Skill Claude CodeCodex
PetSwipe validation workflow for choosing the smallest reliable checks for frontend, backend, infra, docs, and mixed changes. Use when a task needs a concrete validation plan or when the repo's pre-existing lint or type issues make broad validation noisy.
Agent Claude Code
Use proactively for Express API work, TypeORM entity changes, route/controller/service coherence, migrations, Swagger exposure, and backend runtime behavior.
Agent Claude Code
Use proactively for README, ARCHITECTURE, deployment docs, and repo-facing documentation updates that must stay aligned with the real code and infrastructure.
Agent Claude Code
Use proactively for frontend page work, responsive layout issues, chart behavior, navigation polish, and visual QA inside frontend/pages and frontend/components.
Agent Claude Code
Use proactively for Kubernetes, