Top Agent Skills

Research external tools/competitors for a topic and write findings to BRAINSTORM.md (project topics) or ~/.clade/research/ (personal topics). Use when user says "/research [topic]".

Post-ship documentation sync — updates README, CHANGELOG, AGENTS.md, ARCHITECTURE, and TODOS after a release. Ensures docs never drift from code. Run after /commit or /ship before closing a PR.

Mapa i przewodnik po wyspecjalizowanych skillach platformy Soneta (enova365, Triva): soneta-programming (ORM, kod biznesowy), soneta-addon-planning, soneta-business-xml, soneta-form-xml, soneta-repx (wydruki DevExpress .repx), soneta-place-def-elementow, soneta-config (import/eksport XML, scan-folders, appsettings.json — porty i adresy komponentów), soneta-config-reg (rejestr konfiguracji ConfigReg, providery, *.reg.json), soneta-tools (narzędzia CLI: dbmgr, buscall, SonetaFrame), soneta-containers (docker compose, Apple container, Helm/Kubernetes, wersje obrazów, baza w kontenerze). Używaj gdy użytkownik: (1) rozpoczyna zadanie dla platformy Soneta i nie wiadomo, który skill wybrać; (2) pyta ogólnie o dodatki, moduły lub rozszerzenia Soneta ERP; (3) wspomina enova, Soneta Enterprise, Triva bez sprecyzowania warstwy (dane, UI, logika, płace); (4) chce poznać dostępne skille; (5) realizuje zadanie obejmujące wiele warstw platformy (np. moduł z bazą, formularzami i logiką).

Design system Soneta / enova365 do budowania aplikacji webowych spójnych wizualnie z enova365 ERP: palety kolorów (jasny/ciemny), typografia, layout, komponenty UI (przyciski, formularze, tabele, sidebar, header, kafelki, modale), odstępy, cienie, ikony SVG, animacje, responsywność. Używaj gdy użytkownik: (1) prosi o zaprojektowanie, zbudowanie lub ostylowanie strony/aplikacji w stylu Soneta/enova365; (2) wspomina 'styl enova', 'styl Soneta', 'design system enova365', 'UI enova'; (3) chce dashboard, formularz, stronę logowania, panel administracyjny w estetyce enova365; (4) prosi o landing page lub aplikację z zielonym motywem enterprise w stylu Soneta; (5) pyta o kolory, czcionki, komponenty lub wzorce UI enova365/Soneta. Działa z każdym stackiem (HTML/CSS, React, Vue, Tailwind, itp.).

Planowanie projektów dodatków dla platformy Soneta (enova365, Triva) — interaktywny, etapowy proces od wizji biznesowej po specyfikację implementacyjną, zasilającą skille /soneta-business-xml, /soneta-form-xml i /soneta-programming. Używaj, gdy użytkownik chce zaplanować nowy moduł lub dodatek (założenia, specyfikacja funkcjonalna, struktura danych i interfejsu użytkownika).

Create and maintain lightweight Architecture Decision Records as agent-readable decision memory — what was decided, why, and which alternatives were rejected. Use when "record this decision", "set up ADRs", "the agent keeps suggesting Y again". Docs vs code drift → plan-docs-sync. Session state → handoff.

Audit CI/CD pipelines (GitHub Actions) for cost, speed, and safety. Use when the Actions bill is high, Actions minutes, runner cost, slow CI, artifact/cache storage, or "CI/CD / workflow audit". Gate logic (bypass, ratchet gaming, required-but-not) → audit-gate-logic.

Systematic debugging workflow for errors and bugs. Use when debugging errors, investigating bugs, troubleshooting issues, or when something isn't working as expected. Integrates Sentry MCP for production error context, Firecrawl for researching fix patterns, and Sequential Thinking for complex multi-step diagnosis.

Audit frontend API calls against backend implementation for contract alignment and network shape. Use when "API audit", "FE-BE contract", or "review frontend API integration". Live 4xx/5xx reproduction → debug-fe-be-integration.

Drive a planned change to 100% coverage across an entire codebase when a prior agent run stopped early. Use whenever a refactor, migration, rename, rule-application, or sweeping edit was planned and partially executed but left incomplete — i.e.

