workflow-skills

Analyze account usage state and trends from Snowflake data. Use when analyzing account usage, investigating trends by product, reviewing account activity, examining organization metrics, or providing account insights. Accepts account name or organization identifier as input. (project, gitignored)

Systematic 5-phase workflow for handling PR review comments. Fetches review threads via gh api (not gh pr view), triages by priority, executes fixes via sub-agent, posts inline GitHub replies, and commits. Invoke when asked to "address PR feedback", "respond to review comments", or "handle PR review".

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Generate production-ready API scaffolds with Datadog instrumentation. Supports FastAPI, Express/TypeScript, Flask, and Spring Boot. Use when creating new API projects for curriculum, training demos, or lab environments.

Scaffold Astro components, layouts, and pages with TypeScript props, Tailwind CSS styling, proper hydration patterns, and best practice defaults. Use when creating new Astro files, building component libraries, or setting up project structure.

Configure content collections with Zod schemas, query patterns, and type-safe access. Use when setting up blog systems, documentation sites, managing structured content, or building content-driven applications.

Audit Astro applications for performance issues including bundle size, hydration patterns, image optimization, build-time performance, accessibility, and Core Web Vitals. Use when optimizing performance, debugging slow pages, or preparing for production deployment.

Create comprehensive test suites with unit, integration, and e2e tests. Use when writing tests, setting up test automation, creating test fixtures, configuring CI test pipelines, or improving test coverage.

Design RESTful APIs, microservice boundaries, and database schemas. Use when designing API endpoints, planning service architecture, creating database schemas, implementing caching strategies, or setting up authentication patterns.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Incrementally fix TypeScript and build errors one at a time, re-running the build after each fix to verify resolution.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Quick capture to the Obsidian vault. Routes content to daily note or Inbox based on type. Use when the user says "capture", "note this", "jot down", "quick note", "add to inbox", or "meeting note".

Safely scans all git worktrees, checks merge status and PR state, categorizes them (Merged/PR Closed/Remote Deleted/Active), presents a report, and deletes with user approval. Never deletes the current worktree. Invoke when asked to "clean up worktrees", "remove merged worktrees", or "prune worktrees".

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Generate and validate conventional commit messages following the Conventional Commits specification. Analyzes staged changes to determine type, scope, and subject. Use when creating git commits or validating commit message format.

Interactive, lesson-by-lesson course content review for the learning-center repository. Reviews LMS lessons and lab assignment.md files against the Learning Center style guides and Google Technical Writing best practices. Presents findings conversationally one lesson at a time, pausing between lessons for the reviewer to absorb results. Read-only: flags issues with severity ratings and suggests fixes but never modifies files or leaves PR comments. Use when the user says "review course", "course review", "review lessons", "review this course", or asks for a content/style review while working in the learning-center repository.

Create a structured feature implementation plan as a markdown document with progress tracking, status indicators, critical decisions, and modular task breakdown. For multi-session or ticket-driven work, creates a full ExecPlan living document.

Create exhaustive, searchable reference documentation for APIs, libraries, and configuration systems. Use when documenting API references, configuration options, library methods, schema definitions, or creating comprehensive technical references.

Transform complex technical concepts into engaging, hands-on learning experiences with progressive skill building. Use when writing tutorials, creating learning guides, designing hands-on exercises, or teaching technical concepts.

Generate a comprehensive curriculum performance report for a Datadog Learning Center curriculum area. Queries Snowflake for enrollment, completion, survey, RUM pageview, and demographic data; analyzes git history for content staleness; compiles a markdown report and interactive HTML dashboard. Use when asked to generate a course performance report, curriculum analytics, learning center metrics, course health report, or content staleness analysis for any curriculum area (APM, Logs, Infrastructure, Security, Monitors, RUM, etc.). Accepts a curriculum area label and category slug pattern as inputs.

Estimate Datadog usage cost for a set of orgs matched by name pattern (e.g., -LMS, -DEMO, -PARTNER) from Snowflake. Use when asked about the cost of LMS orgs, training sandbox costs, demo org costs, curriculum org usage, or generating periodic org cost reports for any internal org group. Accepts an org name suffix/pattern or parent org ID as input. Outputs a markdown report with cost breakdown by product plus Metabase SQL queries.

Configure CI/CD pipelines, containerize applications with Docker and Kubernetes patterns. Use when setting up deployments, writing Dockerfiles, creating K8s manifests, configuring CI/CD, or implementing deployment strategies.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Auto-generate documentation for curriculum projects including OpenAPI specs, Instruqt lab guides, architecture docs, tutorials, and README files. Use when creating project documentation or training material docs.

