python Error Handlingwshobson/agents	40k	—	~1.5k	Automated safety check: Pass	MIT	3 days ago
Error Handlingthedaviddias/Front-End-Checklist	74k	—	~416	Automated safety check: Pass	MIT	2 days ago
Error Handlingaffaan-m/ECC	275k	—	~2.4k	Automated safety check: Pass	MIT	3 days ago

Similar skills

Error Handling
affaan-m/ECC
Patterns for robust error handling across TypeScript, Python, and Go.
275k GitHub starsUsed in 1 repo~2.7k tokens
DevelopmentAuto-check passed
Handle PR CI Failure
DataDog/datadog-agent
Official
Handle a CI failure that is reliably attributed to the current PR's own code changes.
3.8k GitHub stars~2.9k tokensUpdated today
Testing & QAAuto-check passed
Python Error Handling
wshobson/agents
Python error handling patterns including input validation, exception hierarchies, and partial failure handling.
40k GitHub stars~1.5k tokensUpdated 3 days ago
DevelopmentAuto-check passed
Error Handling
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Implement proper error handling.
74k GitHub stars~416 tokensUpdated 2 days ago
DevelopmentAuto-check passed
Error Handling
affaan-m/ECC
TypeScript、Python、Goにわたる堅牢なエラー処理のパターン。型付きエラー、エラー境界、リトライ、サーキットブレーカー、ユーザー向けエラーメッセージをカバーします。
275k GitHub stars~2.4k tokensUpdated 3 days ago
Auto-check passed
Internal Comms
alirezarezvani/claude-skills
A skill your agent uses when a Head of People Ops, BizOps lead, or Internal Communications owner needs to draft and sequence an internal-only change-management communication — a re-org announcement…
28k GitHub stars~3.4k tokensUpdated 1 mo ago
Writing & ContentAuto-check passed

Questions about Research Fallback

What does Research Fallback do?

Handle web research failures by pivoting to internal knowledge for content generation. Research Fallback is an agent skill from HKUDS/OpenSpace.

How do I install Research Fallback in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill research-fallback -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/research-fallback in HKUDS/OpenSpace) into .claude/skills/research-fallback in your project. Claude Code loads it when a task matches its description.

How do I install Research Fallback in Codex?

Run `npx skills add HKUDS/OpenSpace --skill research-fallback -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/research-fallback in HKUDS/OpenSpace) into .agents/skills/research-fallback in your project. Codex loads it when a task matches its description.

Can I use Research 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 research-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/research-fallback, .gemini/skills/research-fallback, .github/skills/research-fallback and .opencode/skills/research-fallback in your project.

What does Research Fallback need to run?

SKILL.md names no scripts, command-line tools or credentials: Research Fallback is instructions for the agent only.

Does Research Fallback 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 Research 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 Research Fallback use?

Research 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 Research Fallback use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Research Fallback?

Skills that share tags, products or a category with Research Fallback: Error Handling (affaan-m/ECC, 275k stars), Handle PR CI Failure (DataDog/datadog-agent, 3.8k stars), Python Error Handling (wshobson/agents, 40k stars) and Error Handling (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Fallback?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,749 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.

Install Research Fallback

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Research Fallback Workflow

When to Use

Workflow Steps

Step 1: Attempt External Research First

Step 2: Detect Tool Failure

Step 3: Pivot to Internal Knowledge

Step 4: Generate Content with Appropriate Disclaimers

Step 5: Complete File Creation

Example Decision Flow

Best Practices

Example Application

When NOT to Use This Skill

Files

Compare with similar skills

Similar skills

More from HKUDS/OpenSpace

Questions about Research Fallback