Profile the Python engine to identify performance bottlenecks in NumPy/Numba code

Create a changeset for package releases. Analyzes commits since the last release, determines affected packages and bump type, and generates a changeset file.

Code review specialist for quality, security, and best practices

Bug Investigation

Analyze and interpret experiment results for the UWB RTI project.

Git workflow guidance for commits, branches, and pull requests

freeze

Expert in web accessibility, WCAG compliance, screen reader optimization, keyboard navigation, ARIA attributes, and inclusive design. Activates for accessibility improvements, WCAG compliance, a11y audits, and inclusive design tasks.

cuda-guide

Migrate an apollo-react canvas component from Emotion styled-components to apollo-wind Tailwind classes following the BaseNode reference migration patterns

Read a past session and produce a structured summary (messages, tool calls, files, decisions)

Acting as template repo maintainer: review proposals in `localdocs/proposals/` and optionally apply accepted ones to the upstream template.

Guide for defining and using Claude subagents effectively. Use when (1) creating new subagent types, (2) learning how to delegate work to specialized subagents, (3) improving subagent delegation prompts, (4) understanding subagent orchestration patterns, or (5) debugging ineffective subagent usage.

This skill helps you add new rules to the attgo-linter project.

Synchronize shared rules into agent context files and headers.

Guides how to integrate the NNews NuGet package for consuming the NNews CMS API in a .NET 8 project. Use when the user wants to consume articles, categories, tags, images, or AI-powered content generation from the NNews API.

Transform Claude into an expert code reviewer following industry best practices.

Trigger a xylem drain cycle and report what moved through the queue. Use when the user asks to run pending work, kick the daemon manually, process queued vessels, or monitor a fresh drain.

Execution-oriented workflow for HyperParallel distributed operator development. Analyzes the operator, implements or updates code and tests.

TypeScript-first schema validation library with static type inference and runtime validation

Orchestrate Agent Teams for parallel multi-session collaboration. Use for research, implementation, review, and debug workflows requiring independent teammates.

Plans the next sprint with PM analysis, multi-agent technical table, and roadmap generation. Use to plan sprints, prioritize features, convene technical tables.

Write idiomatic Kotlin code that fits this repository's stack (Kotlin on JVM 21, IntelliJ Platform). Use this skill whenever you add or modify `.kt` files in this repo - it enforces Kotlin coding conventions, nullability rules, scope function choices, and the project's specific idioms (PSI helpers, extension fn patterns, bundle/icon singletons).

Expert knowledge for defining REST and WebSocket APIs with `schematic-define`. Use when creating or editing `RestApi`/`Endpoint` models, auth and env mappings, request or response shapes, and OpenAPI extension behavior that drives generated clients.

Implementa feature nel sistema di fatturazione italiana validando contro normativa fiscale. Usa per aggiungere calcoli IVA, ritenuta d'acconto, split payment, imposta di bollo, gestione fatture PA, regime forfettario, numerazione progressiva, note di credito, o qualsiasi logica che deve rispettare DPR 633/72, DPR 600/73, DPR 642/72. NON usare per bug fix tecnici, refactoring, o modifiche UI senza impatto fiscale.

This is an AI-first project: any contributor — human or model — should be able to land a change that respects the architecture without needing to read the whole codebase first. The rules below are che

Review authentication and authorization design including OAuth, JWT, token expiration, RBAC/ABAC, and privilege escalation risks.

Confidence-based model tier escalation for agent tasks. Defines when to escalate from Haiku to Sonnet to Opus, escalation signals, and the never-skip-tiers rule. Use when an agent fails or underperforms.

Writes React components without unnecessary useEffect. Use when creating/reviewing React components, refactoring effects, or when code uses useEffect to transform data or handle events.

Triage and review Linear issues - list, filter, prioritize, and update issue status. Use when asked to check tickets, review backlog, or see what needs doing.

Improve the eval system quality -- add better cases, fix broken cases, improve the LLM judge, add new metrics, or refine pass/fail criteria based on eval run data. Use when the user wants to make the eval system itself better.

>

Meta-level analysis of plan vs execution to identify process improvements. Analyzes divergence patterns and suggests updates to CLAUDE.md, agents, and skills.

Use when testing API integration, state transitions, error recovery, or full user journeys with browser. For isolated component logic, use vitest-testing.

nextjs-performance

> Extends the official PPTX skill with GoTravel Adventures brand standards. Use this skill to create strategy decks, campaign presentations, trip launch decks, and marketing reports — all matching the

Databricks SA coding interview playbook — vertical-agnostic (retail/media/generic), PySpark data gen + SQL transforms. Use when generating interview code, building Bronze/Silver/Gold pipelines, or preparing for Databricks SA coding interviews. Covers: PySpark spark.range() data gen, deterministic MERGE, CHECK constraints, Liquid Clustering, idempotent Gold rebuilds, validation harness, quarantine patterns, SCD2, CDC, scaling discussion, and narration comments.

Select font combinations optimized for Hebrew readability and Latin compatibility:

Produces a categorised branch status table, then stops. Does not delete or modify anything unless the user explicitly asks.

SoNash project context injected into agent definitions via skills: field

Implement React Native mobile apps with TypeScript, Redux Toolkit, Apollo Client, and React Navigation. Use when building cross-platform mobile apps, implementing navigation, or mobile state management. Triggers on requests for React Native, mobile app development, cross-platform apps, or mobile navigation.

Fix a GitHub issue by number. Enforces RED→GREEN→CLEANUP TDD discipline and requires every reproduction case from the issue to have a passing test before any code ships.

This skill identifies and prevents common testing anti-patterns that make test suites unreliable, slow, and difficult to maintain. It provides detection strategies and refactoring solutions for health

Run UnrealCV closed-loop test workflow (build + launch + test)

>

Run unit and integration tests

Remove AI-generated code slop and clean up code style. Use when the user asks to deslop, clean up AI-generated code, remove unnecessary comments, simplify defensive patterns, or fix style inconsistencies introduced by AI.

zero-skills

Review code for design token violations, SCSS convention drift, and theme wrapper compliance. Compares source files against pf-tokens-SSOT.json, MUI-default-theme-object.json, and the project's styling rules. Use when the user asks to review code, audit styling, check token usage, or review a PR for convention compliance.