agents-skills

PR-focused code review with structured checklist, severity ratings, and actionable feedback

Use when a code review finding needs proof — write a focused test in JavaScript or Go that either confirms the issue is real or exposes it as over-engineering hyperbole. Trigger after code-review or code-review-skill findings are presented and evidence is requested.

Use when reviewing Dependabot alerts, npm audit findings, govulncheck output, or CVE reports on a JavaScript/Node.js or Go project — especially when triaging multiple alerts across direct and transitive dependencies to assess real-world risk and produce a remediation plan.

Produce data-driven software delivery estimates by analyzing historical JIRA tickets, git activity, and engineer track records, then matching the new work against the most similar past tickets. Use this skill whenever the user asks "how long will this take", wants to estimate a piece of work, scope an epic, plan a sprint, or estimate delivery for JIRA stories or a Figma design. Also use whenever the user wants developer-to-work assignment recommendations based on history, wants to optimize an estimate by adding or reallocating engineers, or asks "what's the fastest way to ship this" or "who should work on this". Especially trigger when the user provides JIRA ticket IDs, JIRA story links, or Figma designs together with any indication of a team that will execute the work.

Use when auditing an existing test suite for quality and coverage gaps, evaluating Playwright migration readiness, scoring automation against a world-class e-commerce standard, or guiding the creation of new tests. Applicable to Selenium, WebdriverIO, and Playwright suites.

AI-powered observability with Grafana MCP — translates natural language to metrics, logs, and trace queries to diagnose issues like a senior SRE

Audit and optimize Hystrix circuit breaker implementations in Go services for scaling, performance, and availability

Audit and improve Go service logging to ensure Splunk logs capture method, request details, TraceID, SpanID, and timing using the go-common logging library

Measure and assert Core Web Vitals (LCP, INP, CLS) in Playwright scripts. Use when the user wants to capture performance metrics, validate CWV thresholds, audit pages for Google ranking signals, or add CWV measurement to existing Playwright checks. Pairs with the playwright-dev skill.

Analyze codebase architecture and design patterns to assess maintainability, scalability, and adherence to best practices

Use when creating or updating catalog-info.yaml files for Backstage, onboarding repositories to the software catalog, or configuring service metadata for developer portal visibility

Safely clean up merged, stale, and unnecessary git branches with dry-run preview

Whole-repository code quality review covering architecture, security, performance, and testing

Generate architecture documentation with C4 diagrams, ADRs, and system context maps from codebase analysis

Plan and implement new features with structured workflow from requirements through testing and PR creation

Generate codebase-aware onboarding documentation by analyzing the project's tech stack, structure, and workflows

Systematically debug and resolve errors using structured hypothesis-driven investigation

Audit all project dependencies for security vulnerabilities, outdated packages, license compliance, and health

Investigate a directory's architecture and create/update a CLAUDE.md file capturing implementation knowledge

Set up end-to-end testing infrastructure with Playwright, including page objects, CI integration, and test data management

Provide data-driven task estimates using git history, code complexity analysis, and similar past work

Use when adding accessibility scanning to existing Playwright checks via --evinced flag, when instrumenting browser tests for WCAG compliance, or when integrating Evinced SDK with Playwright scripts.

Analyze and explain code sections with multi-level explanations tailored to audience experience level

Scan and explain an entire codebase — structure, entry points, integrations, patterns, and data flow

Review code and produce a prioritized list of missing test cases formatted as GitHub issues

Write and execute k6 load tests, performance checks, and validation scripts. Generates scripts with proper scenarios, checks, thresholds, custom metrics, and structured output. Use when the user wants to create k6 tests, performance benchmarks, or site validation scripts.

Create Mermaid diagrams (activity, deployment, sequence, architecture) from text descriptions or source code. Use when asked to "create a diagram", "generate mermaid", "document architecture", "code to diagram", "create design doc", or "convert code to diagram". Supports hierarchical on-demand guide loading, Unicode semantic symbols, and Python utilities for diagram extraction and image conversion.

Create step-by-step migration guides for upgrading dependencies, frameworks, or architectural changes

Analyze OpenTelemetry traces for latency issues, error diagnosis, retry patterns, dependency bottlenecks, and trace integrity problems. Use when the user provides OTEL trace JSON files or asks about distributed system performance issues.

Analyze codebase for performance bottlenecks across code, database, frontend, network, and async operations

Write and execute Playwright browser checks and API checks. Auto-detects dev servers, writes scripts to /tmp, runs them via the universal executor. Use when the user wants to test websites, validate pages, check APIs, or automate any browser task.

Multi-dimensional project health dashboard with scoring across delivery, quality, debt, team, and dependency metrics

Search the web, evaluate sources, and synthesize findings with citations

Identify security vulnerabilities across dependencies, auth, input validation, data protection, secrets, and infrastructure

Apply security best practices to reduce attack surface — authentication, input validation, headers, encryption, and dependency updates

Create a detailed session summary capturing actions, decisions, costs, efficiency insights, and next steps

Analyze test coverage, identify gaps in critical code paths, and produce a prioritized coverage improvement plan

Generate codebase-aware troubleshooting documentation with diagnostic procedures, error references, and recovery steps

Engage deep multi-perspective analysis for complex architectural decisions, trade-offs, and strategic problem-solving

Generate comprehensive tests including unit, integration, and edge case coverage with framework-aware conventions