Explore skills

Secure-by-default builder for Claude Code, used when scaffolding new projects or repos, writing or modifying authentication/authorization/session/password code, file uploads, SSRF-prone server-side fetches, secrets/env handling, deployment configs, Dockerfiles or docker-compose, GitHub Actions/CI workflows, or dependency installs (e.g., package.json, requirements.txt, Cargo.toml).

Provides AI governance learning, news, and quizzing, covering regulation, policy, law, and compliance, such as the EU AI Act and state-level laws.

This diagnostic playbook addresses Midnight Network backend operational issues, including wallet sync stalls, deployment hangs, three-address confusion, DUST zero-balance, cloud-IP RPC 403 errors, and AWS WAF 8KB submitTx problems.

Generates a personalized weekly meal plan and Migros shopping list based on user preferences, utilizing the Migros MCP for promotions and nutrition verification. It can be triggered by commands such as 'meal plan' or 'grocery list for the week'.

Debug production issues and monitor AWS infrastructure using CloudWatch. This skill is used when users report errors, investigate production behavior, check logs, debug OAuth, API errors, ECS tasks, database issues, WAF blocks, or any production incident, including phrases like "check logs", "what's failing", or "system status".

Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Run a PRISM College session — multi-LLM peer review for one-way-door architecture decisions. Sub-commands prepare / refract / inspect / sync / settle / memorialize walk a state machine; use the no-arg form for state-aware status.

Claude Code token optimization advisor. Analyzes current session/project for token waste and applies proven cost-reduction strategies.

Fetches unresolved AI review comments on the current pull request, decides which issues are real and worth addressing, fixes the worthwhile ones, commits and pushes the changes, and resolves the reviewed threads. Use when the user asks to check all PR comments, refers to PR comments or issues, or wants PR review feedback handled end to end.

Downloads WeChat Official Account articles and converts them to Markdown with local images. It supports single URLs, batch files, searching by account name via Sogou, or bulk downloading via WeChat API.

Invoked helper skill for deep bug diagnosis, usually delegated from /qa when a reported issue needs root-cause analysis and a TDD fix plan before implementation. Use when the cause is unclear, the bug is a regression, or the user explicitly wants diagnosis. Not for lightweight QA intake (use /qa) or already-clear implementation tasks (use /execute).

Infrastructure skill for setting up Ralph loop scripts for Claude-driven AFK execution. Use when a repo wants a HITL-to-AFK runner around /execute with bounded iterations, GitHub-native durable state, and explicit feedback loops. Not a normal feature-delivery stage; it prepares the repo for safer autonomous execution.