Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Hermes Pipeline
|
28b0c483b8 |
@@ -0,0 +1,77 @@
|
||||
---
|
||||
name: autonomous-web-research-agent
|
||||
version: 1.0.0
|
||||
description: Autonomously research a given query on the web using multiple search
|
||||
tools and generate a structured report with summary, detailed sections, source tracking,
|
||||
and bias analysis.
|
||||
inputs:
|
||||
- 'query (string): the research question or topic to investigate'
|
||||
- 'tools (list, optional): selected web search/tools to use (e.g., Tavily, Google,
|
||||
NewsAPI, DuckDuckGo)'
|
||||
- 'api_keys (dict, optional): credentials for LLM and external search APIs'
|
||||
- 'model_config (dict, optional): LLM provider and parameters'
|
||||
steps:
|
||||
- 1. Accept user query and optional tool selections.
|
||||
- '2. Initialize agent framework (e.g., LangGraph) with integrated tools: web search
|
||||
(Tavily, Google, DuckDuckGo), news API, web scraping.'
|
||||
- 3. Decompose query into sub-questions if needed and iteratively call tools to gather
|
||||
relevant information.
|
||||
- 4. Extract and deduplicate content from retrieved sources, tracking source metadata
|
||||
(URL, tool used).
|
||||
- 5. Use a large language model to synthesize findings into an executive summary and
|
||||
detailed sections.
|
||||
- 6. Analyze potential biases or limitations of gathered sources.
|
||||
- 7. Compile a structured report object (ResearchReport) containing query, summary,
|
||||
sections, sources, biases.
|
||||
- 8. Optionally present report via a UI (e.g., Streamlit) or return as JSON.
|
||||
outputs:
|
||||
- 'ResearchReport (JSON/dict) with fields: query (string), summary (string), sections
|
||||
(list of {heading, content}), sources (list of {url, tool_used, title}), potential_biases
|
||||
(string)'
|
||||
- Optional UI rendering of report with source badges and expandable sections
|
||||
tags: []
|
||||
metadata:
|
||||
source_repo: https://github.com/DennisDRX/Faraday-Web-Researcher-Agent.git
|
||||
extracted_at: ''
|
||||
confidence: 0.85
|
||||
---
|
||||
|
||||
# autonomous-web-research-agent
|
||||
|
||||
Autonomously research a given query on the web using multiple search tools and generate a structured report with summary, detailed sections, source tracking, and bias analysis.
|
||||
|
||||
## Steps
|
||||
|
||||
1. 1. Accept user query and optional tool selections.
|
||||
2. 2. Initialize agent framework (e.g., LangGraph) with integrated tools: web search (Tavily, Google, DuckDuckGo), news API, web scraping.
|
||||
3. 3. Decompose query into sub-questions if needed and iteratively call tools to gather relevant information.
|
||||
4. 4. Extract and deduplicate content from retrieved sources, tracking source metadata (URL, tool used).
|
||||
5. 5. Use a large language model to synthesize findings into an executive summary and detailed sections.
|
||||
6. 6. Analyze potential biases or limitations of gathered sources.
|
||||
7. 7. Compile a structured report object (ResearchReport) containing query, summary, sections, sources, biases.
|
||||
8. 8. Optionally present report via a UI (e.g., Streamlit) or return as JSON.
