MODE_Backend_TDD
Methodological skill for Test-Driven Development in NestJS backend. This skill should be used when strict quality requirements demand tests-first approach, refactoring critical services, or building MVPs with mandatory coverage. Complements nestjs-architect skill with TDD methodology.
Docker para NestJS (Dev)
Cria e configura um ambiente de desenvolvimento Docker para NestJS com hot-reload, Dev Containers, e zero dependências no host.
FakeBuilder Generator
Gera FakeBuilders para agregados DDD usando Chance.js seguindo padrão do projeto com PropOrFactory, type augmentation e dados realistas para testes.
git-commit-helper
SEMPRE use esta skill quando usuario pedir para fazer commit, commitar, criar commit, ou escrever mensagem de commit. Analisa git diffs e gera mensagens seguindo Conventional Commits.
index-navigator
Navigate index.md files generated by the catalogador tool to identify the minimal set of documents or sections to read. Use this skill when exploring directories that contain index.md files, when attempting to read documentation in indexed folders, or when optimizing context usage by reading only relevant sections instead of entire documents.
nextjs-architect
SEMPRE use quando trabalhar com Next.js 15/React 19 + shadcn/ui + Tailwind. Arquiteta apps server-first/feature-first com decisões de estado, cache, forms, segurança e performance.
react-electron-code-health
Analisa código React + Electron contra best practices de Clean Architecture, React Hooks, Electron IPC, TypeScript, Apollo Client e Tailwind CSS. Detecta code smells, violações de arquitetura e calcula score quantitativo.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
task-onboarding
Skill para preparar contexto de tarefas de desenvolvimento; bloqueia início se artefatos obrigatórios faltarem.
test:controller-layer
Gera testes para Infrastructure Layer (Controllers, Handlers, React Components). Prioriza integracao. FakeBuilder obrigatorio. RTL com seletores por role.
test:core-layer
Gera testes unitarios para Domain Layer (Entities, Aggregates, Value Objects). FakeBuilder obrigatorio. Foco em regras de negocio e invariantes.
test-e2e-playwright
Analisa testes E2E Playwright contra best practices modernas de arquitetura, locatores, sincronização e isolamento. Detecta anti-padrões como seletores frágeis, esperas fixas, violações de POM e vazamento de recursos. Calcula score quantitativo 0-10 com penalidades por severidade. Use quando auditar qualidade de testes E2E Playwright/TypeScript em aplicações web, React, Next.js ou Electron.
test:integration
Gera testes cross-cutting que atravessam multiplas camadas DDD. FakeBuilder obrigatorio. Banco em memoria ou containers.
test:service-layer
Gera testes para Application Layer (Services, Use Cases). Prioriza integracao sobre unitario. FakeBuilder obrigatorio.
typescript-expert
Expert guidance for writing TypeScript code following modern best practices, targeting TypeScript 5.x and ES2022. Use this skill when writing, reviewing, or refactoring TypeScript code in any .ts or .tsx file. Provides comprehensive guidelines on type system usage, architecture patterns, security, testing, and performance.
spec-driven-dev
Spec-driven development methodology that transforms feature requests into structured documentation before coding. Use when users want to (1) plan a new software project or feature, (2) create requirements/design/tasks documentation, (3) follow a structured development workflow, (4) break down complex features into trackable tasks. Triggers include phrases like "let's plan this properly", "spec-driven", "create requirements", "design document", "task breakdown", "before we start coding".
selfdriven-digital-interaction-framework
Build content, webapps, and documentation based on the selfdriven Digital Interaction Framework — the layered trust architecture for digital relationships. Use when the user mentions trust layers, digital interaction framework, relationship lifecycle, agent network, trust tiers, policy stacks, risk calibration, transactional vs interactional, fidelity/confidence/provenance, or Architecture Decision Records (ADRs) in the selfdriven context.
selfdriven-ecosystem
Build selfdriven Foundation ecosystem properties — branded webapps, documents, APIs, and organisational frameworks. Use when the user mentions selfdriven, selfdriven.money, KERI/ACDC identity, Areas of Focus, Human Conductor models, or the selfdriven brand palette (flamingo #C8442F).
