Checkpoint-between-waves cadence for multi-file refactors. After each logical batch (wave) of edits, run typecheck + tests; commit only on green; roll back the wave (not the whole branch) on red. Use for any refactor touching more than three files or three distinct concerns.

Checkpoint-between-waves cadence for multi-file refactors. After each logical batch (wave) of edits, run typecheck + tests; commit only on green; roll back the wave (not the whole branch) on red. Use for any refactor touching more than three files or three distinct concerns.

Git worktree creation, agent isolation, parallel task execution with EnterWorktree/ExitWorktree, branch-per-worktree patterns, and cleanup lifecycle for Claude Code

Git worktree creation, agent isolation, parallel task execution with EnterWorktree/ExitWorktree, branch-per-worktree patterns, and cleanup lifecycle for Claude Code

This skill should be used when building or registering an agent that operates inside Linear — agent signals, agent interaction, OAuth actor mode, AIG (Agent Intelligence Gateway). Activates on "linear agent", "agent signal", "agent interaction", "linear aig", "agents in linear".

This skill should be used when building or registering an agent that operates inside Linear — agent signals, agent interaction, OAuth actor mode, AIG (Agent Intelligence Gateway). Activates on "linear agent", "agent signal", "agent interaction", "linear aig", "agents in linear".

Blazor forms, EditForm, input components, DataAnnotations, FluentValidation, and custom validation

Blazor forms, EditForm, input components, DataAnnotations, FluentValidation, and custom validation

Deploying .NET apps to Azure Container Apps, App Service, Docker, and Kubernetes with CI/CD

Deploying .NET apps to Azure Container Apps, App Service, Docker, and Kubernetes with CI/CD

Audit a workflow or business process against insurance, mortgage, or financial services regulatory requirements. Use when a client workflow needs regulatory sign-off or when validating that a proposed automation meets compliance requirements before build.

Audit a workflow or business process against insurance, mortgage, or financial services regulatory requirements. Use when a client workflow needs regulatory sign-off or when validating that a proposed automation meets compliance requirements before build.

Computer use and GUI automation patterns — when to use GUI automation vs shell/MCP/browser tools, visual validation techniques, native app testing, and guardrails for visual regression workflows

Computer use and GUI automation patterns — when to use GUI automation vs shell/MCP/browser tools, visual validation techniques, native app testing, and guardrails for visual regression workflows

Domain knowledge for multi-agent council review protocols, orchestration patterns, scoring systems, and deliberation frameworks

Domain knowledge for multi-agent council review protocols, orchestration patterns, scoring systems, and deliberation frameworks

Federated registry protocol for multi-source plugin resolution with policy enforcement, lockfile management, and conflict detection across local, team, org, and public registries.

Federated registry protocol for multi-source plugin resolution with policy enforcement, lockfile management, and conflict detection across local, team, org, and public registries.

Intelligent model selection for Claude Code — decision matrices, cost tables, budget planning, and subagent model assignment for optimal cost/quality tradeoffs

Intelligent model selection for Claude Code — decision matrices, cost tables, budget planning, and subagent model assignment for optimal cost/quality tradeoffs

Pre-flight check to run before any Agent-tool spawn. Prevents the "Prompt is too long" rejection class by enforcing a 5-section minimum-viable-prompt template and estimating forwarded context cost. Use whenever you are about to call the Agent tool with more than a one-paragraph prompt.

Pre-flight check to run before any Agent-tool spawn. Prevents the "Prompt is too long" rejection class by enforcing a 5-section minimum-viable-prompt template and estimating forwarded context cost. Use whenever you are about to call the Agent tool with more than a one-paragraph prompt.

Research agent configurations for gathering data to build accurate, detailed diagrams

Research agent configurations for gathering data to build accurate, detailed diagrams

Expert knowledge for scroll-triggered animations, parallax effects, and scroll-linked interactions that create immersive storytelling experiences.

Expert knowledge for scroll-triggered animations, parallax effects, and scroll-linked interactions that create immersive storytelling experiences.

Understanding and optimizing Claude Code session performance — token tracking, bottleneck identification, caching behavior, and cost estimation

Understanding and optimizing Claude Code session performance — token tracking, bottleneck identification, caching behavior, and cost estimation

Background tasks and worker services with IHostedService, BackgroundService, and .NET hosted service patterns

Background tasks and worker services with IHostedService, BackgroundService, and .NET hosted service patterns

This skill should be used when the user asks to "create a Confluence page", "write documentation", "write a TDD", "create an ADR", "write a runbook", or "publish to Confluence" — authoring and linking technical documentation in Confluence from Jira work.

