Read and follow `skills/fabric/review/code/instructions.md`
Read and follow `skills/fabric/explain/docs/instructions.md`
Read and follow `skills/fabric/export/data-as-csv/instructions.md`
Read and follow `skills/fabric/clean/text/instructions.md`
Read and follow `skills/fabric/answer/interview-question/instructions.md`
Read and follow `skills/fabric/review/design/instructions.md`
Read and follow `skills/fabric/agility/story/instructions.md`
Read and follow `skills/fabric/write/essay/instructions.md`
Read and follow `skills/fabric/analyze/answers/instructions.md`
Read and follow `skills/fabric/analyze/mistakes/instructions.md`
Read and follow `skills/fabric/analyze/claims/instructions.md`
Read and follow `skills/fabric/analyze/bill-short/instructions.md`
Read and follow `skills/fabric/analyze/incident/instructions.md`
Read and follow `skills/fabric/analyze/prose-pinker/instructions.md`
Read and follow `skills/fabric/analyze/product-feedback/instructions.md`
Read and follow `skills/fabric/analyze/logs/instructions.md`
Read and follow `skills/fabric/analyze/prose/instructions.md`
OWASP Top 10 security
Generate safe SQL migrations for profiles/subscriptions with RLS, triggers and policies. Use when creating new tables, adding columns, or adjusting auth/row policies.
Scaffold Next.js pages/routes/layouts with Tailwind, wiring to Supabase auth and current tier UI states. Use when creating new pages or updating pricing/dashboard UX.
Assistant pour le développement du jeu de plateforme 2D avec Godot Engine. Aide sur l'architecture, GDScript, les animations du lézard, la physique, les ennemis et les collectibles.
| name | description | license | |------|-------------|---------| | git-operations | Expert Git operations including branching, merging, rebasing, and conflict resolution | MIT |
Automates the complete release process for npm modules - version bump, changelog, git tag, npm publish, GitHub release
Use this agent when implementing a single feature that requires the full agent chain (Backend → Frontend → UI Review → Test → QA). Spawned by the main orchestrator for multi-feature scenarios.
Notes and quick paths for ASI-synced storage on this host (OneDrive + SharePoint mounts).
Senior Python backend engineer specialized in Django and Django REST Framework (secure, maintainable, testable).
Create a summary of a document or set of documents
No description available
Implement payment processing for course enrollments using Stripe or PayPal with subscription management, invoice generation, and webhook handling.
What is shadcn/ui: shadcn/ui is a collection of re-usable components built with Radix UI and Tailwind CSS. Unlike traditional component libraries, it's not an npm package but rather a collection of components you copy into your project.
Comprehensive development workflow specialist combining TDD, debugging, performance optimization, code review, and quality assurance into unified development workflows
Design cross-client compatible HTML emails with MJML and responsive email patterns
Convert Figma designs to production-ready React/Vue components with proper styling
Build cross-platform terminal applications with Tauri and native PTY support
Build Model Context Protocol servers for AI tool integration
ba role role responsible for its domain tasks. Activate when needed.
Apply consistent naming conventions for directories, files, and identifiers - covers kebab-case rules, SSOT layout, skill naming standards, and script-generated file paths (including temporary files under .ai/.tmp/).
Organize a frontend codebase by feature/module with clear public exports, predictable naming, and minimal cross-feature coupling.
Implement or refactor backend HTTP routing and controllers using a layered pattern (routes delegate, controllers validate and call services).
Create a minimal smoke-test plan for authenticated API routes (happy path, one negative case, and persistence checks).
Canonical source: `.ai/skills/testing/test-web-playwright/`
Canonical source: `.ai/skills/testing/test-mobile-appium/`
Canonical source: `.ai/skills/testing/test-mobile-detox/`
Canonical source: `.ai/skills/testing/test-perf-k6/`
Canonical source: `.ai/skills/testing/test-api-postman-newman/`
Canonical source: `.ai/skills/testing/test-mobile-maestro/`
Canonical source: `.ai/skills/testing/test-web-cypress/`
Turn one or more knowledge documents into a provider-agnostic Agent Skills bundle (SKILL.md + examples/templates), using a plan -> apply -> lint workflow.
Canonical source: `.ai/skills/workflows/planning/review-implementation-plans/`
Project hub synchronizer and validator. Scans the repo (including multiple dev-docs roots), validates project/task metadata against the Project Contract, and can repair drift by generating missing task identity meta (.ai-task.yaml) and regenerating derived views under .ai/project/<project>/. Works in check-only mode for CI and apply mode for manual repair.
Create a goal-aligned macro-level roadmap artifact (dev-docs/active/<task>/roadmap.md) by asking clarifying questions and recording assumptions; planning only (no code changes).
