makifbaysal
UserLocal-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or API models, all on your own Mac
Categories
Indexed Skills (55)
api-contract-openapi
Use when adding or changing a Go API endpoint's request/response shape - keep the OpenAPI/Swagger contract accurate, evolve additively, and update every consumer on a breaking change
board-comment-style
Write board comments the way a colleague does — lead with the finding, a few lines, no preamble or process narration
ci-cd-pipeline-authoring
Use when a repository needs CI/CD - author GitHub Actions workflows so TaskTrooper's pipeline auto-detects your validate/build/test jobs and stage/preprod/prod deploys, and so trigger_release can dispatch the production deploy
cloud-deploy-gcp-aws
Use when a web/frontend app needs a cloud deploy - GitHub Actions to Cloud Run/App Runner for SSR or GCS+CDN/Firebase and S3+CloudFront for static, with build-time env and cache invalidation
deploy-templates
Author a repository's deploy from the built-in provider recipes (GCP, AWS, Vercel, Fly) instead of hand-rolling a workflow, and make it verifiable and reversible.
fiber-rest-api
Use when adding or changing a Go HTTP endpoint with Fiber - thin handlers, centralized domain-error-to-status mapping, boundary validation, and neighbor-consistent middleware
incremental-commits
Break work into bite-sized steps with their own test cycle and commit each one
java-oop-solid-design
Use when modelling a rich domain in Java - SOLID principles, encapsulated entities that enforce their own invariants, and value objects over primitives
java-persistence
Use when a Java service reads or writes the database - JPA/Hibernate and Panache/Spring Data mapping, transaction boundaries, and avoiding N+1 and entity-over-the-wire leaks
java-testing-junit-mockito
Use when writing tests for Java (Quarkus or Spring) code - JUnit 5 structure, Mockito for collaborators, and framework-native integration tests, test-first
java-vs-go-decision
Use when starting a backend task that could be built in either language - decide Go vs Java (Quarkus/Spring) from the task's shape and the repository's existing stack
local-project-context
Use when running any task in this system - explains the local (non-CI) execution environment, the task workspace, and the exploration/verification tools available
mockery-suite-tests
Use when writing Go tests that need mocks or cover multiple cases - generate mocks with Mockery v3 (never hand-written), and structure tests as table-driven testify suites
performance-awareness
Use when working any board task - explains how your performance score moves and how to protect it through the review, QA, and UAT gates
postgres-migrations
Use when changing the database schema in a Go service - ship numbered up/down migration pairs, never edit an applied migration, and keep down migrations truly reversible
quarkus-service-architecture
Use when building or extending a Java service with Quarkus - layered architecture, JAX-RS resources, CDI beans, Panache persistence, and native-friendly patterns
root-cause-debugging
Systematic debugging - find the root cause through four phases before attempting any fix
spring-boot-fallback
Use when Java is chosen but Quarkus does not fit - build the service with Spring Boot using the same clean layering, only when a required library lacks a Quarkus extension or the repo already standardizes on Spring
stepwise-task-execution
Use when you pick up any implementation task - understand it fully, break it into small steps, and execute each with its own test and commit before handoff
tdd-workflow
Test-driven development - write the failing test first, watch it fail, write minimal code to pass
verify-before-done
Never claim done or move a task forward without fresh verification evidence from this run
zerolog-observability
Use when adding logging to Go code - structured zerolog with fields (not string interpolation), correct levels, request correlation, and no secrets or double-logging
api-client-integration
Use when a component talks to the backend - go through the typed api client, type every response, and handle loading, success, and error states explicitly
component-composition
Use when building or changing any web UI - compose from the shared atomic component library (atom/molecule/organism/template/page), reuse before building, and keep components presentation-only
component-testing
Use when writing or changing any React component - React Testing Library tests are behavior-focused (byRole first), use user-event, assert on accessible output, one behavior per test, and run in npm test
vite-tailwind-radix
Use when styling any web UI - style with Tailwind utility classes and design tokens, avoid custom CSS, and build on the existing Radix/shadcn primitives instead of hand-rolling
android-compose-patterns
Use when building native Android with Jetpack Compose - stateless composables, state hoisting, ViewModel-owned state, atomic components, and Material theming over hardcoded values
app-store-deploy
Use when a mobile app needs a release pipeline - fastlane GitHub Actions to TestFlight (iOS) and Play internal track (Android), with code signing and the release naming that maps to TaskTrooper's prod deploy
flutter-atomic-components
Use when adding or reusing Flutter UI - organize widgets as atoms, molecules, and organisms in a shared library and never hand-roll a component that already exists
flutter-testing
Use when testing Flutter code - unit tests for logic, widget tests for UI behavior, golden tests for appearance, test-first
flutter-widget-architecture
Use when building Flutter screens - compose small stateless widgets, keep layout declarative, separate presentation from business logic, and use the theme not hardcoded styles
native-vs-flutter-decision
Use when starting a mobile task that could be Flutter or native - decide from the existing app, platform-specific needs, and the analiz task
swiftui-patterns
Use when building native iOS with SwiftUI - small composable views, observable state models, atomic components, and system styling over hardcoded values
acceptance-criteria-gwt
Use when writing acceptance criteria for a task - express each as an observable Given/When/Then that QA can execute, including negative cases
board-column-flow
Use when moving tasks or reporting status - the kanban column semantics, which columns are human/architect/QA gates, and where the PM actually acts
implementation-task-spec
Use when you create an implementation board task directly - the required fields, one-role-one-deliverable rule, and dependency ordering
post-analiz-handoff
Use after the system-architect finishes an analiz - understand the human approval gate and review the implementation tasks the architect creates once the human approves
analiz-task-spec
How to write an analiz board task
pm-uat-review
How to conduct PM UAT review
codebase-indexing-tools
Code search and indexing tools - explore before changing
go-hexagonal-architecture
Hexagonal architecture in Go - domain at the center, ports as interfaces, adapters at the edge
accessibility-basics
Use on every UI change - semantic HTML, labels for controls, keyboard-navigable dialogs/menus, visible focus, and never color as the only signal
react-typescript-patterns
Use when writing React + TypeScript components - functional components, explicit typed props, derived state over effects, and no any/unsafe casts
routing-state
Use when adding routes or deciding where state lives - carry resource ids and navigation-surviving state in the URL, keep route components thin, and lift shared state to a hook not a global store
analiz-gate
Use when deciding whether a request needs an analiz task before implementation - the conditions that require the architect's analysis versus going straight to implementation
answer-workspace-questions
Use when the stakeholder asks a factual or status question about the workspace - call the matching read tool and answer conversationally, without creating tasks or asking for approval
backlog-prioritization
Use when ordering board tasks - score with RICE, apply the fixed overrides (bugs, unblockers, stakeholder urgency), and place items in backlog vs todo accordingly
plan-approval-and-kickoff
Present plan to stakeholder for approval, then move approved tasks to todo
release-notes-writing
Use when a batch of work reaches done/released - write user-facing release notes grouped into New, Fixed, and Changed, in outcome language with task references
analiz-task-workflow
How to handle a type analiz task assigned to you
pm-as-solo-orchestrator
How PM behaves as the sole orchestration agent
mobile-navigation
Mobile navigation patterns
mobile-ui-ux
Mobile UI/UX standards
offline-sync
Offline resilience and sync
platform-permissions
Platform permission handling
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.