tekkiiiii/the-agency/auto-researcher
Claude Code and agent skill by tekkiiiii/the-agency
- community
Checking that the SKILL.md file is still in the repository.
Use for proactive web research: \"research X for me\", \"what's the latest on...\", \"find out about...\", \"give me a briefing on...\", or when fresh data may exceed the training cutoff. Returns a key finding, sourced evidence, conflicting views, limits and confidence flags.
Install
npx vskill@latest install tekkiiiii/the-agency/auto-researcherSKILL.md
The same SKILL.md was published earlier as tekkiiiii/the-agency/auto-researcher.
Auto Researcher Skill
Core Behavior
Don't wait to be asked to search. If current information would improve the answer, search automatically and synthesize before responding.
Research Process
1. Query Planning (do this before searching)
Break the topic into 3-5 targeted search queries:
- Start broad, then narrow
- Include date modifiers for recent info ("2025", "latest", "recent")
- Search for both facts AND expert opinions
- Search for counterarguments or limitations
2. Execute Searches
- Run multiple searches in parallel when possible
- Fetch full pages for key sources, not just snippets
- Prioritize: primary sources > reputable publications > secondary sources
- Note publication date of each source
3. Synthesis
Structure findings as:
- Key Finding: 1-sentence answer to the core question
- Supporting Evidence: 3-5 data points with sources
- Conflicting Views: Any disagreement among sources
- Limitations: What's unknown or uncertain
- Further Reading: 2-3 best sources for deep dive
4. Source Quality Tiers
- ✅ High: Peer-reviewed, official docs, primary data, major news outlets
- ⚠️ Medium: Industry blogs, secondary analysis, aggregators
- ❌ Low: Forums, anonymous sources, undated content
Research Templates
Competitive Research
- Search "[Company] latest news 2025"
- Search "[Company] product updates"
- Search "[Company] vs competitors"
Technical Research
- Official documentation first
- Search "[technology] best practices 2025"
- Search "[technology] limitations problems"
Market Research
- Industry reports and statistics
- Recent news and trends
- Expert opinions and analyst views
Output Format
Always cite sources inline. Flag confidence level (High/Medium/Low) for key claims. Note knowledge cutoff vs. searched information distinction.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/auto-researcher/SKILL.md
Popularity
- Repository stars
- 3
- 7-day trend score
- 7
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tekkiiiii/the-agency/auto-researcher)