selfdriven-interactive-info-site-build
Build selfdriven-branded interactive info websites from conceptual sketches, notebook photos, or framework descriptions. Use when the user wants to turn notes, sketches, diagrams, or conceptual frameworks into a polished single-file HTML interactive site with the selfdriven brand system — especially for KERI/ACDC trust architecture, digital interaction frameworks, or any selfdriven knowledge base content.
computer-and-information-systems-manager
Ability to plan, direct, and oversee the development, operation, and governance of information systems to meet organisational objectives. Includes aligning technology strategy with business needs, managing teams and resources, ensuring system reliability and security, overseeing budgets and vendors, and governing risk and compliance. Applies across public and private sector contexts and is independent of specific technologies or platforms, with human accountability retained for strategic decisions, assurance, and outcomes.
industrial-engineer
Ability to analyse, design, optimise, and improve systems that integrate people, processes, technology, and resources to meet defined performance, quality, cost, and safety requirements. Includes applying engineering, statistical, and systems methods to model workflows, identify inefficiencies, evaluate trade-offs, and implement improvements across operations and supply chains. Applies across manufacturing, services, logistics, healthcare, and infrastructure contexts and is independent of specific tools or industries, with human accountability retained for decisions, outcomes, and impacts.
mechanical-engineer
Ability to design, analyse, test, and maintain mechanical systems and components that meet defined functional, safety, and performance requirements. Includes applying engineering principles to materials, structures, thermodynamics, fluid mechanics, and motion systems; producing and interpreting technical designs and specifications; validating designs through analysis and testing; and supporting manufacture, operation, and lifecycle management. Applies across industrial, infrastructure, energy, manufacturing, and product contexts and is independent of specific tools or industries, with human accountability retained for safety, compliance, and outcomes.
project-management-specialist
Ability to plan, coordinate, and control projects to achieve defined objectives within agreed scope, time, cost, quality, and risk constraints. Includes defining project plans, managing resources and stakeholders, tracking progress, addressing issues and risks, and adapting delivery in response to change. Applies across technical, organisational, infrastructure, and service contexts and is independent of specific methodologies or tools, with human accountability retained for decisions, governance, and outcomes.
software-developer
Ability to design, implement, test, deploy, and maintain software systems that meet defined requirements. Includes translating specifications into executable code, applying appropriate programming and design practices, managing changes over time, and operating software in production environments. Applies across application, platform, and infrastructure-adjacent contexts and is independent of specific languages, frameworks, or tools. Work may be performed individually or collaboratively and may be supported by automation or artificial intelligence, with human accountability retained for correctness, security, and outcomes.
create-script
Transforms content into a voiceover-ready script optimized for Chatterbox TTS. Use when the user provides ANY content for voiceover - URLs, raw text, video scripts, notes, or asks to "create a script" for audio.
voiceover
Generates audio narration from a text file using Chatterbox TTS. Use when the user wants to generate voiceover/audio from ANY text file.
memory
a file-based long-term memory using a single JSONL file, with append-only writes and recent-window search via bash + jq.
github-repo-analysis
Analyze GitHub repositories to extract insights about commit frequency, outstanding contributors, release timeline, and project health metrics. Use when users request repository analysis, commit history investigation, contributor identification, release tracking, or development activity assessment for any GitHub project.
Society in Silico Book Structure
Auto-activates when navigating or organizing the manuscript. Knows the book's structure, chapter organization, and file conventions.
Society in Silico Writing Style
Auto-activates when writing or editing prose in the manuscript/ directory. Applies Max Ghenis's direct, active voice, data-driven writing style.
reducing-entropy
Manual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias toward deletion.
prompt-creator-10-frameworks
Use when the user asks to create prompts/提示词 for a topic and expects 10 variants using ICIO, CRISPE, BROKE, CREATE, TAG, RTF, ROSES, APE, RACE, TRACE, with strict formatted output (字段清单 + “Prompt：”行 + 分隔符) and a “best prompt” pick with reasons.
