Coding & Dev Tools

9,772 skills
dracounion
7-day-life-reset
当感到生活迷茫、缺乏动力、效率低下,需要快速打破现状并重建秩序时
11 · bundle
dracounion
problem-as-guide
当在行动或追求目标过程中遇到挫折、痛苦或不满等负面体验时,调用此模型将负面体验转化为指引方向的积极信号
11 · bundle
dracounion
learn-by-teaching
当需要深化对某个主题的理解、检验知识掌握程度或克服“冒名顶替综合征”时
11 · bundle
dracounion
career-game-design
当需要主动设计和构建个人职业生涯,而非被动接受传统就业时
11 · bundle
dracounion
anti-niche-branding
当个人或品牌不希望被狭窄市场定义,追求基于独特世界观和多样能力的长期发展时
11 · bundle
dracounion
life-as-game-design
当需要将个人目标或生活挑战转化为结构化、可执行的游戏化系统时
11 · bundle
dracounion
perspective-framing
当需要在写作中与读者建立情感连接、放大问题严重性,并引出后续解决方案时
11 · bundle
dracounion
combat-mode-strategy
当需要在2-3个月内集中精力攻克一个重大、有挑战性的个人或职业目标时,使用此模型
11 · bundle
dracounion
flow-state-balancing
当需要进入并维持高效、专注的心流状态,以提升学习、工作或技能获取效率时
11 · bundle
dracounion
modern-skill-mapping
当需要将抽象的核心能力(如逻辑、修辞、心理学)转化为具体、可实践、可学习的现代技能时调用此模型
11 · bundle
dracounion
burn-boats-commitment
当需要克服拖延、激发最大行动力以完成一项重大挑战或转型时
11 · bundle
dracounion
failure-feedback-loop
当遭遇挫折、失败或结果不如预期时,用于将负面经验转化为成长燃料
11 · bundle
dracounion
holonic-unit-analysis
当需要解构一个复杂系统(如品牌、产品、知识体系)以理解其组成部分及结构时
11 · bundle
dracounion
perspective-reframing
当需要从现有内容中创造新意,或避免内容同质化时
11 · bundle
dracounion
action-first-iteration
当面对新任务或目标,因过度思考“如何开始”或“需要多久”而陷入拖延、焦虑,迟迟无法行动时
11 · bundle
dracounion
brand-identity-framing
当需要为个人或小型企业建立在线品牌身份,以吸引目标受众并建立共享认知框架时
11 · bundle
dracounion
focus-matrix-framework
当需要系统性地理解、诊断和提升个人专注力,以优化工作效能和生活体验时
11 · bundle
dracounion
life-as-game-framework
当需要将生活或工作中的复杂情境转化为可管理、可执行的系统时,或当感到迷茫、缺乏动力、陷入社会比较时,调用此模型来重新构建认知和行动框架
11 · bundle
dracounion
proactive-goal-setting
当个体感到生活缺乏方向、陷入重复性任务或被动接受外部目标,导致焦虑、无聊或停滞时,调用此模型以重新获得对生活的掌控感和成长动力
11 · bundle
kursku
lex
Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.
55 · bundle
kursku
ai-md
Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance.
55
kursku
diary
Unified Diary System: A context-preserving automated logger for multi-project development.
55 · bundle
artubss
senior-architect
Complete toolkit for senior architect with modern tools and best practices.
10 · bundle
artubss
aeon
Esta skill deve ser usada para tarefas de machine learning em séries temporais, incluindo classificação, regressão, clustering, forecasting, detecção de anomalias, segmentação e busca de similaridade. Use quando trabalhar com dados temporais, padrões sequenciais ou observações indexadas por tempo que requerem algoritmos especializados além de abordagens padrão de ML. Particularmente adequada para análise univariada e multivariada de séries temporais com APIs compatíveis com scikit-learn.
10 · bundle
artubss
shap
Interpretabilidade e explicabilidade de modelos usando SHAP (SHapley Additive exPlanations). Use essa skill ao explicar predições de modelos de machine learning, computar importância de features, gerar plots SHAP (waterfall, beeswarm, bar, scatter, force, heatmap), depurar modelos, analisar vieses ou justiça de modelos, comparar modelos ou implementar IA explicável. Funciona com modelos baseados em árvores (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), modelos lineares e qualquer modelo black-box.
10 · bundle
artubss
transcribe
Transcrever arquivos de áudio para texto com diarização opcional e dicas de falantes conhecidos. Use quando um usuário pedir para transcrever fala de áudio/vídeo, extrair texto de gravações ou identificar falantes em entrevistas ou reuniões.
