Team-aware retrospective for the Karvey method. Per-person breakdowns, shipping streaks, test-health trends, and growth opportunities from commit history and work patterns.
Generate implementation tasks from approved architecture. Creates Tasks in ClickUp (E{n}.F{n}.T{n}) with dependencies, or updates PLAN.md checklist.
Execute unit tests and E2E tests after implementation. Generates test_plan.md and test_evidence.md with request/response/PASS/FAIL evidence.
Build a content cluster plan from seed keywords — pillar+spokes architecture with internal-link map, intent grouping, and quality scorecard.
Diagnose and fix Kotlin coroutine race conditions, Flow issues, and thread safety bugs
Manage Koyeb backend services - check status, view logs, redeploy, list deployments
Audit Kubernetes manifests, Helm charts, and Kustomize overlays against CIS Kubernetes Benchmark and NSA/CISA hardening — pod security, resources, probes, RBAC, networking,…
Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and c — from…
Incrementally upgrade a Laravel application to the latest stable version, shifting one major version at a time.
Use when the sensei tutor selects or applies a pedagogical framework. Routes to 10 frameworks: 5w2h (default — structured analysis), pear-loop (Plan-Explore-Analyze-Rewrite),…
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors).
Systematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when — from…
Run a standalone code review on lilnas changes — correctness, testing, maintainability, project standards — plus conditional reviewers (kieran- typescript, julik-frontend-races,…
Configure e opere o ambiente local e de produção deste projeto com Docker, Podman, Minikube e Kubernetes.
Query Logfire logs and traces for debugging. Use when user mentions logs, traces, errors, exceptions, slow requests, or asks to debug backend issues.
Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents —…
プロジェクトの全体像を調査・文書化。ファイル構造、API、データモデル、外部連携、認証、データフロー、歴史を網羅的に整理し、memory/system-architecture.md に保存。プロジェクトの認識ズレを防ぐための Single Source of Truth…
Use when the user asks to build an MCP server, create an MCP integration, wrap an API for AI agents, or expose tools via the Model Context Protocol.
Search and fetch official MediaMTX documentation from mediamtx.org: kickoff (introduction, install, upgrade), features (architecture, publish, read, record, playback,…
Cross-System Code-Analyse und Developer-Handoff fuer AutomationOne. Versteht Nutzerauftraege, verfolgt Daten- und Steuerfluesse quer durch ESP32, MQTT, Server und Frontend anhand…
Avalie, projete e evolua a arquitetura deste projeto entre os espectros de monólito modular e microserviços.
Use when transforming a project's architecture pattern - e.g., Flat to Modular, MVC to Clean Architecture, Monolith to Modular Monolith.
Use when switching a project or component between frameworks - React to Vue, Vue to Svelte, or any supported framework pair.
Migrate a pytest integration test to the test-loop framework. Use when converting a pytest from pytest/tests/ to a deterministic test-loop test.
Migrate existing CLAUDE.md files to .rpiv/guidance/ system. Finds all CLAUDE.md files, transforms references, and creates architecture.md files in the guidance shadow tree.
Use when a component needs migration to the target architecture or framework version.
Use when a complete module needs migration to the target architecture - runs 6 phases with approval gates.
Staged migration plan (additive → backfill → dual-write → cutover → cleanup) for Postgres / Supabase, with rollback gates, observability checkpoints, and db-reviewer agent review.
Build and deploy documentation sites with Mintlify. Use when creating API docs, developer portals, or knowledge bases.
Generate model class จาก MCP schema (GoAPI + MainAPI models). รองรับ Dart, TypeScript ฯลฯ ตาม project. ใช้เมื่อต้องสร้าง model ใหม่ เช่น /model-gen Shop, /model-gen MongoDocModel
Decide the 6R modernization pattern — Rehost / Replatform / Refactor / Repurchase / Retire / Retain — using a decision tree and cost/time/risk matrix.
Comprehensive code review aggregating architecture, performance, documentation, scientific correctness, and quality checks. Use after writing code or during PR review.