|
||||
|
||||
## Inputs
|
||||
|
||||
- query (string): the research question or topic to investigate
|
||||
- tools (list, optional): selected web search/tools to use (e.g., Tavily, Google, NewsAPI, DuckDuckGo)
|
||||
- api_keys (dict, optional): credentials for LLM and external search APIs
|
||||
- model_config (dict, optional): LLM provider and parameters
|
||||
|
||||
## Outputs
|
||||
|
||||
- ResearchReport (JSON/dict) with fields: query (string), summary (string), sections (list of {heading, content}), sources (list of {url, tool_used, title}), potential_biases (string)
|
||||
- Optional UI rendering of report with source badges and expandable sections
|
||||
|
||||
## Failure Modes
|
||||
|
||||
- Missing or invalid API keys causing tool authentication failures
|
||||
- Rate limits or network errors from search APIs
|
||||
- Insufficient or low-quality search results leading to incomplete report
|
||||
- LLM hallucination or mis-summarization despite source tracking
|
||||
- Parsing errors in HTML/scraped content
|
||||
|
||||
## Source
|
||||
|
||||
Extracted from: [https://github.com/DennisDRX/Faraday-Web-Researcher-Agent.git](https://github.com/DennisDRX/Faraday-Web-Researcher-Agent.git)
|
||||
Confidence: 0.85
|
||||
@@ -0,0 +1,6 @@
|
||||
# Commands: autonomous-web-research-agent
|
||||
|
||||
## Available Commands
|
||||
|
||||
- `/skill autonomous-web-research-agent` — Load this skill
|
||||
- `/run autonomous-web-research-agent` — Execute workflow
|
||||
@@ -0,0 +1,10 @@
|
||||
# Examples: autonomous-web-research-agent
|
||||
|
||||
## Usage Example
|
||||
|
||||
```python
|
||||
# How to use this skill
|
||||
# Inputs: query (string): the research question or topic to investigate, tools (list, optional): selected web search/tools to use (e.g., Tavily, Google, NewsAPI, DuckDuckGo), api_keys (dict, optional): credentials for LLM and external search APIs, model_config (dict, optional): LLM provider and parameters
|
||||
# Process: 1. Accept user query and optional tool selections. → 2. Initialize agent framework (e.g., LangGraph) with integrated tools: web search (Tavily, Google, DuckDuckGo), news API, web scraping. → 3. Decompose query into sub-questions if needed and iteratively call tools to gather relevant information.
|
||||
# Outputs: ResearchReport (JSON/dict) with fields: query (string), summary (string), sections (list of {heading, content}), sources (list of {url, tool_used, title}), potential_biases (string), Optional UI rendering of report with source badges and expandable sections
|
||||
```
|
||||
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"name": "autonomous-web-research-agent",
|
||||
"version": "1.0.0",
|
||||
"goal": "Autonomously research a given query on the web using multiple search tools and generate a structured report with summary, detailed sections, source tracking, and bias analysis.",
|
||||
"inputs": [
|
||||
"query (string): the research question or topic to investigate",
|
||||
"tools (list, optional): selected web search/tools to use (e.g., Tavily, Google, NewsAPI, DuckDuckGo)",
|
||||
"api_keys (dict, optional): credentials for LLM and external search APIs",
|
||||
"model_config (dict, optional): LLM provider and parameters"
|
||||
],
|
||||
"steps": [
|
||||
"1. Accept user query and optional tool selections.",
|
||||
"2. Initialize agent framework (e.g., LangGraph) with integrated tools: web search (Tavily, Google, DuckDuckGo), news API, web scraping.",
|
||||
"3. Decompose query into sub-questions if needed and iteratively call tools to gather relevant information.",
|
||||
"4. Extract and deduplicate content from retrieved sources, tracking source metadata (URL, tool used).",
|
||||
"5. Use a large language model to synthesize findings into an executive summary and detailed sections.",
|
||||
"6. Analyze potential biases or limitations of gathered sources.",
|
||||
"7. Compile a structured report object (ResearchReport) containing query, summary, sections, sources, biases.",
|
||||
"8. Optionally present report via a UI (e.g., Streamlit) or return as JSON."