This skill should be used when the user asks to "create a Confluence page", "write documentation", "write a TDD", "create an ADR", "write a runbook", or "publish to Confluence" — authoring and linking technical documentation in Confluence from Jira work.

This skill should be used when uploading files to Linear, linking external URLs as attachments, or downloading existing attachments with auth. Activates on "linear attachment", "linear file upload", "fileUpload mutation", "attachmentLinkCreate".

This skill should be used when uploading files to Linear, linking external URLs as attachments, or downloading existing attachments with auth. Activates on "linear attachment", "linear file upload", "fileUpload mutation", "attachmentLinkCreate".

Auto mode permission handling — classifier-based approvals, PermissionDenied hook, defer permissionDecision, and autonomy profiles for hands-off Claude Code usage

Auto mode permission handling — classifier-based approvals, PermissionDenied hook, defer permissionDecision, and autonomy profiles for hands-off Claude Code usage

Expert knowledge for GSAP (GreenSock Animation Platform) - the industry-standard JavaScript animation library for professional-grade animations with precise timeline control.

Expert knowledge for GSAP (GreenSock Animation Platform) - the industry-standard JavaScript animation library for professional-grade animations with precise timeline control.

Domain knowledge for the cowork marketplace seed catalog, including all 17 items mapped to 16 installed plugins with their agents, skills, and commands

Domain knowledge for the cowork marketplace seed catalog, including all 17 items mapped to 16 installed plugins with their agents, skills, and commands

SignalR for real-time communication in Blazor apps including hubs, groups, streaming, and scaling

SignalR for real-time communication in Blazor apps including hubs, groups, streaming, and scaling

This skill should be used when writing or reviewing GraphQL queries against the Linear API — selecting fragments, navigating connection types, batching, and avoiding deprecated fields. Activates on "linear graphql", "linear query", "linear api", "linear schema".

This skill should be used when writing or reviewing GraphQL queries against the Linear API — selecting fragments, navigating connection types, batching, and avoiding deprecated fields. Activates on "linear graphql", "linear query", "linear api", "linear schema".

This skill should be used when implementing Linear OAuth 2.0, OAuth actor authorization, or file-storage authentication. Activates on "linear oauth", "linear auth", "actor token", "linear-actor-token", "file storage".

This skill should be used when implementing Linear OAuth 2.0, OAuth actor authorization, or file-storage authentication. Activates on "linear oauth", "linear auth", "actor token", "linear-actor-token", "file storage".

This skill should be used when fetching large result sets from Linear — cursor pagination, filter DSL, sorting, and complexity budgeting. Activates on "linear pagination", "linear filter", "linear cursor", "linear filtering".

This skill should be used when fetching large result sets from Linear — cursor pagination, filter DSL, sorting, and complexity budgeting. Activates on "linear pagination", "linear filter", "linear cursor", "linear filtering".

This skill should be used when designing bulk operations against Linear — complexity budgets, exponential backoff, request pacing, and avoiding 429s. Activates on "linear rate limit", "linear 429", "linear throttle", "complexity budget".

This skill should be used when designing bulk operations against Linear — complexity budgets, exponential backoff, request pacing, and avoiding 429s. Activates on "linear rate limit", "linear 429", "linear throttle", "complexity budget".

This skill should be used when implementing Linear integrations using the official @linear/sdk — creating issues programmatically, advanced fetch/modify patterns, error handling, and type safety. Activates on "linear sdk", "@linear/sdk", "linear client", "linear typescript".

This skill should be used when implementing Linear integrations using the official @linear/sdk — creating issues programmatically, advanced fetch/modify patterns, error handling, and type safety. Activates on "linear sdk", "@linear/sdk", "linear client", "linear typescript".

This skill should be used when registering, verifying, or processing Linear webhooks — HMAC signatures, replay protection, idempotency, dead-letter queues. Activates on "linear webhook", "webhook signature", "Linear-Signature", "webhook secret".

This skill should be used when registering, verifying, or processing Linear webhooks — HMAC signatures, replay protection, idempotency, dead-letter queues. Activates on "linear webhook", "webhook signature", "Linear-Signature", "webhook secret".

# Claude Agent SDK

# Claude Agent SDK

Testing Blazor apps with bUnit, xUnit, WebApplicationFactory, and integration testing patterns

Testing Blazor apps with bUnit, xUnit, WebApplicationFactory, and integration testing patterns

Expert knowledge for pure CSS animations - lightweight, performant animations using CSS keyframes, transitions, and modern CSS features without JavaScript dependencies.

