pwarnock

CLI development patterns with Commander.js, argument parsing, and user experience best practices. Use when creating commands, handling options, formatting output, or building CLI tools.

Release workflow with changesets, version bumping, changelog generation, and npm publishing. Use when preparing releases, managing versions, or publishing to npm.

Security scanning with dependency audits, secret detection, static analysis, and vulnerability management. Use when checking for vulnerabilities, scanning dependencies, or enforcing security gates.

Multi-agent coordination patterns for delegating work between specialized agents, managing agent roles, and orchestrating workflows across multiple AI agents.

Testing patterns with Bun test runner, coverage thresholds, mocking, and CI/CD integration. Use when writing tests, organizing test files, or setting up quality gates.

Bun build system, development workflow, and TypeScript patterns. Use when working with Bun projects, setting up development environment, or managing dependencies with Bun package manager.

Automate Git workflows with atomic commits, Beads integration, and real-time sync. Use when managing Git commits, branches, task tracking, or handling complex multi-file changes with proper validation.

Task management and workflow patterns using liaison. Use when managing tasks, creating workflows, or working with task-driven automation.

Use when checking if project context documents are stale or outdated, when the user says "audit staleness", "check context drift", "are my docs current", or when the session-start hook detected drift. Performs deep analysis of all context documents against current codebase state.

Use when setting up persistent context infrastructure for a project, when the user says "bootstrap context", "set up context", "initialize codified context", or when a project lacks .claude/context/ directory. Creates constitution, trigger tables, failure modes, and subsystem map.

Use when capturing debugging insights, repeated explanations, architecture decisions, or gotchas as durable context. Use when the user says "codify this", "write this down", "remember this", "capture knowledge", or after debugging sessions. Implements the "explained it twice, write it down" methodology.

Use when deciding which agent, skill, or context document to invoke for a given file or task. Consults trigger tables to route work to the right specialist. Activated automatically when working in a project with codified context infrastructure.

Use when reviewing the health and completeness of a project's context infrastructure, when the user says "review context", "context health", "how complete is my context", or periodically during maintenance. Provides infrastructure inventory, coverage analysis, and quality assessment.

Use when capturing knowledge from conversations into durable context documents. Implements the "explained it twice, write it down" methodology for AI coding agents. Use when the user says "write this down", "remember this", "codify this", or when you detect repeated explanations, debugging breakthroughs, or architecture decisions.

Use when setting up or understanding the three-tier codified context framework for AI coding agents. Provides the constitution template, trigger table format, failure modes format, and subsystem map format. Use when the user says "set up context", "create a constitution", "what is codified context", or wants to manually build persistent context infrastructure.

Use when evaluating the quality and completeness of a project's codified context infrastructure. Provides rubrics for scoring constitution, trigger tables, failure modes, and subsystem map quality. Use when the user says "check context health", "how good is my context", "score my context", or during periodic maintenance reviews.

Ban useEffect in React components — enforce derived state, event handlers, data-fetching hooks, key resets, and useMountEffect instead.

Capture debugging insights, architecture decisions, and repeated explanations as durable project context. Implements the "explained it twice, write it down" methodology. Use when you say "write this down", "remember this", "codify this".

Three-tier codified context framework for AI coding agents — constitution, trigger tables, failure modes, and subsystem map templates. Use when you say "set up context", "create a constitution", "what is codified context".

Score and evaluate your project's codified context infrastructure — rubrics for constitution, trigger tables, failure modes, and subsystem map quality. Use when you say "check context health", "score my context".

Scaffold a Claude Code plugin from scratch — guides through directory structure, manifest creation, and best practices. Use when you say "create a plugin", "new plugin", "build a plugin", "scaffold a plugin".

Transform an agent execution plan into a team-ready proposal or RFC with adjustable depth and audience awareness. Use when you say "share this plan", "write a proposal", "create an RFC", "make this shareable".

Navigate Claude Code plugin development documentation and resources. Use when asked "where are the docs", "how do I learn plugin development", "find resources for plugins".

This skill should be used when the user says 'done for today', 'end session', 'capture learnings', 'wrap up', or asks 'what did we learn?'. Captures actionable insights, patterns, and outcomes from the current session into persistent memory with optional Beads issue tracking.

This skill should be used when the user asks to 'create a task from', 'add issue for', 'track work on', or provides conversational task descriptions like 'I need to fix the blog bug' or 'remind me to update the docs'. Converts natural language task descriptions into structured beads with automatic categorization, priority inference, and optional blocking relationships.

Displays tasks and work for today with progress tracking and prioritization. Use when the user asks "what should I work on today", "show my tasks", or "/today". Pulls from the beads task system and provides a personalized, actionable digest.

Approves a blog post draft for publishing by removing the draft flag. Use when the user says "approve", "publish", or "I'm done editing" a blog post.

Creates conversational blog posts with proper Hugo frontmatter and SEO optimization. Use when the user wants to write a blog post, draft blog content, or add an article. Supports four content types (original, curated, embed, project) with voice learning for consistent tone.

Creates professional portfolio project entries with achievement-focused content showcasing impact and technical depth. Use when adding new projects, documenting work accomplishments, or showcasing professional experience. Generates content using strong action verbs and quantifiable metrics.

Creates tech radar entries with opinionated but balanced technical analysis following the BYOR (Build Your Own Radar) structure. Use when the user wants to add a technology to the tech radar, assess a new tool/framework/platform, document technology recommendations, or evaluate whether to adopt/trial/assess/hold a technology.

Generate a session retrospective summarizing work done, decisions made, and learnings. Use when the user says "/retro", "session summary", "what did we do", "retrospective", or at the end of a working session.

Optimize long instruction docs with progressive disclosure for CLAUDE.md, AGENTS.md, and runbooks.

This skill should be used when the user asks to "migrate Prisma to custom output", "fix Prisma monorepo hoisting", "upgrade prisma-client-js to prisma-client", "move Prisma out of node_modules", or encounters "stale Prisma types after deploy", "prisma-client-js deprecated", or build failures where PrismaClient types are missing models in a Turborepo/monorepo. Guides the migration from deprecated prisma-client-js (node_modules output) to prisma-client (custom output directory) in Prisma 7.

This skill should be used when the user mentions "met with", "had coffee with", "breakfast with", "lunch with", "dinner with", "meeting with", asks to "log event", "capture meetup", "add to CRM", "new contact", or describes an interaction with people that should be recorded. Handles natural language and voice transcripts to create structured CRM entries.

Use when coordinating multi-session work via Gastown with in-session subagent parallelization, dispatching convoys, or recognizing parallelization signals in beads issues

Use this skill when the user asks about biblical Greek or Hebrew words, Strong's numbers, original language meanings, word etymology in Scripture, or concordance lookups

Generate tailored resumes from job postings by analyzing role requirements and selecting the best archetype. Use when you have a job description and need a tailored resume, when applying to a new job, or when someone asks which resume variation fits a role. Triggers on requests mentioning job postings, resume tailoring, archetypes, or generating application materials.