|
||||
],
|
||||
"outputs": [
|
||||
"ResearchReport (JSON/dict) with fields: query (string), summary (string), sections (list of {heading, content}), sources (list of {url, tool_used, title}), potential_biases (string)",
|
||||
"Optional UI rendering of report with source badges and expandable sections"
|
||||
],
|
||||
"failure_modes": [
|
||||
"Missing or invalid API keys causing tool authentication failures",
|
||||
"Rate limits or network errors from search APIs",
|
||||
"Insufficient or low-quality search results leading to incomplete report",
|
||||
"LLM hallucination or mis-summarization despite source tracking",
|
||||
"Parsing errors in HTML/scraped content"
|
||||
],
|
||||
"confidence": 0.85,
|
||||
"explanation": "The repository implements a generic autonomous web research agent that can be reused for any topical query. The workflow of querying, multi-tool retrieval, synthesis, and structured reporting is not domain-specific and can be extracted as a reusable skill.",
|
||||
"source_repo": "https://github.com/DennisDRX/Faraday-Web-Researcher-Agent.git",
|
||||
"score": 1.0
|
||||
}
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
# Tests: literature-review-with-traceable-ai-evidence
|
||||
# Tests: autonomous-web-research-agent
|
||||
|
||||
## Test Checklist
|
||||
|
||||
@@ -1,77 +0,0 @@
|
||||
---
|
||||
name: literature-review-with-traceable-ai-evidence
|
||||
version: 1.0.0
|
||||
description: Enable researchers to ingest documents, asynchronously index them, and
|
||||
interact with multi-agent AI to answer questions with verifiable citations to original
|
||||
text.
|
||||
inputs:
|
||||
- Documents in PDF, Office, image, or text formats
|
||||
- Research questions or topics of interest
|
||||
- 'Optional: user model configuration via .env or settings'
|
||||
steps:
|
||||
- Upload documents to a project (via desktop app or web UI)
|
||||
- System asynchronously converts Office docs to PDF if needed, runs OCR to extract
|
||||
text with coordinates, chunks and embeds into vector store
|
||||
- User starts a main research session or creates exploration branches without waiting
|
||||
for indexing to finish
|
||||
- Leader agent receives query and delegates subtasks to researcher, reviewer, writer
|
||||
subagents
|
||||
- Subagents perform hybrid retrieval and rerank to find relevant chunks with source
|
||||
coordinates
|
||||
- Agents synthesize answers and return evidence with clickable citations that highlight
|
||||
original pages
|
||||
- User verifies conclusions by navigating to cited source locations and can save notes
|
||||
to research memory or mind map
|
||||
outputs:
|
||||
- AI-generated answers with traceable evidence (coordinates, page highlights)
|
||||
- Research session history with branches
|
||||
- Indexed document library for future queries
|
||||
- Mind maps or structured notes
|
||||
- Persistent run events for resuming sessions
|
||||
tags: []
|
||||
metadata:
|
||||
source_repo: https://github.com/0verL1nk/PaperSage.git
|
||||
extracted_at: ''
|
||||
confidence: 0.85
|
||||
---
|
||||
|
||||
# literature-review-with-traceable-ai-evidence
|
||||
|
||||
Enable researchers to ingest documents, asynchronously index them, and interact with multi-agent AI to answer questions with verifiable citations to original text.
|
||||
|
||||
## Steps
|
||||
|
||||
1. Upload documents to a project (via desktop app or web UI)
|
||||
2. System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store
|
||||
3. User starts a main research session or creates exploration branches without waiting for indexing to finish
|
||||
4. Leader agent receives query and delegates subtasks to researcher, reviewer, writer subagents
|
||||
5. Subagents perform hybrid retrieval and rerank to find relevant chunks with source coordinates
|
||||
6. Agents synthesize answers and return evidence with clickable citations that highlight original pages
|
||||
7. User verifies conclusions by navigating to cited source locations and can save notes to research memory or mind map
|
||||
|
||||
## Inputs
|
||||
|
||||
- Documents in PDF, Office, image, or text formats
|
||||
- Research questions or topics of interest
|
||||
- Optional: user model configuration via .env or settings
|
||||
|
||||
## Outputs
|
||||
|
||||
- AI-generated answers with traceable evidence (coordinates, page highlights)
|
||||
- Research session history with branches
