workflows

You are implementing an approved plan systematically.

You are creating a detailed implementation plan through an interactive process.

You are conducting comprehensive codebase research by composing specialized skills.

You are sharing personal documents to the team's shared namespace.

Upgrade the workflows plugin from one version to another, handling both automated migrations and edge cases that require reasoning.

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the location of files, it will also give you code details!

Deep dive into complex error messages and stack traces. Call error-analyzer when you encounter cryptic errors that require investigation across multiple files.

Analyzes GCP logs and resources to diagnose issues. Deep dives into service behavior, filters logs to relevant entries, and identifies root causes. Use when investigating a specific service or issue.

Locates GCP logs and resources matching criteria. Fetches logs from Cloud Logging, queries IAM resources, and returns structured results. Use when you need to find logs or resources broadly without filtering or analysis.

Finds patterns and correlations across GCP services. Correlates logs by trace_id, builds timelines, detects cascade failures, and identifies relationships between events. Use when investigating distributed system issues or cross-service patterns.

Analyzes Kubernetes resources to diagnose issues. Deep dives into pod health, events, logs, and configurations. Identifies root causes for failures, crashes, and performance issues. Use when investigating specific resource problems.

Locates Kubernetes resources matching criteria. Lists pods, deployments, services, and other K8s resources. Returns structured results without analyzing state. Use when you need to find resources broadly.

Finds patterns and correlations across Kubernetes resources. Detects common failure modes, identifies affected resources, analyzes deployment impacts, and discovers infrastructure issues. Use when investigating cluster-wide or multi-resource problems.

Analyzes Linear issues to understand problem details, extract technical information, and identify related issues. Deep dives into descriptions, comments, labels, and relationships. Use when investigating specific issues for debugging context.

Locates Linear issues matching criteria. Lists issues by team, label, state, project, or search query. Returns structured results without analyzing content. Use when you need to find issues broadly.

Finds patterns and trends across Linear issues. Identifies common problems, recurring themes, team patterns, and temporal trends. Correlates issues with deployments or events. Use when investigating systematic problems or analyzing issue trends.

Generate tests following project patterns without loading test code into main agent context

The research equivalent of codebase-analyzer. Use this subagent_type when wanting to deep dive on a research topic. Not commonly needed otherwise.

Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you can guess this is the `thoughts` equivilent of `codebase-locator`

Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagent_type today to find any and all answers to your questions! It will research deeply to figure out and attempt to answer your questions! If you aren't immediately satisfied you can get your money back! (Not really - but you can re-run web-search-researcher with an altered prompt in the event you're not satisfied the first time)

ALWAYS check this skill before using grep, glob, Task tool, or doing any codebase exploration. Guides you to use specialized agents that are more efficient than basic tools.

Use BEFORE reading multiple files to understand code. Reminds you to use codebase-analyzer agent instead of manual file reading.

Use BEFORE running grep or glob commands. Reminds you to use codebase-locator agent instead of basic file search tools.

Use BEFORE using the Task tool. Ensures you select the correct specialized subagent_type instead of generic agents.

Use when encountering errors or bugs to follow a systematic debugging process instead of jumping to conclusions.

Determine feature slug interactively by auto-detecting next number and prompting user for description

Use during planning to discover and document available project commands (make targets, npm scripts, etc.) for success criteria.

Use during planning to discover and document test patterns and conventions for writing consistent tests.

Use when writing tests to ensure they follow project conventions. References patterns from thoughts/notes/testing.md.

Use when creating research or plan documents to gather git commit, branch, repository info.

ALWAYS check before using gcloud commands. Guide for GCP-related skills and tools.

Query GCP Cloud Logging for errors, service logs, and request traces. Use when investigating GCP-hosted services.

ALWAYS check before using kubectl commands. Guide for Kubernetes-related skills.

Launch ephemeral debug container in running pod for interactive debugging. Use when you need to debug a pod without restarting it.

Query Kubernetes resources (pods, deployments, services, events). Use when checking cluster state and resource status.

ALWAYS check before working with Linear issues. Guide for Linear-related skills for ticket management and debugging workflows.

Fetch and view Linear issues/tickets. List, search, read issue details, status, comments. Use when investigating tickets or gathering debugging context.

Update Linear issues with debugging findings. Add comments, change status, update labels, set priority. Use after completing investigations.

Share personal documents to the shared namespace with atomic git commit and push

Guide for efficient agent orchestration during implementation to conserve main agent context

Use when creating implementation plans to research codebase patterns and gather context for planning.

Use when conducting codebase research to orchestrate specialized agents in parallel for comprehensive investigation.

Append phase completion details or final summary to changelog.md during implementation

Generic migration orchestrator that reads CHANGELOG.md to understand and execute version-specific migrations

Use after implementing changes to run verification commands and ensure tests pass, code builds, and functionality works.

Use when creating git commits to ensure consistent, clear commit messages following conventional commits format.

Use when creating implementation plans to generate properly structured plans with phases, success criteria, and project references.

Use when creating pull requests to write clear, structured PR descriptions that help reviewers understand changes.

Use when documenting research findings to create properly structured research documents with frontmatter, sections, and file references.