Build and maintain cohesive design systems and component libraries with tokens, theming, and documented variants. Use when the user says "design system", "component library", "design tokens", "theming", "consistent styling", "reusable components", or "variant props".

Keep a PR merge-ready by triaging comments, resolving clear conflicts, and fixing CI in a loop.

Audit and fix SEO for any web app. Use when asked to "improve SEO", "add meta tags", "fix search ranking", "add structured data", "sitemap", "canonical URLs", "Open Graph", "Google indexing", "rich results", "SEO audit", or "why is my site not ranking".

Read-only audit of config/env parity across dev, staging, and prod — missing or misnamed vars, drifted flags, hardcoded values, secrets reused across environments. Use when "works locally but not in prod", "audit our environments", or "config drift". Local runnability → workflow-environment-ready.

Audit and optimize application runtime performance (Core Web Vitals, slow code, load time). Use when "slow page", "LCP/INP/CLS", or "optimize performance". JS payload → audit-bundle-size. Concurrent breaking point → test-load. Timeouts/retries → audit-resilience.

Detect and fix repo-wide anti-patterns and consistency drift (naming, organisation, repeated smells). Use when "code smell", "anti-pattern", "technical debt", or "standardize the codebase". This PR/diff review → audit-code-review.

Audit a site for answer-engine / GEO citation readiness (ChatGPT, Perplexity, AI Overviews), then a phased plan. Use when "AEO", "GEO", "show up in ChatGPT/Perplexity", "AI search visibility", "llms.txt", or "am I blocking AI crawlers". Classic SEO meta/sitemap → enhance-web-seo.

Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

Close the post-launch improvement loop for any shipped app. Use when asked to "improve the app after launch", "fix the top issues", "post-launch polish", "what should I fix next", "production issues", "iterate on feedback", "post-release improvements", "what is broken in prod", "ship a polish pass", or "make it better.

Drive an entire repository to a fully green baseline — typecheck, lint, tests, and build all passing from a clean checkout — when the user has explicitly authorized fixing. Use when "make the repo green", "get CI passing", "fix all the failing tests". Ratchet integrity → audit-gate-logic.

Human interface agent that translates ecosystem activity into clear, actionable communication. Creates status briefings, decision requests, celebration reports, concern alerts, and opportunity summaries. Use for 'status update', 'brief me', 'what's happening', 'summarize progress', or when complex multi-agent work needs human-readable reporting.

Comprehensive MDX content sanitizer that escapes angle brackets, generics, and other JSX-conflicting patterns to prevent build failures

Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.

Makes iOS apps feel premium, polished, and unmistakably native — SF Symbols mastery, SwiftUI spring animations, haptic feedback choreography, blur/vibrancy materials, Dynamic Type, color system design, and the specific spacings and radii Apple uses. This is about TASTE, not syntax. Activate on 'iOS design polish', 'SwiftUI animation', 'SF Symbols', 'haptic feedback', 'premium iOS feel', 'Apple HIG', 'native iOS look', 'Liquid Glass', 'iOS visual design', 'app polish'.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. Activate on: Playwright, webapp testing, browser automation, E2E testing, UI testing. NOT for API-only testing without browser, unit tests, or mobile app testing.

AWS CDK infrastructure builder using TypeScript with L2/L3 constructs and Well-Architected patterns. Activate on: AWS CDK, CDK construct, CDK stack, CDK pipeline, AWS infrastructure as code TypeScript, L2 construct, CDK patterns. NOT for: Terraform IaC (use terraform-module-builder), Kubernetes manifests (use kubernetes-manifest-generator), serverless framework (use devops-automator).

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.

Failure diagnosis, DAG mutation, and escalation engine for the WinDAGs meta-DAG. Receives failure information and quality vectors from the Evaluator. Classifies failures on four dimensions. Follows a five-level escalation ladder. Applies seven mutation types with saga compensation. Enforces BC-EXEC-002, BC-EXEC-003, BC-FAIL-002, BC-FAIL-005. Activate when operating as the Mutator role in the meta-DAG, when diagnosing node failures, when restructuring a DAG at runtime, or when deciding escalation level.

Analyze complex systems through stocks, flows, and feedback loops to find high-leverage interventions. For organizational, environmental, social, and technical systems exhibiting circular causality. NOT for linear problems or simple cause-effect chains.

