getsentry/skills▌

Code simplification and refactoring focused on clarity, consistency, and maintainability. \n \n Applies project-specific best practices from CLAUDE.md, including ES modules, explicit type annotations, and proper React patterns \n Eliminates unnecessary complexity through reduced nesting, clearer naming, and removal of redundant abstractions \n Avoids nested ternaries and overly compact solutions in favor of explicit, readable code structures \n Preserves all original functionality and behavior w

Comprehensive code review identifying bugs, security vulnerabilities, and quality issues in branch changes. \n \n Executes a structured five-phase review process: gathering the complete diff, mapping attack surfaces, running a detailed security checklist, verifying findings, and auditing coverage before conclusions \n Security checklist covers 11 critical areas including injection, XSS, authentication, authorization, CSRF, race conditions, session management, cryptography, information disclosure

Use this as the single canonical workflow for skill creation and improvement. Primary success condition: maximize high-value input coverage before authoring so the resulting skill has minimal blind spots.

Alias: skill-creator \n This skill name is kept for compatibility. \n Use sentry-skills:skill-writer as the canonical skill for creating and updating skills. \n If invoked via skill-creator , run the same workflow and conventions documented in sentry-skills:skill-writer .

Find exploitable vulnerabilities in GitHub Actions workflows. Every finding MUST include a concrete exploitation scenario — if you can't build the attack, don't report it.

This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.

Code review framework following Sentry engineering practices for pull requests and code quality assessment. \n \n Covers six key problem areas: runtime errors, performance bottlenecks, side effects, backwards compatibility, ORM query issues, and security vulnerabilities \n Includes design assessment guidance for component interactions, architectural alignment, and requirement conflicts \n Requires appropriate test coverage across functional, integration, and end-to-end tests with verification of

Review Django code for validated performance issues. Research the codebase to confirm issues before reporting. Report only what you can prove.

Systematic security code review identifying high-confidence vulnerabilities with data-flow verification. \n \n Focuses exclusively on HIGH CONFIDENCE findings: vulnerable patterns with confirmed attacker-controlled input, skipping theoretical issues and framework-mitigated code \n Requires codebase research before reporting: traces data flow, checks for validation/sanitization, and verifies exploitability rather than pattern-matching alone \n Covers 14 vulnerability categories (injection, XSS, a

Enforces Sentry conventional commit format with proper types, scopes, and issue references. \n \n Requires feature branch creation before committing to main or master; uses the create-branch skill to manage branch workflow \n Supports 12 commit types (feat, fix, ref, perf, docs, test, build, ci, chore, style, meta, license) with clear subject line rules and footer patterns for issue references \n Includes Co-Authored-By attribution for AI-generated changes and handles breaking changes with expli

Create and maintain minimal, high-signal agent documentation under 60 lines. \n \n Enforces research-backed best practices for agent-facing docs; instruction quality degrades with length \n Requires three core sections: Package Manager, File-Scoped Commands (per-file test/lint/typecheck), and Commit Attribution with agent identity \n Analyzes project structure (lock files, linter configs, CI commands, monorepo indicators) to determine what belongs in the file \n Uses headers and bullets only; re

Create interactive, data-driven presentation slides using React + Vite + Recharts, styled with the Sentry design system and built as a single distributable HTML file.

Create pull requests following Sentry's engineering practices.

SRED expects projects to be presented in a particular format. Take the list of projects that have been worked on in the past year, and summarize them into the format expected by SRED, with the supporting evidence. Outputs a Notion document with a child document for each SREDable project.

Collect all the Github PRs, Notion docs and Linear tickets a person completed in a given year. Group the links from all of those into projects. Put everything into a private Notion document and return a link to that document.

Find access control vulnerabilities by investigating how the codebase answers one question:

This skill enforces Sentry's blog writing standards across every post — whether you're helping an engineer write their first blog post or a marketer draft a product announcement.

Analyze this repository and generate recommended Claude Code settings.json permissions for read-only commands.

Continuously iterate on the current branch until all CI checks pass and review feedback is addressed.

Alias: create-pr \n This skill name is kept for compatibility. \n Use sentry-skills:pr-writer as the canonical skill for creating and editing pull requests. \n If invoked via create-pr , run the same workflow and conventions documented in sentry-skills:pr-writer .

Automated security scanning for agent skills before installation, detecting prompt injection, malicious code, excessive permissions, and supply chain risks. \n \n Runs static analysis via bundled Python scanner that outputs structured JSON findings with severity levels and URLs \n Validates SKILL.md frontmatter (required fields, tool justification, model overrides) and checks for config poisoning or scope creep in instructions \n Analyzes scripts for data exfiltration, reverse shells, credential

Write user-facing copy following Sentry's brand guidelines.

Fetch unread review_requested notifications for open (unmerged) PRs, filtered by a GitHub team.

Create a git branch following Sentry naming conventions. Keep this workflow non-interactive unless the user explicitly asks to choose the name manually.