torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: reorganize README for better flow

Browse Source 
- Move example workflow image to Why This Server section
- Condense File & Directory Support into single bullet point
- Remove duplicate image/prompt from think_deeper section

This creates a cleaner, more compelling introduction that showcases
real usage before diving into setup details.

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Fahad
2025-06-09 22:47:28 +04:00
parent 0c2c3e1ce3
commit 077e731ce0
1 changed files with 11 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
README.md
View File

@@ -47,16 +47,21 @@ Claude is brilliant, but sometimes you need:
- **Massive context window** (1M tokens) - Gemini 2.5 Pro can analyze entire codebases, read hundreds of files at once, and provide comprehensive insights ([`analyze`](#6-analyze---smart-file-analysis)) - **Massive context window** (1M tokens) - Gemini 2.5 Pro can analyze entire codebases, read hundreds of files at once, and provide comprehensive insights ([`analyze`](#6-analyze---smart-file-analysis))
- **Deep code analysis** across massive codebases that exceed Claude's context limits ([`analyze`](#6-analyze---smart-file-analysis)) - **Deep code analysis** across massive codebases that exceed Claude's context limits ([`analyze`](#6-analyze---smart-file-analysis))
- **Dynamic collaboration** - Gemini can request additional context from Claude mid-analysis for more thorough insights - **Dynamic collaboration** - Gemini can request additional context from Claude mid-analysis for more thorough insights
- **Smart file handling** - Automatically expands directories, filters irrelevant files, and manages token limits when analyzing `"main.py, src/, tests/"`
This server makes Gemini your development sidekick, handling what Claude can't or extending what Claude starts. This server makes Gemini your development sidekick, handling what Claude can't or extending what Claude starts.
## File & Directory Support <div align="center">
<img src="https://github.com/user-attachments/assets/0f3c8e2d-a236-4068-a80e-46f37b0c9d35" width="600">
</div>
All tools accept both individual files and entire directories. The server: **Example Workflow:**
- **Automatically expands directories** to find all code files recursively ```
- **Intelligently filters** hidden files, caches, and non-code files Study the code properly, think deeply about what this does and then see if there's any room for improvement in
- **Handles mixed inputs** like `"analyze main.py, src/, and tests/"` terms of performance optimizations, brainstorm with gemini on this to get feedback and then confirm any change by
- **Manages token limits** by loading as many files as possible within Gemini's context first adding a unit test with `measure` and measuring current code and then implementing the optimization and
measuring again to ensure it improved, then share results. Check with gemini in between as you make tweaks.
```
## Quickstart (5 minutes) ## Quickstart (5 minutes)
@@ -463,18 +468,6 @@ Combine both perspectives to create a comprehensive caching implementation guide
### 2. `think_deeper` - Extended Reasoning Partner ### 2. `think_deeper` - Extended Reasoning Partner
<div align="center">
<img src="https://github.com/user-attachments/assets/0f3c8e2d-a236-4068-a80e-46f37b0c9d35" width="600">
</div>
**Prompt:**
```
Study the code properly, think deeply about what this does and then see if there's any room for improvement in
terms of performance optimizations, brainstorm with gemini on this to get feedback and then confirm any change by
first adding a unit test with `measure` and measuring current code and then implementing the optimization and
measuring again to ensure it improved, then share results. Check with gemini in between as you make tweaks.
```
**Get a second opinion to augment Claude's own extended thinking** **Get a second opinion to augment Claude's own extended thinking**
**Thinking Mode:** Default is `max` (32,768 tokens) for deepest analysis. Reduce to save tokens if you need faster/cheaper responses. **Thinking Mode:** Default is `max` (32,768 tokens) for deepest analysis. Reduce to save tokens if you need faster/cheaper responses.