talmolab
- 7 skills
- 0 followers
- 11 hours ago last updated
- ▌ Openspec Review · talmolabCritically 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.
- ▌ Runai · talmolabUse when submitting, monitoring, exec-ing into, or troubleshooting RunAI GPU jobs for the sleap-roots pipeline on the Salk cluster (project busch-lab / namespace runai-busch-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.
- ▌ Roadmap Status Dashboard · talmolabUse when asked to refresh, publish, or share the sleap-roots ↔ Bloom program's status dashboard for Elizabeth's subgroup — e.g. "update the roadmap artifact", "share the status page", "what's the state of the program for the meeting". Sweeps live state across all program repos before touching the page, since the roadmap doc drifts from reality between sessions faster than it gets corrected.
- ▌ Tauri Pilot · talmolabInspect, interact with, and test the running SLEAP desktop (Tauri) app via the `tauri-pilot` CLI. Use when driving the desktop GUI, automating clicks/typing/navigation, taking screenshots, reading the DOM/accessibility tree, or debugging the desktop build's console/network. Only works against `bun run tauri:dev` (debug builds); the plugin is a no-op in release.
- ▌ Pr · talmolab bundleCreate 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.
- ▌ Investigation · talmolabScaffolds 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.
- ▌ Sleap Support · talmolab bundleHandle 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.