Testing & Debugging Skills

Analyzes the working tree for uncommitted work, proposes a structured set of commits, waits for user approval, and executes them.

Investigates external context, forces the AI to search for up-to-date documentation, and saves findings to external-references to prevent context loss.

Build high-impact interactive web dashboards and publication-quality Python data visualizations. Translates analytical datasets and KPIs into responsive visual narratives.

Validates structural consistency between code changes and data definitions (DB connections, queries) prior to a PR.

Analyzes the project's libraries and dependencies. It checks for unused dependencies, outdated versions, security vulnerabilities, and generates a structured report of the project's dependency health.

Helps generate project documentation. Scans the repo to understand its structure, adapts to existing documentation styles, proposes a documentation strategy if starting from scratch, and interactively builds out the docs.

Comprehensive documentation manager. Automatically detects whether to architect new project documentation from scratch or synchronize existing documentation with code changes.

Identifies if codebase documentation exists and updates it to reflect code changes before publishing a PR.

Spawns a council of specialized subagents tailored to discuss, debate, and refine a user's idea or proposed change from multiple perspectives.

Analyzes recent code changes to extract architectural decisions, lessons, patterns, and surprises, documenting them for future reference.

Must be triggered whenever the user asks to solve a problem, fix a bug, or debug an issue. Performs an organized debugging process, systematically isolating the root cause without assumptions, and concludes by writing tests and documentation to prevent regressions.

Analyzes code review comments left by other developers on an active Pull Request, extracting pending tasks, suggestions, and offering to reply.

Analyzes other open Pull Requests in the repository to alert if there are parallel PRs that might conflict with the current changes.

Assists in reviewing Pull Requests from other people. Understands the PR goal, reads available documentation, asks the user clarifying questions, focuses solely on modified code, and outputs quality observations with criticality levels.

Acts as a critical self-reviewer for your own Pull Requests (draft or published). Instead of just leaving comments, it analyzes the diff and proactively suggests and applies concrete code fixes.

Interactively sets up the initial architecture of a new project. It gathers requirements, researches technologies, proposes a stack and folder structure with constant user interaction, and finally scaffolds the initial files and a comprehensive README.md.

Performs a deep code quality, security, and structure audit on modified files prior to publishing a PR.

Performs a static analysis of modified or untracked files before a commit to ensure code quality and English-only rules.

Analyzes git commits to automatically draft comprehensive bilingual release notes (English and Spanish) grouped by feature, bug fix, and maintenance.

Analyzes git commits since the last tag and determines the next semantic version. Handles stable, QA, and RC tags.

Summarizes the current AI coding session by reading the transcript and generating a structured Markdown report saved to docs/coding-sessions/.

Write, translate, and optimize high-performance SQL queries across major database engines. Diagnoses execution anti-patterns, recommends indexing strategies, and refactors complex joins into clean CTEs.

Analyzes the repository for technical debt, including outdated dependencies, dead code, duplication, and architectural inconsistencies. Provides a classified report based on criticality, effort, and risk.

Automatically generates tests for modified code if no existing tests cover the changes.