Expert knowledge for pure CSS animations - lightweight, performant animations using CSS keyframes, transitions, and modern CSS features without JavaScript dependencies.

Entity Framework Core patterns for data access, migrations, relationships, performance, and best practices

Entity Framework Core patterns for data access, migrations, relationships, performance, and best practices

gRPC service development in .NET for high-performance inter-service communication

gRPC service development in .NET for high-performance inter-service communication

This skill should be used when the user asks to "run a Harness pipeline", "trigger a deployment pipeline", "monitor a Harness execution", or "check pipeline status" — executing and watching Harness pipelines with Jira integration.

This skill should be used when the user asks to "run a Harness pipeline", "trigger a deployment pipeline", "monitor a Harness execution", or "check pipeline status" — executing and watching Harness pipelines with Jira integration.

Monitor tool for streaming background process events into conversations — tail logs, watch CI, auto-fix dev server crashes, and /loop self-pacing without Bash sleep loops

Monitor tool for streaming background process events into conversations — tail logs, watch CI, auto-fix dev server crashes, and /loop self-pacing without Bash sleep loops

Rendering ASCII progress dashboards with phase/epic/task breakdown and velocity metrics

Rendering ASCII progress dashboards with phase/epic/task breakdown and velocity metrics

Deep research before task execution using 4-source protocol: codebase→Perplexity→Context7→Firecrawl

Deep research before task execution using 4-source protocol: codebase→Perplexity→Context7→Firecrawl

Expert knowledge for physics-based spring animations - natural, organic motion that follows real-world physics principles for delightful user experiences.

Expert knowledge for physics-based spring animations - natural, organic motion that follows real-world physics principles for delightful user experiences.

Ultraplan cloud planning — kick off a plan in the cloud from your terminal, review and revise in the browser, then execute remotely or send back to CLI

Ultraplan cloud planning — kick off a plan in the cloud from your terminal, review and revise in the browser, then execute remotely or send back to CLI

Authentication and authorization in Blazor with ASP.NET Core Identity, Entra ID, JWT, and policy-based auth

Authentication and authorization in Blazor with ASP.NET Core Identity, Entra ID, JWT, and policy-based auth

Blazor rendering optimization, virtualization, lazy loading, caching, and memory management

Blazor rendering optimization, virtualization, lazy loading, caching, and memory management

# Channels Reference

# Channels Reference

Universal reference for Claude Code automation surface — hooks, skills, plugins, sub-agents, agent teams, MCP, scheduled tasks, channels, routines, headless/SDK, checkpointing, permissions. Invoke when designing automations that leverage Claude Code features or when user asks "how do I automate X with Claude Code".

Universal reference for Claude Code automation surface — hooks, skills, plugins, sub-agents, agent teams, MCP, scheduled tasks, channels, routines, headless/SDK, checkpointing, permissions. Invoke when designing automations that leverage Claude Code features or when user asks "how do I automate X with Claude Code".

Idempotent update of an existing Claude Code setup — re-fingerprint the repo, propagate updates to sub-repos, refresh docs/context, section-merge CLAUDE.md/README.md, fix configuration drift. Use this skill whenever the user runs /cc-sync, asks to "update the claude setup", "propagate to sub-repos", "fix drift", "resync", or reports that the .claude/ directory has gone stale.

Idempotent update of an existing Claude Code setup — re-fingerprint the repo, propagate updates to sub-repos, refresh docs/context, section-merge CLAUDE.md/README.md, fix configuration drift. Use this skill whenever the user runs /cc-sync, asks to "update the claude setup", "propagate to sub-repos", "fix drift", "resync", or reports that the .claude/ directory has gone stale.

# Claude Code CLI Reference

# Claude Code CLI Reference

Knowledge for launching, managing, and monitoring cowork sessions that orchestrate multiple plugin agents in parallel

Knowledge for launching, managing, and monitoring cowork sessions that orchestrate multiple plugin agents in parallel

.NET Aspire for cloud-native app orchestration, service discovery, telemetry, and component integrations

.NET Aspire for cloud-native app orchestration, service discovery, telemetry, and component integrations

Expert knowledge for Framer Motion - the production-ready motion library for React. This skill enables declarative animations, gesture recognition, and layout animations with optimal performance.

Expert knowledge for Framer Motion - the production-ready motion library for React. This skill enables declarative animations, gesture recognition, and layout animations with optimal performance.

Automation YAML patterns, triggers, conditions, actions, and best practices for Home Assistant.

Automation YAML patterns, triggers, conditions, actions, and best practices for Home Assistant.