What kind of questions does this skill generate?

It generates high-level exploration questions focused on how the codebase currently works, such as logic flows, component contracts, and existing implementation details.

Does it suggest new feature implementations?

No, the skill is strictly prohibited from asking how to build things or suggesting improvements. It focuses entirely on documenting what currently exists.

Can it read feedback from project management tools?

Yes, if provided with a ticket file path, it can parse comments mentioning specific assistants (like linear-assistant or Claude) to extract feedback.

How many questions does it typically produce?

Depending on the complexity of the task, it typically generates between 3 to 8 high-level research questions.

Does it integrate with GitHub?

Yes, it uses internal RPI commands to generate GitHub permalinks for the documents it updates, making them easy to share and review.

Codebase Research Iteration

Name: Codebase Research Iteration
Author: mshuffett

bymshuffett

Productivity & Workflow

Refines and updates technical research questions based on user feedback and ticket comments.

About

This skill automates the refinement of technical research documents within the RPI workflow. It systematically reads existing research questions, processes feedback from external sources like ticket comments or direct user input, and regenerates specific, discovery-focused questions about a codebase's current state. By adhering to strict guidelines that focus exclusively on existing implementations rather than proposed changes, it ensures high-quality architectural exploration and knowledge sharing before development begins.

Key Features

Strict exploration guidelines to prevent implementation detail leakage
Preservation of YAML frontmatter and standard document formatting
Automated feedback processing from ticket comments and user mentions
0 GitHub stars
Integration with GitHub permalinks for easy document navigation
Tailored question generation based on task complexity and scope

Use Cases

Refining research plans after receiving feedback from lead engineers on project tickets
Updating technical discovery documents to focus on specific architectural patterns
Standardizing codebase exploration questions for team-wide consistency

About

Key Features

Strict exploration guidelines to prevent implementation detail leakage
Preservation of YAML frontmatter and standard document formatting
Automated feedback processing from ticket comments and user mentions
0 GitHub stars
Integration with GitHub permalinks for easy document navigation
Tailored question generation based on task complexity and scope

Use Cases

Refining research plans after receiving feedback from lead engineers on project tickets
Updating technical discovery documents to focus on specific architectural patterns
Standardizing codebase exploration questions for team-wide consistency