Create production-ready Docker Compose configurations for multi-container applications. Supports API, fullstack, microservices, and Datadog-monitored setups with multi-stage builds, health checks, and proper networking.

Docker and Docker Compose reference patterns for local development, container security, networking, volume strategies, and multi-service orchestration. Complements docker-compose-setup (scaffolding) with best-practice reference.

Create OpenAPI/Swagger specifications, generate SDK documentation, and write developer-focused API guides. Use when creating API documentation, writing endpoint specs, documenting REST APIs, or generating client library documentation.

Create comprehensive technical documentation with clear structure, visual aids, and progressive disclosure patterns. Use when documenting systems, writing technical guides, creating architecture docs, or explaining complex codebases.

End-of-day wrap-up that summarizes completed tasks, surfaces carryover items, and appends to today's daily note. Use when the user says "end of day", "eod", "wrap up", "done for today", or "daily wrap".

Cluster related instincts into skills, commands, or agents

Execute a feature implementation plan precisely as documented, writing elegant modular code that follows existing codebase conventions. Updates progress tracking as each step completes. For ExecPlan living documents, delegates to the execplan-executor agent.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Build React components with hooks, responsive layouts, and accessible UI. Use when creating React components, implementing state management, styling with Tailwind or CSS-in-JS, or ensuring accessibility compliance.

Pin GitHub Actions to commit SHAs to prevent supply chain attacks. Use when updating workflow files to pin third-party actions to full 40-character commit SHAs instead of mutable tags. Handles tag resolution, annotated tags, and validates against GitHub API. Also use when scanning workflow files to update all third-party actions to their latest versions.

Write idiomatic Go code with goroutines, channels, and interfaces. Use when writing Go code, implementing concurrency patterns, designing Go interfaces, handling errors in Go, or optimizing Go performance.

Scan CLAUDE.md and extract architectural decisions, constraints, tech stack, and key patterns into the memory system. Use when starting a new project, after updating CLAUDE.md, or to sync project docs into cross-session memory.

Expert guidance for homelab infrastructure, self-hosting, and Raspberry Pi optimization. Use when recommending self-hosted services, configuring Docker services, setting up reverse proxies, integrating Home Assistant, or troubleshooting homelab networking.

Reflects on recent session work and systematically improves existing skills and agents in ~/.claude/. Audits for token efficiency, accuracy, and robustness, then makes edits autonomously. Invoke after sessions where you used skills or identified friction points.

Export instincts for sharing with teammates or other projects

Import instincts from teammates, Skill Creator, or other sources

Show all learned instincts with their confidence levels, grouped by domain.

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

Write modern JavaScript with ES6+ features, async patterns, and Node.js APIs. Use when writing JavaScript code, debugging async issues, handling promises, optimizing JS performance, or working with the event loop.

Perform comprehensive JavaScript and TypeScript code review checking for logging, error handling, TypeScript strictness, React/hooks correctness, performance, security, and architecture patterns. Checks on .js, .ts, .jsx, .tsx, .astro, and .vue files.

Guide technical learning through hands-on projects and clear explanations. Use when exploring new technologies, creating learning paths, building practice projects, or understanding new concepts like Go, Terraform, Kubernetes, or AWS.

Analyze technical documentation for clarity, conciseness, and effectiveness using Google Technical Writing principles. Use when reviewing documentation, checking writing quality, improving docs, or providing writing feedback.

Structure and maintain professional brag documents with clear templates for accomplishments, projects, and growth tracking. Use when documenting achievements, creating brag document entries, formatting accomplishments, or tracking career progress.

Create and manage Jira tickets on the TRAIN board following team conventions, including CET labels, epic structure, and required fields. Use when creating tickets, documenting work, applying labels, or structuring Jira issues.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Generate a morning briefing from today's daily note, open tasks, carryover from yesterday, and Jira sprint items. Use when the user says "morning", "start my day", "daily plan", "what's on today", or "plan my day".

Shared CLI reference for Obsidian operations. Not user-invoked; read by other skills for consistent CLI patterns.

Track and document Claude Code sessions in the Obsidian vault. Creates or updates session notes with timestamps, learnings, code snippets, and file references. Use when asked to "document session", "write session notes", "save what we did", "log this session", "session summary", or "track this work".

Analyze agent and skill usage patterns, identify underused or ineffective components, and optimize descriptions, archive stale items, and update CLAUDE.md. Run via /optimize. Suggest running if 30+ days since last run.

