Claude Code skills, ranked and checked

Covers writing LangGraph code: StateGraph, state schemas, nodes, edges, streaming and error handling.

Covers human-in-the-loop patterns in LangGraph: interrupts, approval workflows and error handling.

Covers persistence in LangGraph: checkpointers, thread ids, time travel and the Store.

Reads meeting notes, finds the action items and creates Jira tasks for the assigned work.

Generates a project status report from Jira issues and publishes it to Confluence.

Builds a visual sprint dashboard from a Jira project, board, filter or JQL query, for standups and sprint reviews.

Searches Confluence, Jira and internal docs to find and explain internal systems, processes and terminology.

Converts a Confluence specification into a structured Jira backlog of epics and implementation tickets.

Triages a bug report by searching Jira for duplicates, then creates a new issue or comments on an existing one.

Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files.

Writes and reviews technical blog posts to the standards and voice of the Sentry engineering blog.

Analyses a repository and recommends Claude Code settings.json permissions for its tech stack and tools.

Reviews pull requests the way Sentry engineers do, covering security, performance, testing and design.

Simplifies and refines code for clarity, consistency and maintainability while keeping its behaviour.

Creates Sentry-style conventional commits with issue references.

Reviews Django code for performance problems such as N+1 queries and slow querysets.

Finds bugs, security vulnerabilities and code quality issues in the changes on the current branch.

Reviews GitHub Actions workflows for vulnerabilities that could be exploited.

Iterates on a pull request until CI passes and high and medium review feedback has been addressed.

Writes or refreshes pull request titles and descriptions for reviewers.

Creates data-driven presentation slides with React, Vite and Recharts in Sentry branding.

Creates, optimises and refines agent prompts, system prompts and reusable prompt templates.

Reviews code for security vulnerabilities such as injection, XSS and authentication or authorisation flaws.

Scans agent skills for security problems such as prompt injection before you install them.