web-researcher
Skill2 starsChanged 39 days agoMITView on GitHub
Use when gathering web research context via Tavily or DuckDuckGo before content generation or topic summarization
5 other projects use a version of this.
Adopted by
Most recently taken up by
- amanning3390/hermeshubtheir own version, first seen Oct 8, 2026
- zeroclaw-labs/zeroclaw-skillstheir own version, first seen Sep 24, 2026
- markbaindesign/bain-studiotheir own version, first seen Jul 22, 2026
- almax000/claude-skillstheir own version, first seen Apr 19, 2026
- xcrrr/claude-skillstheir own version, first seen Mar 19, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- zeroclaw-labs/zeroclaw-skills★ 65same name
- amanning3390/hermeshub★ 48same name
- xcrrr/claude-skills★ 6same name
- almax000/claude-skills★ 1same name
- markbaindesign/bain-studio★ 0same name
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.
- notemdproSkill
- batch-processorSkill
- concept-extractorSkill
- content-generatorSkill
- diagram-generatorSkill
- formula-healerSkill
- link-analyzerSkill
- mermaid-healerSkill
- mermaid-summarizerSkill
- qa-extractorSkill
- selection-processorSkill
- system-architectureSkill
- test-driven-developmentSkill
- text-translatorSkill
- workflow-runnerSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Fact-checking: Verify information from web sources
“Common” is measured: kept by at least 6 in 10 of the 5 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
NoteMD Pro - Web Research
Overview
This feature researches topics using web search providers and provides summarized context. It supports both Tavily (API-based) and DuckDuckGo (scraper-based) providers.
When to Use
- Research before writing: Gather context for content generation
- Summarize topics: Get overview of any subject
- Fact-checking: Verify information from web sources
- Literature review: Collect information from multiple sources
Function Call Chain
_performResearch (searchUtils.ts)
├── SearchManager.getProvider(settings)
│ ├── TavilyProvider (if searchProvider='tavily')
│ └── DuckDuckGoProvider (if searchProvider='duckduckgo')
├── provider.search(query, settings)
│ └── Returns SearchResult[]
├── fetchContentFromUrl(url) [For DuckDuckGo only]
│ └── requestUrl({url, method: 'GET'})
│ └── Extract text from HTML
├── Combine research context
└── Return combined context stringSearch Providers
Tavily Provider
- API-based search (requires API key)
- Returns snippets/summaries
- Faster, more reliable
- Configuration:
tavilyApiKey,tavilyMaxResults,tavilySearchDepth
DuckDuckGo Provider
- Web scraping (no API key needed)
- Returns URLs, fetches full content
- More results, slower
- Configuration:
ddgMaxResults,ddgFetchTimeout
Key Functions (from searchUtils.ts)
_performResearch
Performs web research for a topic and returns combined context.
export async function _performResearch(
settings: NotemdSettings,
topic: string,
progressReporter: ProgressReporter,
): Promise<string | null>;fetchContentFromUrl
Fetches content from a URL and extracts text.
export async function fetchContentFromUrl(
url: string,
progressReporter: ProgressReporter,
debugMode?: boolean,
): Promise<string>;
// Returns extracted text or error messageSearchManager (search/SearchManager.ts)
Factory for getting search provider.
export class SearchManager {
static getProvider(settings: NotemdSettings): SearchProvider;
// Returns TavilyProvider or DuckDuckGoProvider
}Settings
Provider Settings
| Setting | Description |
searchProvider | 'tavily' or 'duckduckgo' |
tavilyApiKey | API key for Tavily |
Tavily Settings
| Setting | Description |
tavilyMaxResults | Number of results (default: 5) |
tavilySearchDepth | 'basic' or 'advanced' |
DuckDuckGo Settings
| Setting | Description |
ddgMaxResults | Number of results (default: 5) |
ddgFetchTimeout | Timeout in seconds (default: 10) |
Contextual Context (Macro Settings)
| Setting | Description |
enableFocusedLearning | Inject macro user domain preferences globally |
focusedLearningDomain | The specific domain context (e.g., "Physics", "History") |
Research Limits
| Setting | Description |
maxResearchContentTokens | Max tokens for research context |
enableApiErrorDebugMode | Enable detailed error logging |
Prompt Template (researchSummarize)
From promptUtils.ts:
Summarize the following search results for the topic "{TOPIC}".
Provide a concise yet comprehensive overview.
Focus on key findings, data, and important conclusions.
Format the summary in Markdown.
The output language should be {LANGUAGE}.
Search Results:
{SEARCH_RESULTS_CONTEXT}Output Format
Research context is formatted as:
Research context for "{query}" (via {provider}):
Result 1:
Title: {title}
URL: {url}
Content: {content}
Result 2:
Title: {title}
...Error Handling
Common Errors
- No API key for Tavily
- Error: "Tavily API key not configured"
- Solution: Add API key in settings or switch to DuckDuckGo
- Network timeout
- Error: "Timeout fetching {url}"
- Solution: Increase
ddgFetchTimeout
- No search results
- Warning: "Search returned no results"
- Solution: Try different search query
Debug Mode
Enable enableApiErrorDebugMode for detailed error information including:
- Full API request/response
- HTTP status codes
- Error stack traces
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.

