Added 2 plugins, qna-coach and actionable-insights. #1226
Conversation
WalkthroughThis pull request introduces two new plugins to the Changes
Possibly related PRs
Suggested reviewers
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
🔇 Additional comments (3)community-plugins.json (3)
The plugin configuration is complete and aligns well with its intended purpose. The memory prompt is particularly well-crafted with clear guidelines for:
The plugin configuration is complete and aligns well with its intended purpose. The memory prompt effectively:
The configurations reference two icon files:
Let's verify these files exist in the repository. ✅ Verification successfulIcon files are present and correctly referenced ✓ Both required icon files exist at the expected locations:
🏁 Scripts executedThe following scripts were executed for the analysis: Script: #!/bin/bash
# Description: Check if the referenced plugin icon files exist
fd -t f "qna-coach.png|actionable-insights.png" plugins/logos/
Length of output: 130 Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Outside diff range and nitpick comments (2)
community-plugins.json (2)
1257-1268: LGTM! Consider adding chat capability for interactive Q&A.The plugin configuration is well-structured with clear description and detailed memory prompt. The memory prompt effectively guides the AI to identify unasked questions and generate thoughtful follow-ups.
Consider adding chat capability to enable interactive Q&A sessions where users can get real-time suggestions for follow-up questions. This would enhance the plugin's utility during live interviews.
{ "id": "qna-coach", "name": "QnA Coach", "author": "Akshay Kripalani", "description": "Identifies key questions that weren't asked during an interview or Q&A session, helping you get a more complete understanding.", "image": "/plugins/logos/qna-coach.png", "memories": true, + "chat": true, "capabilities": [ - "memories" + "memories", + "chat" ], "memory_prompt": "From the transcript provided, analyze the transcript and identify the main topic of conversation, focusing on the key themes and concepts discussed. Then, analyze the conversation to identify any questions asked about said topic. Consider questions grounded in the topic of the conversation that aim to uncover deeper insights about the subject and enhance the questioner's understanding. \n\nProvide at most 3 high quality, thought-provoking questions that could have been asked during this interview or Q&A session. Focus on questions that could be asked specifically to the person being interviewed and that are likely to lead to further exploration of the topic. \n\nIt is imperative that questions be hyper-specific and not generalized. Encourage questions that are: \n- Open-ended, allowing for detailed responses. \n- Lead to critical thinking. \n- Connected, building on previous answers and leading to further exploration. \n\nIf no such questions are found, simply state 'No relevant questions were identified'. YOUR OUTPUT MUST CONTAIN ONLY THE QUESTIONS SHOULD YOU SEE THEM.", + "chat_prompt": "You are an expert interview coach helping users ask better questions during Q&A sessions. Analyze the ongoing conversation and suggest relevant, thought-provoking follow-up questions in real-time. Focus on questions that are specific, open-ended, and build upon the current discussion to uncover deeper insights.", "deleted": false }
1270-1280: LGTM! Consider adding chat capability for interactive insights.The plugin configuration is well-structured with clear description and detailed memory prompt. The memory prompt effectively guides the AI to extract specific, actionable insights while avoiding generic advice.
Consider adding chat capability to enable interactive sessions where users can get real-time actionable insights. This would help users immediately apply learnings from their conversations.
{ "id": "actionable-insights", "name": "Actionable Insights", "author": "Akshay Kripalani", "description": "Extracts key lessons from conversations, providing one or two specific actions to improve your daily life, free from general advice.", "image": "/plugins/logos/actionable-insights.jpeg", "memories": true, + "chat": true, "capabilities": [ - "memories" + "memories", + "chat" ], "memory_prompt": "From the transcript provided, analyze the transcript and identify the main topic of conversation, focusing on the key themes and concepts discussed. Then, analyze the conversation to identify any lessons that the user can learn from this conversation. Consider lessons grounded in the topic of the conversation that aim to uncover insights about the user, and provide actionable change they can implement IN DAILY LIFE. Takeaways must be HYPERSPECIFIC and tell the user EXACTLY WHAT ONE THING THEY CAN LEARN FROM THIS CONVERSATION. It is IMPERATIVE to AVOID GENERAL ADVICE THAT IS SEEN AS COMMON SENSE. Examples of GOOD ADVICE include: 'your particular action of <some action> could use improvement in <area>; you could have phrased <sentence> in a better way by <changes>'. Examples of BAD ADVICE include: 'challenge your biases; be more inclusive, be more respectful'. Your advice must be such that it is something the user can take action on RIGHT AWAY AND IMPROVE THEIR LIFE. Provide only ONE or AT MAX 2 IF REQUIRED takeaways. If the user mentions learning something, include that. If nothing very specific is mentioned, simply state 'No specific learning'. YOUR OUTPUT MUST ONLY CONTAIN THE LEARNING AND THE LEARNING ONLY.", + "chat_prompt": "You are an expert coach helping users extract actionable insights from their conversations. Focus on providing specific, implementable advice that users can apply immediately to improve their daily lives. Avoid generic advice and ensure each suggestion is concrete and tailored to the user's situation.", "deleted": false }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
⛔ Files ignored due to path filters (2)
plugins/logos/actionable-insights.pngis excluded by!**/*.pngplugins/logos/qna-coach.pngis excluded by!**/*.png
📒 Files selected for processing (1)
community-plugins.json(1 hunks)
|
Fixed a misnamed plugin icon, reopening pr. |
Features:
Summary by CodeRabbit