|
||||
- Indexed document library for future queries
|
||||
- Mind maps or structured notes
|
||||
- Persistent run events for resuming sessions
|
||||
|
||||
## Failure Modes
|
||||
|
||||
- Missing local Office/LibreOffice converter causes document conversion failure
|
||||
- First-time model download may be slow or require network
|
||||
- OCR may have low confidence on poor quality scans
|
||||
- Retrieval might miss context if chunking splits semantics
|
||||
- Multi-agent coordination could produce conflicting intermediate results
|
||||
|
||||
## Source
|
||||
|
||||
Extracted from: [https://github.com/0verL1nk/PaperSage.git](https://github.com/0verL1nk/PaperSage.git)
|
||||
Confidence: 0.85
|
||||
@@ -1,6 +0,0 @@
|
||||
# Commands: literature-review-with-traceable-ai-evidence
|
||||
|
||||
## Available Commands
|
||||
|
||||
- `/skill literature-review-with-traceable-ai-evidence` — Load this skill
|
||||
- `/run literature-review-with-traceable-ai-evidence` — Execute workflow
|
||||
@@ -1,10 +0,0 @@
|
||||
# Examples: literature-review-with-traceable-ai-evidence
|
||||
|
||||
## Usage Example
|
||||
|
||||
```python
|
||||
# How to use this skill
|
||||
# Inputs: Documents in PDF, Office, image, or text formats, Research questions or topics of interest, Optional: user model configuration via .env or settings
|
||||
# Process: Upload documents to a project (via desktop app or web UI) → System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store → User starts a main research session or creates exploration branches without waiting for indexing to finish
|
||||
# Outputs: AI-generated answers with traceable evidence (coordinates, page highlights), Research session history with branches, Indexed document library for future queries, Mind maps or structured notes, Persistent run events for resuming sessions
|
||||
```
|
||||
@@ -1,37 +0,0 @@
|
||||
{
|
||||
"name": "literature-review-with-traceable-ai-evidence",
|
||||
"version": "1.0.0",
|
||||
"goal": "Enable researchers to ingest documents, asynchronously index them, and interact with multi-agent AI to answer questions with verifiable citations to original text.",
|
||||
"inputs": [
|
||||
"Documents in PDF, Office, image, or text formats",
|
||||
"Research questions or topics of interest",
|
||||
"Optional: user model configuration via .env or settings"
|
||||
],
|
||||
"steps": [
|
||||
"Upload documents to a project (via desktop app or web UI)",
|
||||
"System asynchronously converts Office docs to PDF if needed, runs OCR to extract text with coordinates, chunks and embeds into vector store",
|
||||
"User starts a main research session or creates exploration branches without waiting for indexing to finish",
|
||||
"Leader agent receives query and delegates subtasks to researcher, reviewer, writer subagents",
|
||||
"Subagents perform hybrid retrieval and rerank to find relevant chunks with source coordinates",
|
||||
"Agents synthesize answers and return evidence with clickable citations that highlight original pages",
|
||||
"User verifies conclusions by navigating to cited source locations and can save notes to research memory or mind map"
|
||||
],
|
||||
"outputs": [
|
||||
"AI-generated answers with traceable evidence (coordinates, page highlights)",
|
||||
"Research session history with branches",
|
||||
"Indexed document library for future queries",
|
||||
"Mind maps or structured notes",
|
||||
"Persistent run events for resuming sessions"
|
||||
],
|
||||
"failure_modes": [
|
||||
"Missing local Office/LibreOffice converter causes document conversion failure",
|
||||
"First-time model download may be slow or require network",
|
||||
"OCR may have low confidence on poor quality scans",
|
||||
"Retrieval might miss context if chunking splits semantics",
|
||||
"Multi-agent coordination could produce conflicting intermediate results"
|
||||
],
|
||||
"confidence": 0.85,
|
||||
"explanation": "The README describes PaperSage's core workflow: asynchronous document ingestion with OCR/indexing, followed by multi-agent question answering with cited evidence. This process is not tied to the specific codebase and can be reused as a general literature review methodology for any document-centric research using RAG and agent collaboration.",
|
||||
"source_repo": "https://github.com/0verL1nk/PaperSage.git",
|
||||
"score": 1.0
|
||||
}
|
||||
Reference in New Issue
Block a user