john-skills

Use this agent when the user returns to a coding session and needs to catch up on what was previously done, when the user asks 'where were we?', 'what were we working on?', 'recap the session', or similar questions about resuming work. Also use when starting a new conversation that appears to be a continuation of previous work.

Proactively catch common AWS infrastructure mistakes before they happen. Use when creating or modifying AWS components — CloudFormation, CDK, Lambda, API Gateway, IAM, S3, CloudFront, EC2, Secrets Manager, or SSM — to apply hard-won deployment lessons and avoid known pitfalls.

Create a token-secured REST API endpoint backed by AWS Lambda and DynamoDB with full CRUD and paginated list support. Deploys via CloudFormation. Use when user wants to quickly spin up an API endpoint, create a simple REST API on AWS, build a quick data store with an API, set up a Lambda+DynamoDB endpoint, or needs a fast way to log and retrieve structured data. Triggers on "create an endpoint", "quick API", "Lambda endpoint", "DynamoDB API", "CRUD endpoint", "log data to AWS".

Track API token costs for specific operations in Claude Code. Use when the user invokes /cost-tracking to start measuring costs, or says "stop tracking", "stop cost tracking", or "how much did that cost" to stop and calculate. Tracks input, output, and cache tokens per API call and calculates USD cost using current Anthropic pricing.

Create and maintain a DEVLOG.md file capturing the development story of a project. Use this periodically over the course of a project to capture important information about the development story. Invoke when the user asks to update the devlog, create a devlog, document project progress, or capture development history. Also appropriate after completing significant milestones or before context switches.

Create an Ubuntu 24.04 LTS EC2 instance with Claude Code, Playwright (headless browser testing), tmux, git, beads (bd) task tracking, and agent-deck session manager pre-installed. Use when user wants to spin up a cloud development environment, create an EC2 for Claude Code, launch a remote Claude Code instance, or set up a dev box on AWS. Supports multiple instances per account with unique naming.

description: Reviews a webpage URL and provides actionable suggestions to improve GEO (Generative Engine Optimization) — how well the page will be cited and recommended by AI search engines like ChatGPT, Perplexity, Gemini, and Copilot.

Convert any Git repository into a text file optimized for LLM consumption using GitIngest. Use when the user wants to ingest a repo, create a text digest of a codebase, prepare a repository for LLM analysis, or needs to convert a GitHub URL to a readable text file.

Help users evaluate whether an MCP (Model Context Protocol) tool is safe and right for them before installing it. Use when a user wants to check, scan, review, or assess a third-party MCP server from GitHub, npm, or any repository URL. Provides plain-language assessments that anyone can understand, with technical details available on request.

Save and restore session state for continuity across context compressions. Invoke with "/memory-checkpoint" to save current session state, or "/memory-checkpoint your search query" to search past checkpoints by semantic similarity.

Create and configure Claude Code plugin marketplaces hosted on GitHub. Use this skill when users want to set up a new plugin marketplace repository, add plugins to an existing marketplace, configure team distribution settings, or troubleshoot marketplace issues. Triggers include "create a plugin marketplace", "set up a marketplace on GitHub", "add plugins to my marketplace", "configure marketplace for my team", or "distribute Claude Code plugins".

Security audit for GitHub repositories before installation. Use when user wants to check if a repo/app is safe to install, review install scripts for malicious code, verify an open source project isn't collecting data, or audit dependencies for suspicious packages. Triggers on phrases like "is this safe to install", "check this repo", "review this script", "audit this code", "is this sketchy".

Manage Python virtual environments in a consistent, organized way. Use when a skill needs Python packages installed, or when the user wants to create a venv following standard conventions. Provides the authoritative convention for venv location and naming that other skills should follow.