squirrelsoft-dev

Advises on choosing the right Claude Code extensibility approach (Skills, Commands, Subagents, Hooks, Plugins, MCP, Output Styles). Activates when user discusses extending Claude Code, creating automation, or is unsure which feature to use. Analyzes use cases and recommends appropriate solutions with trade-off explanations. Use when user mentions "should I use", "what's the best way", "skill or command", "which approach", or discusses extensibility options.

Creates and configures Claude Code hooks for event-driven automation. Activates when user wants to automate tasks, create event handlers, add formatting/logging/notifications, or ensure deterministic behaviors. Updates settings.json safely with hook configurations. Use when user mentions "create hook", "automate", "on save", "pre/post tool", "notification", "formatting hook", or wants always-on behaviors.

Scaffolds complete Claude Code plugin structures with all necessary directories, manifest, and documentation. Activates when user wants to create a new plugin, package features together, or prepare for marketplace distribution. Creates plugin.json, directory structure, and starter documentation. Use when user mentions "create plugin", "new plugin", "scaffold plugin", "plugin structure", or "share via marketplace".

Generates new Claude Code Skills with intelligent defaults. Activates when user discusses creating a new skill, capability, or reusable workflow. Infers purpose from context, creates proper YAML frontmatter, suggests tool restrictions, and sets up supporting file structure. Use when user mentions "create a skill", "new skill", "skill for", or discusses adding reusable capabilities.

Generates custom Claude Code subagents with specialized expertise. Activates when user wants to create a subagent, specialized agent, or task-specific AI assistant. Creates properly formatted .md files with YAML frontmatter, suggests tool restrictions and model selection, generates effective system prompts. Use when user mentions "create subagent", "new agent", "specialized agent", "task-specific agent", or wants isolated context for domain-specific work.

Example skill demonstrating Claude Code capabilities. Activates when user mentions "example", "demo", or "template". Shows how to create effective Skills with proper structure. Use when user wants to see skill examples or understand skill creation.

Master GitHub integration using gh CLI, GitHub API, issue/PR management, GitHub Actions, sprint planning with Projects, and automated workflows. Essential for GitHub-based development automation.

Master Jira integration using acli CLI, Jira REST API, issue management, sprint operations, JQL queries, and ADF comment formatting. Essential for Jira-based project management automation.

Comprehensive code review standards covering security, quality, performance, testing, and documentation. Includes checklists, common issues, and best practices for thorough code reviews.

Master orchestration patterns, multi-agent coordination, and effective workflow composition using the Agency plugin's 51+ specialized agents. Activate when planning complex implementations, coordinating multiple agents, or optimizing development workflows.

Master GitHub workflows including branching strategies, commit standards, PR processes, issue triage, sprint management, and git worktree usage. Activate when planning GitHub workflows, managing sprints, or establishing team conventions.

Comprehensive testing strategy covering test pyramids, framework selection, coverage standards, test organization, mocking patterns, and CI/CD integration. Activate when planning testing approaches, setting quality gates, or establishing test standards.

Perform a thorough, whole-project code review for any language or framework — map the codebase, scan for risky patterns, deep-read the important files, and produce a per-file findings report (file, line, severity, and why it matters). Load this whenever the user asks to review, audit, assess, or critique a codebase, project, module, or directory; to find bugs, code smells, security issues, SOLID or structure problems, or tech debt; or says things like "review this code", "do a code review", "audit the project", "look over this codebase", or "what's wrong with this code". This is for reviewing existing code in place — not for reviewing a single diff or pull request.

Audit one Rust module for real, actionable defects.

Audit one Rust module for real, actionable defects.

Implement a spore-core component across all four language targets (Rust, TypeScript, Python, Go) from a GitHub issue spec. Use this skill whenever the user says "implement issue #N", "implement <ComponentName>", "build the <X> component", or anything that involves translating a spore-core spec issue into working code. Also use it when the user wants to implement a single language target ("implement the Rust version of issue #5"). The skill orchestrates subagents end-to-end: a research/planning agent, a Rust reference-implementation agent, three parallel language agents, and a cross-language verifier agent. The main thread coordinates — it does not write implementation code itself.

Install the full development workflow into a Claude Code project: slash commands for breakdown, spec, work, commit, review, PR, security scanning, and issue triage; agents for architecture, implementation, quality review, and git management. Run this after the greenfield or brownfield skill has set up the project foundation. Trigger phrases: "/workflow", "install workflow", "set up commands", "set up agents", "install breakdown and work commands", "configure my workflow", "install the development workflow".

Configure Claude Code for a brand new project. Detects your stack, runs a short interview, then generates CLAUDE.md, rules, hooks, and settings tailored to your project. Invoke manually with /greenfield or "set up Claude Code", "initialize Claude", "configure Claude for this project".

Configure Claude Code for an existing codebase by discovering its conventions, architecture, testing patterns, and git workflow — then generating tailored CLAUDE.md, rules, hooks, and settings. Use when a developer says "set up Claude Code for this project", "onboard Claude to this repo", "/brownfield", "analyze this codebase for Claude", or opens an existing project with no .claude/ directory. Run the workflow skill after this to install development commands and agents.

Triage GitHub issues by analyzing the codebase and posting structured implementation plans as comments. Use this skill when the user wants to triage, analyze, assess, or plan a GitHub issue — especially when they provide an issue number (e.g., "triage #12", "look at issue 45", "assess this issue"). Also supports triaging all issues in a milestone at once with --milestone flag. Trigger on phrases like "triage", "assess issue", "plan issue", "what would it take to implement #X", "investigate issue", or "analyze issue".

Configuration reference for Cloudwerk applications. Use when setting up cloudwerk.config.ts, choosing a renderer, configuring Vite plugins, or setting up path aliases. Triggers on tasks involving project configuration, renderer selection (hono-jsx vs react), Vite configuration, or Tailwind CSS setup.

Handler, middleware, and component patterns for Cloudwerk applications on Cloudflare Workers. Use when writing route handlers, middleware, page/layout components, or client-side interactive components. Triggers on tasks involving CloudwerkHandler, response helpers (json, redirect), Cloudflare bindings (D1, KV, R2), middleware composition, PageProps, LayoutProps, or client directives.

Monorepo workflow for the Cloudwerk framework. Use when building, testing, or releasing Cloudwerk packages. Covers pnpm workspace commands, package structure, changeset requirements, and test workflows. Triggers on tasks involving building packages, running tests, creating changesets, or understanding the monorepo structure.

File-based routing conventions for Cloudwerk, a full-stack framework for Cloudflare Workers. Use when creating pages, API routes, layouts, middleware, or error boundaries. Triggers on tasks involving route files (page.tsx, route.ts, layout.tsx, middleware.ts, error.tsx, not-found.tsx), dynamic segments ([id], [...slug]), route groups ((group)), loaders, actions, or data loading patterns.

Triage GitHub issues by analyzing the codebase and posting structured implementation plans as comments. Use this skill when the user wants to triage, analyze, assess, or plan a GitHub issue — especially when they provide an issue number (e.g., "triage #12", "look at issue 45", "assess this issue"). Also supports triaging all issues in a milestone at once with --milestone flag. Trigger on phrases like "triage", "assess issue", "plan issue", "what would it take to implement #X", "investigate issue", or "analyze issue".