Code Review

server-management

by vudovn

Server management principles and decision-making. Process management, monitoring strategy, and scaling decisions. Teaches thinking, not commands.

frontend-design

by vudovn

Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

behavioral-modes

by vudovn

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

clean-code

by vudovn

Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments

systematic-debugging

by vudovn

4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.

code-review-checklist

by vudovn

Code review guidelines covering code quality, security, and best practices.

pr-demo

by mikeyobrien

Use when creating animated demos (GIFs) for pull requests or documentation. Covers terminal recording with asciinema and conversion to GIF/SVG for GitHub embedding.

react-native-best-practices

by storybookjs

Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead, FlashList, native modules, or debugging jank and frame drops.

ontoindex-debugging

by ontograph

'Diagnose failing behavior, trace errors, and locate the source of a reproducible bug.'

ontoindex-impact-analysis

by ontograph

'Assess blast radius before editing a symbol and identify dependencies that need review or validation.'

ontoindex-pr-review

by ontograph

'Review a pull request or diff for correctness, merge risk, and missing test coverage.'

ontoindex-cli

by ontograph

'Use when the user needs to operate the OntoIndex CLI to index, inspect, clean, or document a repository.'

ontoindex-guide

by ontograph

'Consult for OntoIndex tool families, resource URIs, graph schema, and bounded Cypher reference.'

lint-rule-development

by biomejs

Step-by-step guide for creating and implementing lint rules in Biome's analyzer. Use when implementing rules like noVar, useConst, or any custom lint/assist rule. Examples:<example>User wants to create a rule that detects unused variables</example><example>User needs to add code actions to fix diagnostic issues</example><example>User is implementing semantic analysis for binding references</example>

slack-gif-creator

by Prat011

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

ai-assisted-development

by peterbamuhigire

Orchestrate AI agents (Claude Code, sub-agents, etc.) for software development workflows. Use when coordinating multiple AI assistants or planning AI-driven development processes.

Ai Code Security

by omer-metin

code-review

by staruhub

专业的代码审查助手，提供结构化的审查流程、详细的检查清单和建设性的反馈指南。适用于审查Pull Request、代码提交或任何需要代码质量评估的场景，涵盖功能性、安全性、性能、测试、文档、架构设计等多个维度。

Windscribe Android App — AI Agent Skill

by Windscribe

Maintained By: Engineering Team

domain-discovery

by TanStack

Use when the maintainer explicitly requests full-library discovery or a skill taxonomy review. For an agreed skill batch or a concrete code/docs update, use generate-skill instead.

data-engineering

by rohitg00

Data engineering patterns for ETL pipelines, data warehousing, Apache Spark, and data quality validation

generate-skill

by TanStack

Use when creating or extending library skill batches, updating guidance after library source or docs change, configuring repository skill distribution, or acting on an Intent review report, including when the maintainer asks only for the library change. For full-library discovery or taxonomy design, use domain-discovery; for generating an approved full-library tree, use tree-generator.

fable-mode

by mrtooher

Enforces staged execution discipline on large tasks: a written stage plan, delegation to named fable agents where the runtime supports it, a failable verification check at each stage, and a skeptical self-review before delivery. Trigger when the user explicitly asks ("do this thoroughly", "be systematic", "deep work mode") OR when the task objectively spans multiple files, multiple sources, or multiple sessions. Do NOT trigger on ordinary multi-step requests that a direct attempt handles fine. For a run pinned to a specific model, use fable-opus, fable-sonnet, or fable-haiku instead. Always-on guardrails (verify-before-flag, warning batching, sed safety) live in the companion execution-guardrails skill.

Art Consistency

by omer-metin