zach-source

Jujutsu (jj) version control system. Use when working with jj repositories, creating changes, rebasing, managing bookmarks, resolving conflicts, or syncing with Git remotes. Triggers on "jj", "jujutsu", "jj rebase", "jj bookmark", "jj squash", or when user mentions working with jj instead of git.

Infrastructure deployment verification workflow. Use when: (1) Pushing infrastructure/config changes, (2) Deploying to Kubernetes, (3) User says "deploy", "rollout", "verify deployment", (4) After committing Helm/K8s/Hydra/Kratos YAML changes, (5) Need to check deployment status.

Git version control essentials and best practices. Use when working with git repositories, commits, branches, merges, rebases, remotes, or resolving conflicts. Triggers on git commands, branch operations, merge/rebase questions, or version control workflows.

AWS role assumption with Granted CLI. Use when assuming AWS profiles, switching accounts, opening AWS console, or authenticating to AWS. Triggers on: assume, granted, AWS profile, AWS role, AWS SSO, switch AWS account, AWS console, AWS authentication.

Claude Code task framework for reusable workflows. Use when user asks about "/task:run", "/task:list", "/task:new", "create a task", "global tasks", "local tasks", or needs to run structured multi-step workflows. Triggers on task-related questions or when creating reusable automation.

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.

Design comprehensive test cases using PICT (Pairwise Independent Combinatorial Testing) for any piece of requirements or code. Analyzes inputs, generates PICT models with parameters, values, and constraints for valid scenarios using pairwise testing. Outputs the PICT model, markdown table of test cases, and expected results.

Semantic code search tool using natural language queries instead of regex patterns. Use when exploring codebases, finding implementations by concept, or answering 'where do we handle X?' questions.

CI/CD pipeline monitoring and polling. Use PROACTIVELY when user pushes code, creates PR/MR, mentions "wait for CI", "check the build", "monitor pipeline", "watch workflow", or asks about build status. Launches background polling tasks that report back on completion.

Expert guidance for tmux terminal multiplexer and zsh shell configuration, design, and troubleshooting. Use when users need to configure tmux sessions, panes, keybindings, or plugins; set up zsh with vi-mode, plugins (zplug/zinit/oh-my-zsh), completions, or prompts (starship/powerlevel10k); integrate tmux and zsh with Nix/Home Manager; debug shell startup issues, keybinding conflicts, or plugin problems; or design productive terminal workflows.

Vincent Driessen's GitFlow branching model. Use when working with feature/release/hotfix branches, merging to develop or main, creating releases, or managing GitFlow workflows. Triggers on "gitflow", "feature branch", "release branch", "hotfix", "develop branch", "--no-ff", or questions about branch strategy.

Temporal knowledge graph memory system. Use PROACTIVELY at session start to load context, when solving non-trivial problems to check for known solutions, and at session end to persist learnings. Auto-store failure→success learnings when debugging takes 3+ attempts. Auto-store infrastructure context when discovering services/clusters/topology. Triggers on: 'remember this', 'what do you know about', 'save for later', project context questions, approach pivots, or when debugging takes >15 min.

Context recommendation system for reducing action uncertainty. Use PROACTIVELY when user mentions keywords like 'use this kubeconfig', 'our goal is', 'debug this', 'in production', 'deploy to', or when uncertainty about environment, cluster, namespace, or AWS profile drops below 80%.

Experience replay for tool/test/build failures. Invoke IMMEDIATELY when any tool fails (non-zero exit, FAIL/error/panic in output). Looks up known fixes before debugging, records failures and fixes, promotes successful fixes. Triggers on: test failures, build errors, lint failures, compilation errors, any recurring error patterns.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Local Kubernetes development with Tilt. Use when users need to create or modify Tiltfiles, debug multi-service applications, set up live updates, or work with the Tilt development workflow. Covers Tiltfile authoring, extensions, debugging, and integration with kubectl/Helm/Kustomize.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

Debug GitLab CI/CD pipeline failures including vault auth, docker builds, K8s deployments, and job errors. Use when: (1) Pipeline jobs fail, (2) Vault JWT auth issues, (3) Docker build/push errors, (4) K8s deployment failures, (5) "permission denied" or "unauthorized" errors, (6) rkeychain/devenv issues, (7) User asks to check pipeline status, (8) ECR push failures, (9) Runner or executor problems.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

This skill should be used when the user asks to create a hook, add a PreToolUse/PostToolUse/Stop hook, validate tool use, implement prompt-based hooks, use CLAUDE_PLUGIN_ROOT, set up event-driven automation, block dangerous commands, or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

This skill should be used when the user asks to create an agent, add an agent, write a subagent, agent frontmatter, when to use description, agent examples, agent tools, agent colors, autonomous agent, or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

This skill should be used when the user asks to create a slash command, add a command, write a custom command, define command arguments, use command frontmatter, organize commands, create command with file references, interactive command, use AskUserQuestion in command, or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.

DBOS durable execution framework for Go. Use when implementing resilient, failure-recoverable applications with durable workflows, steps, queues, and workflow communication patterns. Triggers on DBOS Go, durable execution Go, resilient workflows Go, saga pattern Go, or when building fault-tolerant Go applications.

OpenTelemetry instrumentation for Go. Use when adding observability with distributed tracing, metrics, logging, context propagation, and exporters (OTLP, Jaeger, Prometheus). Triggers on OpenTelemetry Go, OTel Go, tracing Go, instrumentation Go, observability Go, or when debugging distributed Go systems.

DBOS durable execution framework for Python. Use when implementing resilient, failure-recoverable applications with durable workflows, steps, transactions, queues, and workflow communication patterns. Triggers on DBOS Python, durable execution Python, resilient workflows Python, saga pattern Python, or when building fault-tolerant Python applications.

OpenTelemetry instrumentation for Python. Use when adding observability with distributed tracing, metrics, logging, automatic instrumentation, context propagation, and exporters (OTLP, Jaeger, Prometheus). Triggers on OpenTelemetry Python, OTel Python, tracing Python, instrumentation Python, observability Python, or when debugging distributed Python systems.

AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure programmatically. Covers CDK app structure, construct patterns, stack composition, and deployment workflows.

This skill provides AWS cost optimization, monitoring, and operational best practices with integrated MCP servers for billing analysis, cost estimation, observability, and security assessment.