dotFiles

Use this skill whenever a task would benefit from authoritative, technology-specific input beyond generalist knowledge — for example during code review, implementation planning, or troubleshooting, whenever the code, design, or issue touches Rust, Bun runtime TypeScript/JavaScript, Java/Spring Cloud microservices, GIS/geospatial processing, web front-end code, or Datadog observability data. This skill identifies the relevant expert sub-agent(s) for the technology or domain in scope, delegates to them via the Task tool, and synthesizes their findings into a single, actionable answer for the calling skill or user.

Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML. Trigger whenever you are about to write an inline script (python3 heredoc, node -e, regex over HTML) or a bare curl for one-off web fetching, scraping, or page exploration.

This skill analyzes a given improvement ticket or idea and provides a detailed plan on how to implement it. It gathers relevant information from the ticket or request, including context, requirements, and constraints, and generates a step-by-step implementation plan. The skill also identifies potential challenges, required tests, and validation steps, and can assist in creating prototypes or breaking down the implementation into smaller tasks or milestones. When the implementation touches a technology with a dedicated expert (e.g. Rust, Bun/TypeScript, Java/Spring Cloud, GIS, web front-end, or Datadog observability), it consults the `ask-the-expert` skill to validate the proposed approach, risks, and tradeoffs before finalizing the plan.

Use this skill when the user wants recently written or modified code reviewed, needs targeted feedback on code quality, security, performance, idiomatic usage, or architecture, or has specific technical questions about their codebase. This skill delegates to the `ask-the-expert` skill to identify the languages and technologies involved and consult the appropriate specialized experts, then synthesizes their findings into a single, prioritized review.

This skill analyzes a given problem or issue and provides a detailed troubleshooting plan to resolve it. It gathers relevant information from the problem description, including context, symptoms, and constraints, and generates a step-by-step troubleshooting plan. The skill also identifies potential causes, required tests, and validation steps, and can assist in creating prototypes or breaking down the troubleshooting into smaller tasks or milestones. When the issue touches a technology with a dedicated expert (e.g. Rust, Bun/TypeScript, Java/Spring Cloud, GIS, web front-end, or Datadog observability), it consults the `ask-the-expert` skill for root-cause input before finalizing the plan.

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.

Create or update a pull request for GitHub repositories. Use when: creating a PR, opening a pull request, pushing changes to an existing PR, rebasing with main, squashing commits, force-pushing with lease, updating a PR branch.

Use this skill when you need a consolidated Datadog-driven system health report for a specific area of responsibility — typically once per day before a daily standup or SoS (Scrum of Scrums) meeting. This skill orchestrates specialized sub-agents that query Datadog for metrics, logs, traces, monitor states, SLOs, and incidents, then synthesizes their findings into a structured, meeting-ready health summary.

A relentless interview to sharpen a plan or design.

Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

Compact the current conversation into a handoff document for another agent to pick up.

Implement a given improvement or bug ticket's implementation plan, previously generated by either the 'brainstorm' or 'troubleshoot' commands. This command will execute the implementation plan, making the necessary changes to the codebase, configuration, or infrastructure as specified in the plan.

Enable code intelligence (go-to-definition, find-references, hover, type info) for any programming language by installing and configuring an LSP server for Copilot CLI. Detects the OS, installs the right server, and generates the JSON configuration (user-level or repo-level). Use when you need deeper code understanding and no LSP server is configured, or when the user asks to set up, install, or configure an LSP server.

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Connect to Postgres databases via the psql CLI using per-environment credential files (e.g. env.prod) and run SQL queries. Use when the user wants to query a Postgres database, inspect or analyze data, run ad hoc SQL, or explore schema. Defaults to a read-only session and requires explicit user confirmation plus --write to run INSERT/UPDATE/DELETE/DDL statements.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Brings up (and tears down) the containers a project needs for its integration tests, using whichever container runtime is available — docker, podman, or the macOS-native "container" CLI, checked in that priority order. Use when the user asks to prepare/start/stop containers for integration tests, e.g. "prepare for IT tests", "start the docker containers for integration tests", "bring up containers for the ITs", "spin up podman for tests", or before running an integration test suite that requires a database/broker/etc. running in containers.

Operate the user's tldraw offline canvas app, including open .tldraw or .tldr files. Use whenever a task involves inspecting, editing, arranging, connecting, linting, or scripting a tldraw Desktop canvas.