whalefall-version-update
WhaleFall(鲸落) 全局版本更新/发版同步工作流. 用于 bump 版本号(语义化 MAJOR.MINOR.PATCH)、消除 APP_VERSION/pyproject/env/uv.lock/部署脚本/健康检查/页脚/错误页/README/CHANGELOG/About 时间轴的版本漂移,并提供自检脚本与提交/PR 模板.
career-advisor
Career Advisor agent for PhD application planning and career management. Helps with university research, application tracking, professor matching, and career documentation.
youtube
Extract subtitles, frames, and metadata from YouTube videos. Use when user shares a YouTube URL and wants transcript, screenshots, or video analysis.
unity-bootstrap
Bootstrap a new Unity project for a 2D management/simulation game. Use when you need to create the Unity project, choose URP/UI approach, set up folder structure, gitignore, packages (Input System/TextMeshPro), and establish a minimal scene + tick loop scaffold before porting gameplay systems.
unity-migration
Migrate a browser-based JavaScript/Canvas game to Unity (C#). Use for Shelter 2250 (or similar) when you need: (1) Unity project setup decisions (2D/URP/input/UI), (2) mapping existing JS classes/systems to Unity architecture, (3) porting core simulation loops (time/resources/rooms/dwellers/save), and (4) planning incremental milestones with parity checks.
morpho-solana-frontend
Build production-ready frontend for Morpho Blue lending protocol on Solana. Covers all 26 program instructions across supply/borrow, flash loans, liquidations, authorization, and admin features. Uses Next.js 14, Anchor client, Jupiter wallet adapter, and Kamino-style UI/UX. Integrates with morpho-solana-builder skill for contract understanding.
torchserve
Model serving engine for PyTorch. Focuses on MAR packaging, custom handlers for preprocessing/inference, and management of multi-GPU worker scaling. (torchserve, mar-file, handler, basehandler, model-archiver, inference-api)
torchtext
Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, regextokenizer, nlp-pipeline)
torchvision
Computer vision library for PyTorch featuring pretrained models, advanced image transforms (v2), and utilities for handling complex data types like bounding boxes and masks. (torchvision, transforms, tvtensor, resnet, cutmix, mixup, pretrained models, vision transforms)
unsloth-core
Core fundamentals of Unsloth for fast LLM fine-tuning, covering FastLanguageModel setup, optimized gradient checkpointing, and native inference acceleration (triggers: unsloth, FastLanguageModel, from_pretrained, get_peft_model, for_inference, gradient checkpointing).
unsloth-cpt
Strategies for continued pretraining and domain adaptation in Unsloth (triggers: continued pretraining, CPT, domain adaptation, lm_head, embed_tokens, rsLoRA, embedding_learning_rate).
unsloth-datasets
Standardizing and formatting datasets for Unsloth, including chat template conversion and synthetic data generation (triggers: chat templates, ShareGPT, Alpaca, conversation_extension, add_new_tokens, standardize_sharegpt, formatting_prompts_func).
unsloth-dpo
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
unsloth-fft
Performing full fine-tuning (FFT) in Unsloth with 100% exact weight updates and optimized gradient checkpointing. Triggers include fft, full fine-tuning, full_finetuning, exact fine-tuning, and weight updates.
unsloth-gguf
Exporting fine-tuned models to GGUF format for deployment in llama.cpp, Ollama, and local serving tools. Triggers: gguf, quantization export, llama.cpp, ollama, save_pretrained_gguf, modelfile.
unsloth-grpo
Implementation of Group Relative Policy Optimization (GRPO) for training reasoning models, optimized for 8x memory savings (triggers: GRPO, reasoning, DeepSeek-R1, reinforcement learning, RLVR, GRPOTrainer, thinking tokens).
unsloth-inference
Deploying fine-tuned models for production inference using native kernel optimization, vLLM, or SGLang. Triggers: inference, serving, vllm, sglang, for_inference, model merging, openai api.
unsloth-long-context
Training models on extended context lengths using optimized RoPE scaling and memory-efficient attention kernels. Triggers: long context, max_seq_length, rope scaling, large context window, flex attention.
Page 1665 of 1706 · 85266 results