talmolab

Create a well-structured GitHub PR with proper branching, testing, formatting, and documentation. Use when the user says "create a PR", "make a PR", "open a pull request", or wants to submit changes for review. Handles the full workflow: branch creation, implementation, testing, formatting, committing, and PR creation with comprehensive descriptions.

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

Handle SLEAP GitHub support workflow for issues and discussions. Use when the user says "support", provides a GitHub issue/discussion number like "#2512", or asks to investigate a user report from talmolab/sleap. Scaffolds investigation folders, downloads posts with images, analyzes problems, and drafts friendly responses.

Capture and visually inspect Qt GUI widgets using screenshots. Use when asked to verify GUI rendering, test widget appearance, check layouts, or visually inspect any PySide6/Qt component. Enables Claude to "see" Qt interfaces by capturing offscreen screenshots and analyzing them with vision.

Test local Jekyll build and visualize pages using Playwright MCP. Starts the development server, navigates through key pages, captures screenshots, and validates rendering. Use when testing local changes before deployment.

Interactive guide for adding new lab members to the website. Gathers information via web research, helps write appropriate bios, optimizes images, and generates properly formatted member files. Use when adding new team members, updating member info, or marking members as alumni.

Generate comprehensive lab member rosters in both markdown and CSV formats. Analyzes member profiles, git history, and alumni information to create detailed rosters with role transitions, team assignments, and career tracking. Use when user mentions roster, team list, lab members, or updating member information.

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

Run test coverage analysis, identify missed and partial lines, and write tests to improve coverage. Use this when the user asks to check coverage, improve coverage, or write tests for uncovered code. This skill detects both completely missed lines and partially covered lines (executed but missing branch coverage) to match Codecov analysis.

Create a well-structured GitHub PR with proper branching, testing, formatting, and documentation. Use when the user says "create a PR", "make a PR", "open a pull request", or wants to submit changes for review. Handles the full workflow: branch creation, implementation, testing, formatting, committing, and PR creation with comprehensive descriptions.

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

Create a well-structured GitHub PR with proper branching, testing, formatting, and documentation. Use when the user says "create a PR", "make a PR", "open a pull request", or wants to submit changes for review. Handles the full workflow: branch creation, implementation, testing, formatting, committing, and PR creation with comprehensive descriptions.

Critically review an OpenSpec proposal using a team of specialized subagents. Use when: reviewing proposals before approval, validating spec quality, checking TDD plans, ensuring scientific rigor (metadata, reproducibility, traceability), and verifying GitHub issue alignment. Launches 5 parallel subagents for deep, adversarial review.

Scaffolds a structured investigation in scratch/ for empirical research and documentation. Use when the user says "start an investigation" or wants to: trace code paths or data flow ("trace from X to Y", "what touches X", "follow the wiring"), document system architecture comprehensively ("document how the system works", "archeology"), investigate bugs ("figure out why X happens"), explore technical feasibility ("can we do X?"), or explore design options ("explore the API", "gather context", "design alternatives"). Creates dated folder with README. NOT for simple code questions or single-file searches.

Use when submitting, monitoring, exec-ing into, or troubleshooting RunAI GPU jobs for the sleap-roots pipeline on the Salk cluster (project talmo-lab / namespace runai-talmo-lab) — e.g. running the predictor stage interactively, debugging a stuck pod, or staging data over the /hpi/hpi_dev NFS mount. Adapted from the mosquito-cfd runai-cluster-skill.

Scaffolds a template for a small investigation for empirical experimentation. Use when the user asks for an investigation, experiment or research to support making design decisions, assess performance or try out a new idea that requires data or an MVP.