Build a zero-based or 50/30/20 AUD budget mapped from income, fixed costs, and goals, with pay-day automation routing and AU bank-account architecture.
Service health monitoring, alerting patterns, and incident response. Check if services are up, diagnose issues, set up alerting rules.
Drop in supervisor config + /healthz endpoint + restart runbook for each service in profile.monitors.targets, per supervisor (systemd / pm2 / k8s / docker-compose)
Wygeneruj skrypt CI do synchronizacji grafu zaleznosci kodu z platforma Monolynx. Analizuje projekt Python (Django, FastAPI, Flask itp.), tworzy cicd/sync_graph.py i stage w…
Use this skill when running or debugging the Myco skill lifecycle end to end: identifying candidates from vault knowledge, curating them through approval, generating `SKILL.md`…
Activate Mythic Engineering mode — architecture-first, document-guided, AI-orchestrated development with six specialist roles.
Scan for EF Core N+1 query patterns — loops over materialized lists that access navigations, missing Include, lazy loading in hot paths. Reports file:line findings.
Narrow bare `rescue _ ->` / `rescue e ->` so UndefinedFunctionError, KeyError, and typos propagate instead of being swallowed.
Execute complex tasks through sequential sub-agent orchestration with intelligent model selection, meta-judge → LLM-as-a-judge verification — from TuYv/ccpm
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
Use when: designing, scaffolding, implementing, refactoring, or debugging NestJS applications; building modules, controllers, services, providers, guards, interceptors, pipes,…
Cria um Django Model completo no padrão Fat Model do SurveyHub: UUID PK, TextChoices para status, soft delete (deleted_at), state machine (ativar/pausar/encerrar com guards),…
Cria um Manager e QuerySet customizado Django para um model do SurveyHub, com métodos em português seguindo o padrão do projeto (ativos, nao_deletados, do_usuario, com_contagens,…
Cria uma função de serviço em apps/{app}/services/{dominio}_service.py para orquestrar lógica que envolve múltiplos models, efeitos colaterais externos (email, arquivo,…
Audit/fix Next.js i18n SEO — crawlability, 307 redirects, locale URLs, sitemap, hreflang.
Next.js SEO optimization guide. Use when building Next.js apps, optimizing for search engines, fixing Google indexing issues, implementing metadata, sitemaps, robots.txt, JSON-LD,…
Creates Next.js frontends with shadcn/ui. Use when building React UIs, components, pages, or applications with shadcn, Tailwind, or modern frontend patterns.
分析nft platform compliance相关互联网金融合规问题。 覆盖：监管框架、资质要求、合规要点、违规风险。 适用情形：用户提及nft platform compliance相关事项。
Add OAuth2 credential support to an existing n8n node — creates the credential file, updates the node, adds tests, and keeps the CLI constant in sync.
Fetch NuGet package metadata, versions, vulnerabilities, compat matrix, and deprecation status. Supports dotnet list package and NuGet.org v3 API.
MUST use for developer provider recommendations involving free tier, free trial, cheap, pricing, best value, hosting, Node hosting, Next.js, auth, Postgres, database, email API,…
MUST use for developer provider discovery involving free tier, free trial, cheap, pricing, best value, hosting, Node hosting, Next.js, auth, Postgres, database, email API,…
Use when: refreshing OIAP platform support documentation, updating MATRIX.md, researching agent harness platform docs, auditing exporter assumptions, checking target profiles…
Use this skill when working with Myco's skill lifecycle system — whether generating a new skill from an approved candidate, reviewing the candidate queue, updating a stale skill,…
Optimize CLAUDE.md — remove noise (directory trees, type defs, tool tables), keep only commands, constraints, and architecture rules that agents can't discover from code
Create and update Mermaid UML diagrams in .orchestra/uml/ — sequence, component, and class diagrams. Use when adding new diagrams, updating existing ones after architecture…
Validates that a DAG node's output matches its declared JSON schema before passing to downstream nodes. The glue that makes multi-agent DAGs reliable.
Debug Output SDK workflow issues. Use when user reports a workflow failing, erroring, hanging, producing wrong results, or asks to debug, troubleshoot, or investigate a workflow…