Apply schema changes from repo SSOT (prisma/schema.prisma) to a target DB via Prisma migrations, with diff preview + approval gate; then refresh LLM context (docs/context/db/schema.json).
Execute dependency-aware code refactors (moves, extraction, import rewrites) incrementally with approval gates, rollback points, and continuous verification.
Resolve TypeScript compilation errors by grouping diagnostics, fixing root causes first, applying safe fix patterns, and verifying via a clean compile.
Review code changes for architectural consistency, correctness risks, security/performance concerns, and verification gaps; produce a prioritized, actionable review report.
Fix frontend runtime errors (console exceptions, blank screens) by capturing repro steps and diagnostics, applying a minimal targeted fix, and verifying user-visible behavior.
Enforce test-first changes and debug based on failing tests.
Enforce .agentpolicy rules before executing commands.
Detect repo tooling and patterns, then record a dynamic manifest.
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, alignment before implementation, and creating TodoWrite todos for checklists
Apply simple repo conventions for reproducible changes and clear diffs.
这是图生视频(Image-to-Video)提示词生成的专业知识库,为 video-prompt-generator Agent 提供方法论支持。
Excel文档生成技能包,专门用于将网文改编项目的多个组件(剧情、脚本、分镜、图像提示词)整合到一个结构化的Excel文档中。
Your approach to handling testing pytest. Use this skill when working on files where testing pytest comes into play.
GitHub Issue を起点としたワークフローを実行する。Issue の分析、作業計画、実行、レビューを連携して行う際に使用する。
Guidance for Using AlarmKit in a SwiftUI App from Xcode AdditionalDocumentation. Use when implementing, updating, or reviewing related features and you need to consult the local Xcode doc at /Applications/Xcode.app/Contents/PlugIns/IDEIntelligenceChat.framework/Versions/Current/Resources/AdditionalDocumentation/SwiftUI-AlarmKit-Integration.md. (Xcode 26.2 17C52)
Guidance for Implementing Liquid Glass Design in AppKit from Xcode AdditionalDocumentation. Use when implementing, updating, or reviewing related features and you need to consult the local Xcode doc at /Applications/Xcode.app/Contents/PlugIns/IDEIntelligenceChat.framework/Versions/Current/Resources/AdditionalDocumentation/AppKit-Implementing-Liquid-Glass-Design.md. (Xcode 26.2 17C52)
Create a new React component following project conventions
This skill enables Nanobot to proactively analyze and clean system junk, caches, and redundant development files.
Terraform, CloudFormation, ARM templates, Kubernetes manifests, and state management best practices
Model selection guidelines, feature engineering techniques, hyperparameter tuning strategies, evaluation metrics, and common ML frameworks
Model deployment strategies, monitoring and drift detection, CI/CD for ML models, feature store concepts, and model versioning
Test coverage, code quality, defect metrics, and QA KPIs
Build backend application logic including route generation, request/response handling, and database connectivity. Use for server-side development.
Generate complete production-ready software projects from project books and specification documents.
Use when working on the trahoangdev/codex-test repository, including setup, running the Next.js app, and making common edits.
Generates comprehensive test strategies (60/30/10 distribution) from OpenSpec proposals. Activates via codeword [ACTIVATE:TEST_STRATEGY_V1] injected by hooks after OpenSpec proposal creation. Activation trigger: [ACTIVATE:TEST_STRATEGY_V1]
{{AGENT_DESCRIPTION}}
Criar endpoint de API com validacao de input robusta usando Zod.
Implementar nova funcionalidade seguindo TDD (Test-Driven Development).
Summarize API Guide - When the user asks to summarize a list of APIs
No description available
No description available
Modern React desenleri ve prensipleri. Hook'lar, kompozisyon, performans, TypeScript en iyi uygulamaları.
MITRE ATT&CK'a dayalı Red Team taktik prensipleri. Saldırı aşamaları, tespit atlatma, raporlama.
Auto-invoked when user is making git commits. Enforces conventional commit format and ensures commit messages are descriptive.
Comprehensive development workflow specialist combining TDD, debugging, performance optimization, code review, and quality assurance into unified development workflows
Enterprise Mermaid diagramming skill for Claude Code using MCP Playwright
No description available
Improve clarity and flow while preserving meaning.
O2ButtonGroup 按钮组
O2Object 对象选择组件
Summarize text or a document
Optimized for architecture design, algorithm optimization, and complex problem-solving with deep reasoning. Use for architecture, design, planning, structuring systems, or algorithm work. and creative exploration - STRAYLIGHT-CORE CONFORMANT
Run tests, fix failures, iterate until all pass. Use after code changes.
Readeck is a simple web application that lets you save the precious readable content of web pages you like and want to keep forever. https://readeck.org/
Change working directory.
Rate the severity of security issues found during review.
When reviewing code, always include a specific marker in your comments.
No description available