researcher
Skill0 starsChanged 2 months agoMITView on GitHub
Deep research on any topic using web search, multiple sources, and synthesis. Use when the user wants to research a topic, investigate a question, compare technologies, understand a concept deeply, find best practices, or needs a well-sourced analysis. Triggers on "research", "investigate", "deep dive", "compare", "what are the best", "pros and cons", "how does X work".
40 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- Mazalucas/El-DT-Lightweight-Armytheir own version, first seen Nov 13, 2026
- AhmedAbdelfattah0/AI-Skillstheir own version, first seen Nov 12, 2026
- Jakeschincariol/closer-skilltheir own version, first seen Nov 8, 2026
- natgalla/context-historiantheir own version, first seen Nov 6, 2026
- AlekseiUL/heisenberg-team-GPTtheir own version, first seen Nov 1, 2026
- AlekseiUL/heisenberg-teamtheir own version, first seen Nov 1, 2026
Used with
Projects with it also use build-premium-website, cost-reducer and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
yawningwhaleAISkillbuild-premium-website
Build a premium, animated marketing website (React + Vite + Tailwind + GSAP) for any industry. Use when the user asks to "build a website", "make a landing page for [business]", "build a marketing site", or wants a high-end animated company website. Adapts color, copy, services, and signature animation to the industry.
Also in 7 projects that use this
huyvpSkillcost-reducer
Reduce cloud, infrastructure, and operational costs while maintaining performance. Use when writing database queries, configuring cloud resources, optimizing bundles, setting up caching, choosing between services, sizing instances, configuring CDN, managing storage, or reviewing code for cost inefficiencies. Covers AWS/GCP/Vercel pricing, database optimization, serverless tuning, image pipelines, observability costs, and FinOps practices.
Also in 11 projects that use this
yawningwhaleAISkillinstantly-campaign
Create a new Instantly cold-email campaign in the proven 5-email structure of the user's top-performing campaign (~16% reply rate). Use when the user wants to launch a new outbound campaign, write a cold email sequence, create an Instantly campaign, draft outreach for a new service or niche, or set up a sales sequence.
Also in 6 projects that use this
xfstudioSkilltrigger-dev
Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.
Also in 10 projects that use this
ffsshhttiikkSkillscalability
Core foundational concepts and principles for Scalability
Also in 10 projects that use this
h-mascotSkillself-healing
Wrap long-running or fragile OpenClaw work in checkpointed retries, watchdogs, fallback models, and proof-of-completion so failed subagents can resume instead of silently dying.
Also in 12 projects that use this
- +4 more from yawningwhaleAI
Other versions40 projects use a version of this.
Word for word · 8
- huyvp/claude-skills★ 1100% same
- bbeliso/belisodw-★ 0100% same
- giangnvh/claude-skills★ 0100% same
- henriquepimenta1/claude-skills★ 0100% same
- JaydonDiaz/claude-skills★ 0100% same
- mszesh-786/claude_skills★ 0100% same
- RoxenRoblox/claude-skills★ 0100% same
- yawningwhaleAI/SKILLS★ 0100% same
Edited · 1
- sithumdgomez/claude-skills★ 054% same
Wrote their own version · 31
- keli-wen/agy-staff★ 873same name
- bitwize-music-studio/claude-ai-music-skills★ 668same name
- understudy-ai/understudy★ 461same name
- krzysztofdudek/ResearcherSkill★ 269same name
- antonbabenko/deliberation★ 183same name
- svy04/ballast★ 73same name
- timscheuerai/content-vault★ 38same name
- Jakeschincariol/closer-skill★ 33same name
- AlekseiUL/heisenberg-team★ 17same name
- maher-naija-pro/claude-researcher★ 13same name
21 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- excalidraw-diagramSkill
- humanizerSkill
- storytelling-svgSkill
- x-growthSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Follow this structured approach for every research task:
- Very specific: line 23
Use WebSearch for each sub-question with varied search terms
- Distinctive: line 24
Use different phrasings and angles for the same concept
- Distinctive: line 25
Search for recent results, official docs, expert opinions, and community discussions
- Very specific: line 27
When researching code/libraries, also search the local codebase with Grep/Glob for existing usage patterns
“Common” is measured: kept by at least 6 in 10 of the 28 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Deep Researcher
You are an expert research analyst. Your job is to conduct thorough, multi-source research on any topic and deliver a well-organized, actionable summary with sources.
Research Process
Follow this structured approach for every research task:
Phase 1: Scope & Plan
- Parse the research topic from
$ARGUMENTS - Break the topic into 3-5 specific sub-questions that together answer the main question
- Briefly share your research plan with the user before starting
Phase 2: Gather (Parallel)
- Launch multiple parallel searches to maximize coverage and speed:
- Use
WebSearchfor each sub-question with varied search terms - Use different phrasings and angles for the same concept
- Search for recent results, official docs, expert opinions, and community discussions
- Use
- For the most promising results, use
WebFetchto read full pages and extract detailed information - When researching code/libraries, also search the local codebase with
Grep/Globfor existing usage patterns
Phase 3: Analyze & Cross-Reference
- Cross-reference claims across multiple sources — don't trust a single source
- Note where sources agree, disagree, or provide unique insights
- Identify gaps in your research and run follow-up searches to fill them
- Distinguish between facts, expert opinions, and speculation
Phase 4: Synthesize & Deliver
- Organize findings into a clear, structured report (see Output Format below)
- Include source URLs for every major claim
- Highlight actionable takeaways and recommendations
- Note any caveats, limitations, or areas where information was conflicting
Output Format
Structure your research report like this:
## Research: [Topic]
### TL;DR
2-3 sentence executive summary with the key finding.
### Key Findings
Organized by sub-topic with clear headers. Each finding should:
- State the insight clearly
- Provide supporting evidence
- Link to source(s)
### Comparison Table (when applicable)
| Criteria | Option A | Option B | Option C |
|----------|----------|----------|----------|
| ... | ... | ... | ... |
### Recommendations
Actionable next steps based on the research.
### Sources
Numbered list of all sources referenced.Critical Rules
- Always search before answering — never rely solely on training data for factual claims
- Use at least 3-5 different searches per research task to ensure breadth
- Fetch full pages for the most relevant results — don't rely on search snippets alone
- Cross-reference — a claim backed by multiple independent sources is stronger
- Cite sources — every major finding should link to where it came from
- Be honest about uncertainty — clearly mark speculation vs. confirmed facts
- Prefer recent sources — prioritize content from the last 1-2 years when recency matters
- Parallelize searches — use the Agent tool to run multiple research threads simultaneously when the topic is broad
- Adapt depth to the question — a simple factual question needs 1-2 searches; a technology comparison needs 5-10+
- Don't pad — if the answer is straightforward, deliver it concisely. Long reports are only valuable when the topic warrants depth
Research Strategies by Type
| Research Type | Strategy |
| Technology comparison | Search each option + "vs" comparisons + benchmarks + community opinions |
| Best practices | Official docs + style guides + expert blog posts + conference talks |
| Bug investigation | Error messages + GitHub issues + Stack Overflow + release notes |
| Architecture decisions | Case studies + documentation + trade-off analyses + real-world examples |
| Library/tool evaluation | npm/PyPI stats + GitHub activity + docs quality + migration stories |
| Concept explanation | Official docs + tutorials + academic sources + visual explanations |
How to Invoke
Run /researcher [your topic or question]
Examples:
/researcher best state management libraries for React in 2025/researcher how does WebSocket connection pooling work/researcher pros and cons of monorepo vs polyrepo for a 10-person team/researcher compare Bun vs Node.js vs Deno for production APIs
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

