Conduct a detailed technical review of recent changes or a specific feature, focusing on logic, bugs, code style, and performance. Research false positives and apply fixes for critical and high-priority items.
Usage: When user says "review PR", "code review", or "review [scope]"
Instructions
Analyze Changes:
Use GitHub CLI (gh) or GitHub MCP tools if available to fetch PR diffs, comments, and conversation history.
Identify new or modified code.
Review for logic errors, edge cases, and potential bugs.
Evaluate against project coding standards and style guides.
Check for potential regressions or performance bottlenecks.
Handle Findings:
Research False Positives: Verify if flagged issues are genuine bugs or intentional implementations.
Prioritize: Categorize findings into Critical, High, and Medium.
Next steps: Always provide actionable next steps.
Remediate:
Fix Criticals: Automatically attempt to fix verified "Critical" and "High" priority technical issues (delegate to appropriate coding agent).
Comment: Provide feedback on "Medium" or stylistic items.
Verify:
Ensure the build passes after fixes.
Verify that tests cover the new logic.
Scopes
(default): Review changes in the current working branch/directory.
{feature-name}: Review code within a specific feature folder.
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: brendankowitz-fhirpath-lab-dotnet-technical-review3description: Technical PR Review4---56# Technical PR Review78Conduct a detailed technical review of recent changes or a specific feature, focusing on logic, bugs, code style, and performance. Research false positives and apply fixes for critical and high-priority items.910**Usage**: When user says "review PR", "code review", or "review [scope]"1112## Instructions13141. **Analyze Changes**:15 - Use **GitHub CLI (`gh`)** or **GitHub MCP tools** if available to fetch PR diffs, comments, and conversation history.16 - Identify new or modified code.17 - Review for logic errors, edge cases, and potential bugs.18 - Evaluate against project coding standards and style guides.19 - Check for potential regressions or performance bottlenecks.20212. **Handle Findings**:22 - **Research False Positives**: Verify if flagged issues are genuine bugs or intentional implementations.23 - **Prioritize**: Categorize findings into Critical, High, and Medium.24 - **Next steps**: Always provide actionable next steps.25263. **Remediate**:27 - **Fix Criticals**: Automatically attempt to fix verified "Critical" and "High" priority technical issues (delegate to appropriate coding agent).28 - **Comment**: Provide feedback on "Medium" or stylistic items.29304. **Verify**:31 - Ensure the build passes after fixes.32 - Verify that tests cover the new logic.3334## Scopes3536- (default): Review changes in the current working branch/directory.37- `{feature-name}`: Review code within a specific feature folder.3839---40> Converted and distributed by [TomeVault](https://tomevault.io/claim/brendankowitz) — claim your Tome and manage your conversions.41<!-- tomevault:4.0:skill_md:2026-04-13 -->
Run npx skillmds@latest add tomevault-io/brendankowitz-fhirpath-lab-dotnet-technical-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Technical PR Review It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tomevault-io