Latest Agent Skills

Configure and run CodeQL code scanning through GitHub Actions workflows or the standalone CLI for security analysis.

Orchestrates polyglot distributed applications using Aspire's AppHost, CLI, and MCP server for local development, testing, and deployment.

Generate comprehensive Product Requirements Documents (PRDs) for software systems and AI-powered features, including executive summaries, user stories, technical specifications, and risk analysis.

Remove assigned mypy exclusion modules in small batches, fix typing issues, run validation, and produce a structured completion summary.

Archive non-actionable noise from the Sentry javascript project issue queue, using untilEscalating mode with documented categories.

Organize a list of projects and their documentation into the SRED format for submission, creating Notion documents with project summaries, uncertainties, and supporting evidence.

Add or fix OpenAPI documentation for Sentry API endpoints using drf-spectacular, including type drift correction, legacy migration, and endpoint promotion.

Analyze a repository to generate recommended Claude Code settings.json permissions for read-only commands, detecting tech stack, build tools, and monorepo structure.

Create interactive, data-driven presentation slides using React, Vite, and Recharts with Sentry branding, built as a single distributable HTML file.

Reviews Django codebases for access control vulnerabilities and IDOR by tracing authorization flows, mapping attack surfaces, and reporting confirmed gaps with enforceable fixes.

Audits GitHub Actions workflows for exploitable vulnerabilities with concrete attack scenarios.

Analyze Sentry session replays to surface UX patterns, pain points, and user journeys for a given product area.

Fetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member.

Audit Django code for validated performance issues including N+1 queries, unbounded querysets, missing indexes, and write loops.

Write, review, and improve blog posts for the Sentry engineering blog following Sentry's specific writing standards, voice, and quality bar.

Collects GitHub PRs, Notion docs, and Linear tickets from the past year, groups them into projects, and creates a private Notion document summarizing the work.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

Write user-facing copy following Sentry's brand guidelines, covering Plain Speech and Sentry Voice tones for UI text, documentation, and marketing content.

Conducts systematic security code reviews to identify exploitable vulnerabilities, reporting only high-confidence findings after researching the codebase.

Guides users through a structured workflow for co-authoring documentation, proposals, technical specs, and decision docs across three stages: context gathering, iterative refinement, and reader testing.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.

Scans agent skills for security issues including prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.

Appends a GitHub issue link and its associated Linear ticket to the current PR's description.

Create a git branch following Sentry naming conventions, automatically deriving the branch type and description from current work context.

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Handles source capture, precision passes, authoring, registration, and validation.

Review pull requests following Sentry engineering practices, covering security, performance, testing, and design.

Iterate on a pull request until actionable CI checks pass and high/medium review feedback is addressed, stopping at human approval, draft, or merge gates.

Create, refresh, and rewrite PR titles and descriptions following Sentry conventions, focusing on reviewer-facing content that describes the full branch diff.

Reviews local branch changes for bugs, security vulnerabilities, and code quality issues using a structured checklist and attack surface mapping.

Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files for AI coding agents, keeping them under 60 lines and referencing existing documentation.

Create commits following Sentry conventions with proper format, issue references, and AI attribution.

Generates Angular code and provides architectural guidance for projects, components, services, reactivity, forms, dependency injection, routing, SSR, accessibility, animations, styling, testing, and CLI tooling.

Creates a new Angular application using the Angular CLI, following modern best practices and generating components, services, and other artifacts.

Update ElevenLabs agent skills from a merged weekly changelog, then open a pull request.

Remove background noise and isolate vocals or speech from audio files using the ElevenLabs Voice Isolator API.

Generate natural speech from text using ElevenLabs voice AI, supporting 70+ languages, multiple models, and various output formats.

Transcribe audio to text using ElevenLabs Scribe v2, supporting 90+ languages, speaker diarization, and word-level timestamps.

Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer API.

Add real-time voice conversations to a custom agent runtime using ElevenLabs Speech Engine, handling WebSocket servers, browser clients, and interruption-aware streaming.

Generate sound effects from text descriptions using ElevenLabs, with support for looping, duration control, and prompt influence tuning.

Guides through obtaining and configuring an ElevenLabs API key, checking for existing keys and validating them before running the full setup.

Build voice AI agents with natural conversations, multiple LLM providers, custom tools, and easy web embedding.

Generate music from text prompts using ElevenLabs Music API, supporting instrumental tracks, songs with lyrics, composition plans, video-to-music, and inpainting.

Resize photos and videos to exact pixel dimensions, aspect ratios, or named sizes using Adobe tools.

Resize, crop, or export any image or video into platform-ready social media assets using Adobe Creative Cloud tools.

Merges CSV/TSV data with an InDesign template to generate personalized PDFs like certificates, badges, and catalogs.

Create visual designs like flyers, posters, social media posts, and business cards by searching Adobe Express templates and customizing text, colors, and animations.

Bulk-retouch a folder of portrait photos using Adobe tools — designed for wedding photographers and event photographers who need fast, walk-away batch processing.

Apply consistent photo adjustments across a set of images so they look like they were edited together, using Adobe tools for color, tone, cropping, and optional selective enhancements.

Migrate AEM Cloud Service resource listeners to the lightweight ResourceChangeListener + JobConsumer pattern, covering migration from legacy APIs, OSGi configuration, troubleshooting, and review checklists.

Monitor and react to content distribution lifecycle events using the Sling Distribution API, covering event handling, queue monitoring, and distribution tracking.

Creates three AI-edited sizzle reel variations from a user-uploaded video, letting the user choose their preferred cut.

Audit and optimize headings across AEM Edge Delivery Services pages for search intent, hierarchy, and consistency.

Scan AEM Edge Delivery Services pages for WCAG 2.1 AA violations and generate specific fixes for content authors and developers.

Detects outbound HTTP clients constructed without explicit timeouts in AEM Cloud Service code and applies mechanical fixes with CSO-aligned defaults to prevent request-thread pool saturation.

Audit AEM Edge Delivery Services commerce product pages for search engine crawlability and indexing, then remediate issues with meta tags, structured data, canonical URLs, and image optimization.

Crawl and validate all internal and external links across an AEM Edge Delivery Services site, producing a prioritized report of broken, redirecting, and insecure links.

Analyze and improve the internal link structure of an AEM Edge Delivery Services site by building a link graph from the query index and page content, identifying orphan pages, hub pages, and content silos, and generating specific linking recommendations with suggested anchor text and placement.

Migrate deprecated and removed Java imports, Maven dependencies, and unmodifiable OSGi configs to comply with AEM as a Cloud Service enforcement policies.

Upgrades outdated Maven dependency versions in AEM Cloud Service pom.xml files, handling both literal <version> and same-pom ${property} shapes.