garage

Plugin garage from marketplace garage in OmexIT/claude-skills-pack. Commands read from the repo's manifest — 27 days ago.

Skills (48)

• adr

  Use when the user wants to record an architecture decision, write an ADR or decision record, or explain why a technology, data model, boundary, or pattern was chosen over alternatives.

• api-design

  Use when the user is designing, reviewing, or changing an API contract (REST, GraphQL, or RPC): endpoint shape, naming, errors, versioning, pagination, or developer experience, before or apart from implementing it.

• api-first

  Use when the user wants to scaffold or implement a REST endpoint or resource in a Spring Boot project, especially from an OpenAPI snippet or spec: create endpoint, add API, add CRUD, generate controller, or implement POST/GET/PUT/PATCH/DELETE on a resource.

• arch-review

  Use when the user asks for an architecture review of existing Java or Spring Boot code: clean or hexagonal architecture boundaries, module boundaries, dependency direction, domain leakage, transaction boundaries, or business logic in controllers.

• code-audit

  Use when existing implementation code needs a rigorous review: code audit, code review, code quality, code smells, SOLID or duplication concerns, security or performance of a module, production readiness, or a second opinion on code that already exists.

• competitive-analysis

  Use when the user asks for a competitive analysis, competitor review, market landscape, feature comparison against rivals, or who else solves this problem.

• data-design

  Use when the user is designing a data layer or schema across PostgreSQL, MongoDB, Elasticsearch, or Typesense: data model, indexing, query patterns, consistency, or keeping several stores in sync.

• db-migration

  Use when the user needs a PostgreSQL schema or data change through Liquibase or Flyway: new table, add, rename, or drop a column, add an index, change a constraint, backfill or one-time data fix, zero-downtime migration, or a new entity that needs persistence.

• debug-triage

  Use when something is broken and the cause is not yet established: a bug report, a pasted stack trace or error log, a failing or flaky test, a crash, hang, or regression, \"X is not working\", or \"why is this happening\", before any fix is proposed.

• decision-matrix

  Use when the user needs help deciding between options with trade-offs: help me decide, compare options, which should we choose, trade-off analysis, or a weighted decision matrix for a technical, product, or strategic choice.

• design-doc

  Use when the user wants a system design doc or RFC written for a feature, or a quick gap check of one: requirements, constraints, architecture, data model, APIs, rollout, and risks. A rigorous multi-expert review before implementation belongs to spec-panel.

• docs-review

  Use when the user wants documentation reviewed or edited for clarity, correctness, structure, or consistency: review docs, edit this doc, make this clearer.

• evidence-review

  Use when work must pass a final quality gate backed by proof: evidence review, prove it works, show me proof, or deciding whether claimed test results, screenshots, and build logs justify calling something done.

• experiment-design

  Use when the user wants to measure the impact of a product change: A/B test, experiment, feature flag rollout, staged exposure, or deciding metrics, guardrails, duration, and a decision rule.

• finalize

  Use when implementation is done and the user wants to wrap it up: finalize, commit this, create a PR, ship it, or done implementing.

• fintech-ledger

  Use when work touches money movement or balances: double-entry ledger postings, wallet credit or debit, holds, capture, refunds, settlement, payouts, collections, float, multi-currency or FX, reconciliation, balance mismatches, Blnk, pgledger, or ledger tables.

• flow-map

  Use when the user wants every path through a feature mapped before coding: happy paths, validation and auth failures, network errors, concurrency conflicts, timeouts, and recovery, or asks what are all the paths or for a state diagram.

• go-to-market

  Use when the user is planning a product or feature launch: go to market, GTM, launch plan, messaging, channels, enablement, or launch success criteria.

• handoff

  Use when a skill needs to find, read, or write a handoff manifest in claudedocs, chain its output into the next skill, or clean up artifacts that downstream skills have consumed.

• incident-response

  Use only when the user explicitly asks to run or coordinate incident response for an active outage, SEV, or production incident that is still affecting users.

• infra-design

  Use when the user is designing infrastructure or deployment: Docker images, Kubernetes, Terraform, CI/CD pipelines, environments, or deployment strategy.

• linkedin-post

  Use when the user wants a LinkedIn post drafted: thought leadership, an announcement, a story, or lessons learned.

• metrics-review

  Use when the user wants a feature's analytics or instrumentation reviewed: event taxonomy, data accuracy, tracking gaps, dashboard usefulness, or are we tracking this right.

