nikita-voloshyn

Assign agents and skills to a plan's tasks, producing docs/plans/<feature>-dispatch.md. Run after /plan.

Generate a session changelog from git diff. Triggers on 'changelog', 'what changed', 'session summary', 'diff summary'.

Run the full quality pipeline: lint, typecheck, and tests. Triggers on 'check', 'run checks', 'quality check', 'ci check'.

Pre-deployment audit: verify code quality, secrets, dependencies, and build. Triggers on 'deploy check', 'pre-deploy', 'deployment audit', 'ready to deploy'.

Maintain project documentation coverage: audit all components, update specific docs, or check coverage status. Triggers on 'docs audit', 'update docs', 'docs status', 'documentation coverage'.

Execute an approved dispatch plan task by task, producing docs/plans/<feature>-report.md. Run after /assign.

Configure OpenTelemetry export from Claude Code to a tracing backend (LangSmith, Langfuse, or Jaeger). Triggers on 'enable tracing', 'setup observability', 'configure otel', 'send traces'.

Execute the current phase from the development plan step by step. Triggers on 'phase', 'next phase', 'run phase', 'execute phase'.

Skill for defining a clear project vision and generating all core project documentation. MANDATORY TRIGGERS: "build project vision", "define the project", "what are we building", "project scope", "start a project", "plan the project", "create vision", "I want to build X", "structure my idea", "project architecture", "let's define this", "vision document", "where do we start", "project foundation", "before we write code". Use when: user describes an idea and wants to structure it, needs to go from idea → stack → phases, no clear point A or point B defined yet. Do NOT use: if the project is already in progress and vision is locked with no changes needed.

Скилл для формирования чёткой визии проекта и генерации всей базовой документации. ОБЯЗАТЕЛЬНЫЕ ТРИГГЕРЫ: "сформируй визию", "создай визию", "визия проекта", "формируем проект", "нужна визия", "начнём с визии", "определи проект", "что мы строим", "план проекта", "с чего начнём", "хочу построить X", "опиши проект", "структура проекта". Использовать когда: пользователь описывает идею и хочет её структурировать, нужно пройти путь идея → стек → фазы, нет чёткого понимания А и Б. НЕ использовать: если проект уже в работе и визия зафиксирована без изменений.

Use this skill to review, audit, or document API contracts and endpoints. MANDATORY TRIGGERS: API review, API design, REST API, GraphQL schema, gRPC proto, OpenAPI, Swagger, endpoint review, API consistency, API audit, routes, controllers. Also use when: checking naming conventions, validating error handling, reviewing versioning strategy, documenting existing API surface, finding inconsistencies across endpoints. Do NOT use for: full architecture review (use architecture-analyzer) or CI/CD pipeline review (use pipeline-auditor).

Use this skill to analyze, map, or document a codebase's architecture. MANDATORY TRIGGERS: architecture, codebase structure, module map, layer diagram, dependency flow, how is this project organized, project structure analysis. Also use when: reviewing separation of concerns, identifying design patterns in use, generating architecture documentation, onboarding to an unfamiliar codebase. Do NOT use for: CI/CD pipeline review (use pipeline-auditor), infrastructure configs (use infra-config-analyzer), or individual API endpoint review (use api-contract-reviewer).

Use this skill to map, analyze, or audit project dependencies. MANDATORY TRIGGERS: dependency, dependencies, package.json, requirements.txt, go.mod, pom.xml, Cargo.toml, Gemfile, circular dependency, outdated packages, dependency graph, import map, module dependencies. Also use when: looking for circular imports, checking for vulnerable packages, mapping internal module coupling, preparing for a package upgrade, analyzing bundle size contributors. Do NOT use for: full architecture review (use architecture-analyzer).

Use this skill to review and analyze infrastructure configuration files. MANDATORY TRIGGERS: Dockerfile, docker-compose, Kubernetes, k8s, Terraform, Helm chart, infrastructure review, container config, deployment config, YAML config, infra audit, cloud config, IaC. Also use when: reviewing Docker multi-stage builds, checking k8s resource limits, auditing Terraform security groups, optimizing container images, checking environment variable management. Do NOT use for: CI/CD pipeline files (use pipeline-auditor) or application architecture (use architecture-analyzer).

Use this skill to review, audit, or optimize CI/CD pipelines. MANDATORY TRIGGERS: CI/CD, pipeline, GitHub Actions, GitLab CI, Jenkinsfile, .github/workflows, .gitlab-ci.yml, build pipeline, deployment pipeline, review pipeline, pipeline optimization, CI audit. Also use when: checking pipeline security, looking for missing stages, optimizing build times, reviewing workflow YAML files. Do NOT use for: codebase architecture (use architecture-analyzer) or infrastructure configs like Dockerfiles (use infra-config-analyzer).

Use this skill to review system design, evaluate architectural trade-offs, or create Architecture Decision Records (ADRs). MANDATORY TRIGGERS: system design, design review, trade-off analysis, ADR, architecture decision record, scalability review, design document review, technical decision, should we use, which approach, design trade-offs. Also use when: comparing technology choices, evaluating migration strategies, reviewing RFC or design docs, assessing scalability and reliability, documenting why a decision was made. Do NOT use for: code-level architecture mapping (use architecture-analyzer) or CI/CD pipeline review (use pipeline-auditor).

Assign agents and skills to plan tasks. Use after /plan to create a dispatch schedule. Triggers: assign, dispatch, route, map tasks.

Audit and update documentation coverage for NanoVec components. Use to check which modules have docs, update component docs, or generate coverage reports. Triggers: docs coverage, document, audit docs, update docs.

Execute an approved dispatch plan task by task. Use after /assign to implement the planned work. Triggers: execute, run plan, implement, go.

Decompose a feature into tasks with domain agent assignments. Use when starting a new feature, phase, or multi-step implementation. Triggers: plan, decompose, break down, feature planning.

Reconfigure the development approach for NanoVec. Use to switch between TDD-First, YAGNI/KISS, Iterative+Timeboxing, Shape Up, or Trunk-Based development. Triggers: change approach, switch methodology, setup approach.

Scaffold a complete multi-agent Claude Code development system for any project. Run this in any repo to generate agents, skills, hooks, and documentation tailored to your tech stack. Triggers on "setup agents", "scaffold agents", "initialize agent system", "setup forgeline".