Research

Verified Research

Quick Start

When researching, always fetch and verify actual sources:

# Always do this
WebFetch URL → read content → verify claims → present findings

# Never do this
WebSearch → present snippets without verification

Core Rule

Never present findings without examining actual source content.

Steps:

1. Fetch the actual source (WebFetch or extract tools) 2. Read the complete relevant sections 3. Verify claims match what source actually says 4. Quote specific passages when making claims

Common Pitfalls

❌ Presenting search snippets as facts ❌ Trusting summaries without checking sources ❌ Citing sources you haven't read

When Uncertain

If you can't verify (paywall, 404, contradictions): Say so explicitly. Don't present unverified info as fact.

References

For detailed patterns and examples:

• references/verification-patterns.md
• references/repo-cloning-pattern.md -

Clone repos via subagent for source-level research

Source Verifier

Verify sources and citations when researching. Use when you need to fact-check claims, validate sources, or ensure research accuracy by examining actual source content rather than summaries or snippets.

Structure

• SKILL.md - Main skill instructions
• references/ - Detailed documentation loaded as needed
• scripts/ - Executable code for deterministic operations
• assets/ - Templates, images, or other resources

Usage

This skill is automatically discovered by Claude when relevant to the task.

Repo Cloning Pattern

For library/framework research, clone source repos to get authoritative, current information.

When to Use

• Questions about library internals/implementation
• Undocumented behavior
• Checking actual source vs docs
• Framework patterns not covered in official docs

Pattern: Subagent Clone Research

Always delegate to subagent to avoid context pollution.

Task(subagent_type=Explore) →
  1. git clone --depth 1 <repo> /tmp/research-<name>
  2. Glob/Grep for relevant patterns
  3. Read key files
  4. Return distilled findings
  5. rm -rf /tmp/research-<name>

Example Prompt for Subagent

Clone https://github.com/sveltejs/svelte to /tmp/research-svelte
Find how $effect() cleanup works internally.
Search for cleanup patterns in src/
Read relevant implementation files
Summarize findings
Delete clone when done

Key Points

• Use --depth 1 for speed (no history needed)
• Clone to /tmp/ for auto-cleanup on reboot
• Always cleanup after: rm -rf /tmp/research-*
• Subagent keeps main context clean
• Return only essential findings, not full file contents

Anti-Patterns

• Cloning in main context (trashes context)
• Full clone with history (slow, unnecessary)
• Leaving clones around (disk clutter)
• Dumping entire files back to main context

Verification Patterns

Detailed patterns for verifying sources during research.

Pattern 1: URL Research

When given a URL to research:

1. Use WebFetch to get the actual content 2. Read the complete relevant sections 3. Don't rely on summaries or snippets 4. Quote specific passages that support claims 5. Cite exact URLs

Example:

User: "Research this article about MCP performance"

WRONG approach:
- Search for article
- Present snippet results
- Make claims based on title

RIGHT approach:
- WebFetch the URL
- Read full content
- Search for performance mentions
- Quote specific data/claims
- If no performance data exists, say so

Pattern 2: Official Sources

When asked to "use official sources":

1. Search for official documentation 2. Fetch the actual pages (don't trust search snippets) 3. Read relevant sections completely 4. Quote specific parts 5. Cite exact URLs for each claim

Pattern 3: Questionable Claims

When something seems questionable:

• Fetch the original source
• Compare snippet/summary to actual content
• Call out discrepancies explicitly
• Say "I couldn't verify this" if sources don't support

Anti-Patterns

Never do these:

❌ Presenting search snippets as facts without verification ❌ Trusting summaries without checking original sources ❌ Citing sources you haven't actually read ❌ Assuming snippets accurately represent full content ❌ Making confident claims based on titles alone

When To Admit Uncertainty

If you can't verify because:

• Source is behind paywall/404
• Content doesn't support the claim
• Multiple sources contradict

Say so explicitly. Better to admit uncertainty than present unverified info.

Detailed Examples

Example 1: Security Documentation

User: "Research how Claude Code handles bash security"

Process:

1. Search for official Claude Code security docs 2. Fetch the actual documentation pages 3. Read security sections completely 4. Extract specific quotes about bash handling 5. Present findings with exact citations and line references

Not: Just present search result snippets

Example 2: Technical Article

User: "Study this article and tell me what it says about overhead"

Process:

1. Fetch the actual article content 2. Search for mentions of "overhead", "performance" 3. Read those sections in full context 4. Quote specific passages 5. If article doesn't mention overhead, say "The article doesn't actually discuss overhead"

Not: Assume what it says based on title/snippet

Example 3: Contradictory Sources

User: "Research whether MCP tools are faster than CLI"

Process:

1. Search for relevant sources 2. Fetch multiple actual sources 3. Compare what they actually say 4. If they contradict, present both views with quotes 5. Explain the contradiction explicitly 6. Don't pick one without evidence

Not: Present the first search result as truth