web-research
Skill1 starsChanged 49 days agoMITView on GitHub
Research a question across several independent, reliable web sources and return a sourced answer with confidence notes. Use when the user asks to look into a topic, verify a claim, compare viewpoints, or needs citations - not for a single quick fact (use web-search for that).
45 other projects use a version of this.
Adopted by
Most recently taken up by
- juninmd/skillstheir own version, first seen Nov 8, 2026
- thensls/nsls-builder-toolkittheir own version, first seen Nov 8, 2026
- memi-design/design-skillstheir own version, first seen Nov 8, 2026
- ai-assist-org/ai-assisttheir own version, first seen Nov 8, 2026
- WingedGuardian/GENesis-AGItheir own version, first seen Nov 8, 2026
- Bobagi/claude-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use meeting-notes, prompt-engineering and 8 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.
claude-office-skillsSkillmeeting-notes
>
Also in 4 projects that use this
kongyo2Skillprompt-engineering
Comprehensive prompt engineering framework for designing, optimizing, and iterating LLM prompts. This skill should be used when users request prompt creation, optimization, or improvement for any LLM task, or when users need help translating vague requirements into effective prompts through collaborative dialogue and iterative refinement.
Also in 4 projects that use this
rogue-dev-studioSkillbrowser-automation
Canonical browser automation and web UI verification: Playwright, agent browser CLIs, and CDP-based tooling in one playbook.
Also in 3 projects that use this
JetBrainsSkillbrand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Also in 4 projects that use this
AnthropicSkillpdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Also in 6 projects that use this
- JetBrainsSkill
slack-gif-creator
Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack.
Also in 3 projects that use this
- +1 more from JetBrains
Other versions45 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 45
- langchain-ai/deepagents★ 31ksame name
- pollinations/pollinations★ 5.3ksame name
- langchain-ai/deepagentsjs★ 1.6ksame name
- alfredxw/denova★ 990same name
- icey1287/SuperMew★ 884same name
- cohen-liel/hivemind★ 108same name
- grandamenium/cortextos★ 106same name
- WingedGuardian/GENesis-AGI★ 100same name
- jezweb/vite-flare-starter★ 49same name
- dewil/ai-toolkit★ 9same name
35 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 repository15 other files it gives its agents.
- academic-researchSkill
- codebase-auditSkill
- code-documentationSkill
- code-reviewSkill
- competitive-analysisSkill
- data-analysisSkill
- email-assistantSkill
- fullstack-dev-teamSkill
- github-integrationSkill
- market-researchSkill
- pdf-analysisSkill
- research-paperSkill
- sql-analysisSkill
- ui-ux-designSkill
- web-searchSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 38 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Do not use for a single lookup ("what year was X founded") — that is web-search.
- Distinctive: line 62
Search results skew toward English and recent content.
“Common” is measured: kept by at least 6 in 10 of the 38 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
Web Research
Overview
A repeatable procedure for answering open questions from the web: plan the searches, read primary sources, cross-check claims, and report what is known, what is disputed and where each fact came from.
When to Use
- "Research…", "look into…", "what's the current state of…", "is it true that…"
- The answer needs more than one source, or the user will act on it.
- The user asks for citations, a comparison of viewpoints, or a recent development.
Do not use for a single lookup ("what year was X founded") — that is web-search.
Usage
- Restate the question in one sentence and list 2–4 sub-questions it depends on.
- Plan searches. For each sub-question write 1–2 queries. Vary wording; include one query aimed at a primary source (official site, paper, dataset, filing, standard).
- Collect sources. Aim for at least 3 independent sources for any key claim. Prefer, in order: primary sources → reputable institutions and journals → established news outlets → everything else. Note the publication date of each; flag anything older than the question needs.
- Read, don't skim snippets. Open the page. Quote only short passages; paraphrase the rest.
- Cross-check. For each key claim record: sources that agree, sources that disagree, and why they might differ (date, method, incentive).
- Write the answer in this shape:
- Answer — 2–4 sentences, direct.
- Key findings — bullets, each ending with a citation like
[2]. - Disagreements / uncertainty — what is contested and why.
- Sources — numbered list: title, publisher, date, URL.
- State confidence (high / medium / low) and what would change it.
Examples
Prompt: "Is intermittent fasting better than calorie restriction for weight loss?"
The agent splits it into: effect size in RCTs, adherence, populations studied. It searches for meta-analyses first, then individual trials, then public-health guidance, and reports that most trials find similar weight loss when calories are matched — with the disagreement being about adherence.
A full sample answer is in examples/sample-answer.md.
Requirements
- Web search and the ability to open pages.
Limitations
- Cannot read paywalled content; says so rather than guessing what it contains.
- Search results skew toward English and recent content.
- The agent can still misread a source — citations let the user check.
Changelog
- 1.0.0 — Initial release.
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.