10 · bundle
artubss
pymoo
Framework de otimização multi-objetivo. NSGA-II, NSGA-III, MOEA/D, frentes de Pareto, tratamento de restrições, benchmarks (ZDT, DTLZ), para problemas de design e otimização em engenharia.
10 · bundle
artubss
simpy
Framework de simulação de eventos discretos baseado em processos em Python. Use essa habilidade ao construir simulações de sistemas com processos, filas, recursos e eventos baseados em tempo, como sistemas de manufatura, operações de serviço, tráfego de rede, logística, ou qualquer sistema onde entidades interagem com recursos compartilhados ao longo do tempo.
10 · bundle
artubss
multi-stage-dockerfile
Create optimized multi-stage Dockerfiles for any language or framework
10
artubss
astropy
Biblioteca Python abrangente para astronomia e astrofísica. Esta skill deve ser usada ao trabalhar com dados astronômicos, incluindo coordenadas celestes, unidades físicas, arquivos FITS, cálculos cosmológicos, sistemas de tempo, tabelas, sistemas de coordenadas mundiais (WCS) e análise de dados astronômicos. Use quando as tarefas envolvem transformações de coordenadas, conversões de unidades, manipulação de arquivos FITS, cálculos de distâncias cosmológicas, conversões de escalas de tempo ou processamento de dados astronômicos.
10 · bundle
artubss
matchms
Análise de espectrometria de massas. Processa mzML/MGF/MSP, similaridade espectral (cosine, modified cosine), harmonização de metadados, identificação de compostos, para metabolômica e processamento de dados MS.
10 · bundle
artubss
code-review
Realize análises de código seguindo as práticas de engenharia da Sentry. Use ao revisar pull requests, examinar alterações de código ou fornecer feedback sobre qualidade de código. Abrange segurança, performance, testes e revisão de design.
10
theycallmeholla
hot-seat
Put the user in the hot seat — one question at a time until their plan, decision, or idea actually holds up. Use whenever the user says "hot seat me", "grill me", "stress-test this", "poke holes in this", "am I missing anything", or drops a plan and wants it challenged before anyone acts on it — even if they never say the words. Also used as a sub-procedure by the whiteboard and connotation-cop skills.
0
theycallmeholla
swipe-deck
Runs a Tinder-style swipe interview to pull requirements out of someone's head. Claude generates a deep pool of question cards, the user swipes right/left/up/down (yes / no / absolutely / not sure), the deck reshapes itself around every swipe, and it ends in a written brief once a saturation meter fills. Use this whenever a request is vague, broad, or taste-dependent and you would otherwise fire off a list of clarifying questions — kicking off a project, scoping a build, planning a trip or event, choosing a direction, naming something, deciding what to eat, or any "help me figure out what I want". Trigger on "swipe", "swipe deck", "tinder style", "interview me", "ask me questions", "quiz me", "20 questions me", "figure out what I want", "get it out of my head". Also reach for it proactively any time you catch yourself about to ask more than three clarifying questions in a row, or when someone says a batch of questions felt like a chore or a form.
0 · bundle
theycallmeholla
walkthrough-gif
Generate browser walkthrough recordings as GIF and MP4 from a natural language description. Use this skill whenever the user wants to record a browser walkthrough, create a product demo, document a UI flow, generate onboarding visuals, or produce a "how to" screen recording for any web app. Triggers include: "record a walkthrough of", "create a GIF showing how to", "make a demo of", "capture the flow for", "show how [feature] works in the browser", "document this UI flow", or any request combining a browser/web app with recording/capture/demo output. The skill generates a local Node.js/TypeScript project that the user runs on their machine using Stagehand + Playwright for AI-controlled browser automation, and gifski/ffmpeg for output. For quick one-off captures in the user's live browser session, prefer the claude-in-chrome gif_creator tool instead; use this skill when a re-runnable script, MP4, high-quality GIF, clean-profile recording, or CI repeatability is needed.
0 · bundle
dvy1987
socratic
Break a stuck or complex problem into the smallest sub-question that, if answered, unlocks the next step — then answer it and repeat until the path forward is clear. Load when a problem feels genuinely stuck, when reasoning keeps circling, or when deep-thinking diagnoses a Socratic frame. Also triggers on "I keep going in circles", "what is the real question here", "help me reason through this step by step", "unstick my thinking", "recursive questioning", "what is the root question". Based on the recursive Socratic questioning method (EMNLP 2023) which outperforms CoT and Tree-of-Thought on complex reasoning tasks.
3 · bundle