Browse Skills

A four-phase debugging framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting fixes. Use for any bug, test failure, or unexpected behavior.

Initializes the Nori agent workflow, checking for protected branches, selecting operating modes (full-send or copilot), and setting coding guidelines and tone before any development begins.

Systematically traces bugs backward through the call stack to identify the original trigger, using instrumentation and stack trace analysis to fix root causes rather than symptoms.

Handle code review feedback with technical rigor: fetch, verify, implement, and test changes before pushing updates. Use when receiving PR comments to avoid performative agreement and ensure each suggestion is sound.

Split large plans into smaller chunks to manage context windows. Use subagents with tests to implement pieces, then integrate the results, ensuring everything passes and fits together coherently.

Automates testing, formatting, linting, type checking, code review, and pull request creation to finalize a feature branch.

Guides through creating custom skills for Claude Code profiles, including writing SKILL.md with required blocks and bundling scripts. Use when you need reusable instructions that persist across sessions.

A systematic debugging approach that replicates bugs by writing external scripts interacting only with public interfaces. Ideal for isolating difficult issues without modifying internals.

Guides through implementing user interfaces by exploring design variations, gathering feedback, setting up frontend environments, and ensuring proper integration with data and routing.

A structured brainstorming skill that uses Socratic questioning to transform rough ideas into fully-formed designs. Use before writing code or implementation plans to explore alternatives and validate incrementally.

Use this skill to query Fluid Framework telemetry in Kusto: investigate errors, track deployments, monitor reliability, and analyze session data across Loop, Whiteboard, and other Microsoft 365 apps.

Aggregates data from IcM, ADO, Kusto, Teams, and WorkIQ to present a consolidated shift status dashboard for OCE (incidents, pipelines, errors). Use for a quick operational overview.