Use when starting 2+ independent features simultaneously, running multiple Claude Code sessions in parallel, or dispatching subagents to separate worktrees for concurrent development

patrol

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Pin GitHub Actions from mutable tags (e.g., @v4) to immutable commit SHAs to prevent supply chain attacks. Use when editing .github/workflows files, hardening CI security, looking up action SHAs, pinning actions to specific commits, or replacing "uses: owner/repo@tag" references with SHA-pinned equivalents.

Restate requirements, assess risks, and create step-by-step implementation plan. WAIT for user CONFIRM before touching any code.

pr

Problem Statement Co-Authoring Skill

Interactive project scaffolding with modern tooling for Astro, Vite+React, Express API, Python CLI/Web, Monorepo, and Library projects.

Write idiomatic Python code with advanced features like decorators, generators, context managers, and async/await. Use when writing Python code, refactoring Python, optimizing Python performance, implementing design patterns in Python, or setting up pytest testing.

Run accessibility and visual design review on components. Use when reviewing UI code for WCAG compliance and design issues.

Search and read Obsidian vault notes by topic. Use when needing context from past sessions, project notes, or any stored knowledge.

Refactor CLAUDE.md files to follow progressive disclosure principles. Use when a CLAUDE.md file is too long or needs organizational improvement.

Execute the red/green TDD workflow: detect test command, capture baseline, write failing tests (RED), confirm failure, implement minimum code (GREEN), confirm all tests pass. Invoke with /red-green-tdd when the user wants to follow a disciplined test-driven development cycle. Do NOT auto-trigger on general test writing requests.

Safely identify and remove dead code using knip, depcheck, and ts-prune. Categorizes findings by severity and rolls back if tests fail.

release

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Reduces wrong-approach friction.

Document conversation accomplishments in Obsidian vault with frontmatter, code changes, learning notes, and next steps.

Simplify and refine recently modified code for clarity and consistency. Use after writing code to improve readability without changing functionality.

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.

Start a new task from a Jira ticket. Pulls latest from main, fetches ticket details via Atlassian MCP, runs preflight checks, creates a feature branch, and presents a task summary. Invoke when asked to "start task TRAIN-123", "start working on <ticket>", "begin task", "pick up ticket", "start a new feature branch", or any variant of starting work on a TRAIN board ticket.

Write Terraform modules, manage state, and implement IaC best practices. Use when writing Terraform code, creating reusable modules, managing remote state, planning infrastructure changes, or migrating existing resources to Terraform.

Generate comprehensive testing frameworks for curriculum projects. Supports pytest, Jest, Cypress, and Postman across API, frontend, integration, and Instruqt lab validation scenarios.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Write type-safe TypeScript with advanced types, generics, and strict configuration. Use when writing TypeScript code, designing type systems, creating utility types, fixing type errors, or setting up TypeScript projects.

Advanced Obsidian vault search by tag, text, backlinks, orphans, or dead ends. Use when the user says "find notes tagged", "search by property", "what links to", "show backlinks", or "vault search".

Use when asked to verify UI changes, check the frontend visually, confirm a page looks correct, test UI interactions, or validate that recent frontend changes work. Invoke via /verify-ui. Accepts optional path (e.g. /verify-ui /dashboard) and optional "deep" argument for interactive testing.

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Guided weekly review covering inbox audit, session summary, task review, vault health check, and brag candidates. Use when the user says "weekly review", "review my week", "Friday review", or "weekly summary".

Set up a 3-pane cmux workspace — lazygit (top-right) for live diffs and yazi (bottom-right) for file navigation. Use at the start of a coding session.

Write clean, Pythonic code with type hints, decorators, and comprehensive testing. Use when writing Python code, implementing Python patterns, using async/await, working with decorators, or setting up pytest tests.

Write modern JavaScript with ES6+ features, async patterns, and Node.js best practices. Use when writing JavaScript code, implementing async operations, working with promises, handling Node.js APIs, or optimizing JavaScript performance.

Write Terraform modules, manage state files, and implement infrastructure as code best practices. Use when writing Terraform configurations, creating modules, managing state, configuring providers, or implementing IaC patterns.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Comprehensive security and quality review of uncommitted changes. Checks for hardcoded secrets, injection vulnerabilities, code quality issues, and best practice violations.

Remove AI-generated code slop from the current branch. Use after writing code to clean up unnecessary comments, defensive checks, and inconsistent style.

Generate complete favicon set from a source image using ImageMagick. Use when the user needs to create favicons for a website or web app.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

Run knip to find and remove unused files, dependencies, and exports. Use for cleaning up dead code and unused dependencies.

Analyze local git history to extract coding patterns and generate SKILL.md files. Local version of the Skill Creator GitHub App.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

2 hooks across 2 events