• migration-plan

  Use when the user needs a plan to migrate a database, API, data format, or infrastructure safely, with staging, validation, and rollback, rather than a single schema changeset.

• mobile-dev

  Use when the work is a mobile app in Flutter, React Native, Android (Kotlin), or iOS: architecture, state management, navigation, platform channels, widget or device tests, or app store readiness.

• monitoring-plan

  Use when the user needs observability for a service or feature: a monitoring plan, metrics, alerts, dashboards, SLOs, logging, or tracing.

• onboarding-doc

  Use when the user wants an onboarding guide for a new team member on a service, domain, or codebase: architecture, key workflows, local setup, and tribal knowledge.

• opportunity-assessment

  Use when the user is deciding whether a feature or product idea is worth building: should we build this, is this worth it, cost and benefit, risk, strategic fit, or prioritization.

• performance-review

  Use when a feature or PR needs a performance and reliability review, or the user reports something slow: latency, throughput, hot paths, query patterns, caching, concurrency, or load testing.

• postmortem

  Use only when the user explicitly asks for a postmortem, RCA, or incident review after an incident is resolved.

• prd

  Use when the user wants to write a PRD, product spec, or feature brief, capture requirements, or update an existing PRD to match design or implementation changes.

• release-notes

  Use only when the user explicitly asks for release notes, a changelog, or a summary of what shipped from a set of PRs, commits, or features.

• repo-conventions

  Use when the user wants a repository's architecture, API style, or testing conventions written down or updated, or asks which conventions to follow in a repository.

• runbook

  Use when the user wants an operational runbook, operations or on-call guide, or playbook for deploying, scaling, recovering, or operating a service.

• search-design

  Use when the user is designing search: Elasticsearch or Typesense indexes, mappings, analyzers, relevance tuning, autocomplete, faceting, full-text search, or syncing search from the source of truth.

• security-review

  Use when a feature or PR needs a security review or lightweight threat model: auth, data access, injection, abuse cases, privacy, secrets, logging, or is this safe.

• spec-panel

  Use when a spec, PRD, BRD, design doc, or RFC needs expert review before implementation starts: review this spec, is it ready to build, any gaps, am I missing anything, spec smells, or a devil's advocate pass.

• spec-to-impl

  Use when the user provides a spec, PRD, BRD, API spec, or analysis document and wants it implemented end to end: implement this spec, build this from the PRD, or produce code, tests, migrations, and docs together. Tracker tickets for a team belong to ticket-breakdown.

• sprint-retro

  Use only when the user explicitly asks to run a sprint retrospective or team reflection on what went well and what to change.

• stakeholder-update

  Use only when the user explicitly asks for a stakeholder, exec, investor, or weekly status update covering progress, risks, and decisions needed.

• tech-debt-assessment

  Use when the user wants technical debt inventoried or prioritized: tech debt, code health, refactoring priorities, or a cleanup roadmap.

• temporal-workflow

  Use when the work involves Temporal in Java: workflows, activities, SAGA compensation, long-running or durable orchestration, config-driven state machines, retries, signals, queries, versioning, child workflows, or continue-as-new.

• test-plan

  Use when the user wants a test plan, QA plan, or release checklist, or asks how a feature, PR, or release should be tested.

• ticket-breakdown

  Use when the user wants a PRD or design doc broken into tracker-ready epics and tickets for a team to pick up: work breakdown, Jira tickets, or Linear issues, rather than implemented now.

• ui-design

  Use when the user wants UI or UX design artifacts: design the UI for a spec, wireframes, screens, layouts, component specs, design tokens, a design system, typography, color, or spacing systems, for web, Flutter, React Native, or AngularJS.

• user-flow

  Use when the user wants user journeys mapped through a feature or product: user flow, user journey, flow diagram, decision points, friction, error states, or edge cases.

• ux-review

  Use when the user wants a UI design or implementation evaluated for usability: UX review, heuristic evaluation, accessibility audit, cognitive walkthrough, or is this usable.

• verify-impl

  Use when a completed implementation needs live verification: test the implementation, verify this works, run API tests, check the database, test the UI with Playwright, smoke or sanity test, or any post-build check beyond unit tests.

Hooks (3)

• PreToolUse

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/pre-bash.py

• PreToolUse

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/pre-edit-guard.py

• PostToolUse

  python3 ${CLAUDE_PLUGIN_ROOT}/hooks/post-edit-format.py

Similar plugins