Cline rules

1---
2description: Guides the user through a research process using available MCP tools, offering choices for refinement, method, and output.
3author: https://github.com/nickbaumann98
4version: 1.0
5category: "Workflow"
6tags: ["research", "mcp", "workflow", "assistant-behavior"]
7globs: ["*"]
8---
9# Cline for Research Assistant
10 
11**Objective:** Guide the user through a research process using available MCP tools, offering choices for refinement, method, and output.
12 
13**Workflow:**
14 
151.  **Initiation:** This rule activates automatically when it is toggled "on" and the user asks a question that appears to be a research request. It then takes the user's initial question as the starting `research_topic`.
162.  **Topic Confirmation/Refinement:**
17    *   Confirm the inferred topic: "Okay, I can research `research_topic`. Would you like to refine this query first?"
18    *   Provide selectable options: ["Yes, help refine", "No, proceed with this topic"]
19    *   If "Yes": Engage in a brief dialogue to refine `research_topic`.
20    *   If "No": Proceed.
213.  **Research Method Selection:**
22    *   Ask the user: "Which research method should I use?"
23    *   Provide options:
24        *   "Quick Web Search (Serper MCP)"
25        *   "AI-Powered Search (Perplexity MCP)"
26        *   "Deep Research (Firecrawl MCP)"
27    *   Store the choice as `research_method`.
284.  **Output Format Selection:**
29    *   Ask the user: "How should I deliver the results?"
30    *   Provide options:
31        *   "Summarize in chat"
32        *   "Create a Markdown file"
33        *   "Create a raw data file (JSON)"
34    *   Store the choice as `output_format`.
35    *   If a file format is chosen, ask: "What filename should I use? (e.g., `topic_results.md` or `topic_data.json`)" Store as `output_filename`. Default to `research_results.md` or `research_data.json` if no name is provided.
365.  **Execution:**
37    *   Based on `research_method`:
38        *   If "Quick Web Search":
39            *   Use `use_mcp_tool` with a placeholder for the Serper MCP `search` tool, passing `research_topic`.
40            *   Inform the user: "Executing Quick Web Search via Serper MCP..."
41        *   If "AI-Powered Search":
42            *   Use `use_mcp_tool` for `github.com/pashpashpash/perplexity-mcp` -> `search` tool, passing `research_topic`.
43            *   Inform the user: "Executing AI-Powered Search via Perplexity MCP..."
44        *   If "Deep Research":
45            *   Use `use_mcp_tool` for `github.com/mendableai/firecrawl-mcp-server` -> `firecrawl_deep_research` tool, passing `research_topic`.
46            *   Inform the user: "Executing Deep Research via Firecrawl MCP... (This may take a few minutes)"
47    *   Store the raw result as `raw_research_data`.
486.  **Output Delivery:**
49    *   Based on `output_format`:
50        *   If "Summarize in chat":
51            *   Analyze `raw_research_data` and provide a concise summary in the chat.
52        *   If "Create a Markdown file":
53            *   Determine filename (use `output_filename` or default).
54            *   Format `raw_research_data` into Markdown and use `write_to_file` to save it.
55            *   Inform the user: "Research results saved to `<filename>`."
56        *   If "Create a raw data file":
57            *   Determine filename (use `output_filename` or default).
58            *   Use `write_to_file` to save `raw_research_data` (likely JSON).
59            *   Inform the user: "Raw research data saved to `<filename>`."
607.  **Completion:** End the rule execution.
61 
62---
63**Notes:**
64 
65*   This rule relies on the user having the Perplexity Firecrawl, and Serper MCP servers connected and running.
66*   The "Quick Web Search" option is currently hypothetical and would require a Serper MCP server to be implemented and connected.
67*   Error handling (e.g., if an MCP tool fails) is omitted for brevity but should be considered for a production rule.
68