Interprets GitHub Actions run status and logs, diagnoses CI failure patterns, and suggests targeted fixes. Handles dependency install failures, test timeouts, build OOM, flaky tests, and workflow misconfigurations. Activate on: 'CI failing', 'build broken', 'workflow error', 'GitHub Actions debug', 'flaky CI', 'pipeline timeout', 'CI red'. NOT for: writing new workflows from scratch (use github-actions-pipeline-builder), CI caching strategy (use ci-cache-optimizer), deployment orchestration (use devops-automator).

Use when designing, building, or debugging a Model Context Protocol (MCP) server in Node/TypeScript. Triggers: stdio JSON-RPC handshake, tool descriptions as discovery surface, lazy startup vs eager catalog loading, telemetry placement, schema design for tool inputs (zod), tool naming conventions for discoverability, error handling that does not leak stack traces, MCP client compatibility (Claude Desktop, Claude Code, Cursor), local resource fetching, secrets and env var handling, distributing as npm + claude mcp add. NOT for MCP client implementation, MCP HTTP transport (different surface), Anthropic Agent SDK building, or non-MCP plugin systems.

Expert en cartes et géolocalisation avancé (OpenStreetMap, Nominatim, OSRM, geocoding, routing, timezones, GIS)

AI Safety Specialist IA — Expert en sécurité IA (alignment, guardrails, filtrage de contenu, test de biais, red teaming)

Expert en technologies éducatives avancées (LMS, MOOC, adaptive learning, AI tutoring, assessment, DZ context)

Team lead agent — sprint planning, standups, velocity, impediments, team health

Expert en ComfyUI workflows avancé (install, custom nodes, model management, workflow design)

Expert en fintech avancé (open banking, digital wallets, BNPL, crypto, regulations, DZ context)

Expert en informatique quantique avancée (Qiskit, Cirq, algorithms, error correction, DZ research)

Yuanbao groups — @mention users, info/members query, Chinese AI assistant

Expert en animations mathématiques Manim (3Blue1Brown, équations, algorithmes, vidéos éducatives)

Expert en technologies pour animaux de compagnie avancées (tracking, health monitoring, feeding automation, insurance, DZ context)

Technical Writer IA — Expert en documentation technique (API docs, README, architecture docs, ADRs, changelogs). Rend le savoir explicite et accessible.

Expert en technologies agricoles avancées (precision farming, IoT sensors, satellite imagery, yield prediction, DZ context)

ETL Pipeline Specialist IA — Expert en pipelines ETL (Airflow, dbt, data quality, incremental loads, CDC)

Expert en génération musicale HeartMuLa (lyrics + tags → Suno-like songs)

Expert en logistique avancée (route optimization, last-mile, warehouse automation, tracking, DZ context)

Expert en scheduling v2 (cron, Celery Beat, Temporal, BullMQ, tâches récurrentes, timezones)

MUX Architect IA — Expert en architecture UX technique, CSS systems, motion design systems, et implementation developer-friendly. Pont entre design et code.

3D modeler v2 — Blender, Maya, ZBrush, texturing, rigging, animation, game assets, rendering

Expert en prospection à froid (cold email, LinkedIn DMs, séquences personnalisées, délivrabilité)

Redige a reconvencao — pretensao propria do reu deduzida na mesma peca da contestacao (CPC 343): conexa com a acao principal ou com o fundamento da defesa, processada simultaneamente. Cobre o cabimento, a admissibilidade independente da contestacao (343 §2 e §6), o valor da causa proprio, as custas e a contestacao do autor-reconvindo (15 dias). Use quando o operador disser reconvencao, reconvir, pedido contraposto, contra-ataque do reu, o reu tambem quer cobrar, ou houver pretensao propria do reu conexa a demanda.

Redige contrarrazoes (resposta ao recurso da parte contraria) defendendo a decisao recorrida — preliminares de NAO CONHECIMENTO (intempestividade, desercao, falta de pressuposto), refutacao do merito recursal, devolucao de interlocutorias nao agravaveis (CPC 1.009 §1) e pedido de majoracao de honorarios recursais (85 §11). Prazo 15 dias uteis (1.003 §5). Use quando o operador disser contrarrazoes, responder ao recurso, fui intimado da apelacao/agravo, defender a sentenca, contraminuta.

