From 28b0c483b884a2cd78e1ca8a65739ea84dc96ee7 Mon Sep 17 00:00:00 2001 From: Hermes Pipeline Date: Mon, 10 Aug 2026 17:05:01 +0000 Subject: [PATCH] Add Skill: autonomous-web-research-agent Extracted from: https://github.com/DennisDRX/Faraday-Web-Researcher-Agent.git Score: 1.0 --- skills/autonomous-web-research-agent/SKILL.md | 77 +++++++++++++++++++ .../autonomous-web-research-agent/commands.md | 6 ++ .../autonomous-web-research-agent/examples.md | 10 +++ .../metadata.json | 36 +++++++++ skills/autonomous-web-research-agent/tests.md | 9 +++ 5 files changed, 138 insertions(+) create mode 100644 skills/autonomous-web-research-agent/SKILL.md create mode 100644 skills/autonomous-web-research-agent/commands.md create mode 100644 skills/autonomous-web-research-agent/examples.md create mode 100644 skills/autonomous-web-research-agent/metadata.json create mode 100644 skills/autonomous-web-research-agent/tests.md diff --git a/skills/autonomous-web-research-agent/SKILL.md b/skills/autonomous-web-research-agent/SKILL.md new file mode 100644 index 0000000..eddabc7 --- /dev/null +++ b/skills/autonomous-web-research-agent/SKILL.md @@ -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 diff --git a/skills/autonomous-web-research-agent/commands.md b/skills/autonomous-web-research-agent/commands.md new file mode 100644 index 0000000..2385491 --- /dev/null +++ b/skills/autonomous-web-research-agent/commands.md @@ -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 diff --git a/skills/autonomous-web-research-agent/examples.md b/skills/autonomous-web-research-agent/examples.md new file mode 100644 index 0000000..7d99125 --- /dev/null +++ b/skills/autonomous-web-research-agent/examples.md @@ -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 +``` diff --git a/skills/autonomous-web-research-agent/metadata.json b/skills/autonomous-web-research-agent/metadata.json new file mode 100644 index 0000000..03afd3b --- /dev/null +++ b/skills/autonomous-web-research-agent/metadata.json @@ -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 +} \ No newline at end of file diff --git a/skills/autonomous-web-research-agent/tests.md b/skills/autonomous-web-research-agent/tests.md new file mode 100644 index 0000000..57b9894 --- /dev/null +++ b/skills/autonomous-web-research-agent/tests.md @@ -0,0 +1,9 @@ +# Tests: autonomous-web-research-agent + +## Test Checklist + +- [ ] Workflow has at least 3 steps +- [ ] All inputs are defined +- [ ] All outputs are defined +- [ ] Failure modes are documented +- [ ] Skill can be loaded without errors -- 2.43.0