Redige agravo interno do CPC 1.021 contra decisao MONOCRATICA do relator em tribunal, levando a materia ao colegiado, no prazo de 15 dias uteis, com impugnacao especifica dos fundamentos (1.021 §1) e alerta sobre a multa de 1-5 por cento (1.021 §4). Use quando o operador disser agravo interno, recorrer da decisao monocratica, decisao do relator, levar ao colegiado, agravo regimental.

Redige acao rescisoria - acao autonoma de impugnacao para desconstituir coisa julgada (CPC 966 hipoteses I a VIII; 967 legitimidade; 968 requisitos + deposito de 5% no inciso II; 969 nao suspende o cumprimento em regra; 975 prazo decadencial de 2 anos do transito em julgado). Competencia originaria do tribunal. Use quando o operador disser acao rescisoria, rescindir sentenca transitada, desconstituir coisa julgada, violacao de norma na sentenca, ou prova nova depois do transito.

Redige acao declaratoria pelo rito comum: interesse limitado a declaracao (CPC 19 - existencia, inexistencia ou modo de ser de relacao juridica; autenticidade ou falsidade de documento), admissibilidade ainda que ja ocorrida a violacao do direito (CPC 20). Declaratoria positiva x negativa; declaratoria incidental. Use quando o operador disser acao declaratoria, declarar inexistencia de debito, declarar relacao juridica, declaratoria de nulidade, ou quero que o juiz declare.

Estrutura o requerimento e a estrategia de provas no rito comum (CPC 369-484): documental (434+), testemunhal (rol, ate 10 — 357 §6/450-457), pericial (464-480 — quesitos e assistente tecnico), depoimento pessoal (385-388), inspecao judicial. Trata o onus da prova (373) e a vedacao a prova ilicita (369 + CF 5 LVI). Use quando o operador disser provas, requerer provas, rol de testemunhas, pericia, quesitos, depoimento pessoal, prova documental, prova emprestada, ou montar a estrategia probatoria do caso.

Redige acao de cobranca pelo rito comum (quando nao ha prova escrita) ou acao monitoria (CPC 700-702 - prova escrita SEM eficacia de titulo executivo): cheque prescrito, nota promissoria sem forca, contrato sem aceite. Mandado de pagamento + honorarios 5% (701); embargos ao mandado (702); prazos prescricionais (CC 206). Use quando o operador disser cobrar divida, acao de cobranca, monitoria, cheque prescrito, nota promissoria sem forca, ou contrato sem titulo executivo.

Avalia riscos e oportunidades do caso civel e sugere os proximos passos processuais. Pondera probabilidade de exito, onus da prova, custos/beneficios de acordo x litigio, momento de tutela de urgencia, escolha de pedidos e de via (conhecimento x cumprimento), e calibra a postura. Use quando o operador disser qual a estrategia, vale a pena recorrer, devo fazer acordo, quais os riscos, proximo passo, ou pedir analise estrategica do caso.

Argui impedimento (CPC 144, hipoteses objetivas I a IX) ou suspeicao (CPC 145, amizade intima/inimizade, presente/aconselhamento, credor/devedor, interesse no julgamento — I a IV) do juiz, em peticao especifica no prazo de 15 dias do conhecimento do fato (CPC 146), que o juiz reconhece ou remete ao tribunal — efeito suspensivo declarado pelo relator (146 §2), extensiva a MP, auxiliares da justica e demais sujeitos imparciais (CPC 148). Use quando o operador disser suspeicao, impedimento do juiz, juiz parcial, recusar o juiz, excecao de suspeicao, juiz amigo da parte contraria.

Redige pedido de gratuidade da justica (CPC 98-102) e impugnacao a gratuidade da parte contraria. Trata a diferenca PF x PJ: pessoa fisica tem presuncao relativa (CPC 99 §3); pessoa juridica deve PROVAR a insuficiencia (Sumula 481/STJ). Use ao requerer ou impugnar justica gratuita, ao analisar declaracao de hipossuficiencia, quando o operador disser pedir gratuidade, justica gratuita, hipossuficiencia, impugnar a gratuidade do autor, beneficio da assistencia. Acionada pelo civel-master na gestao processual transversal.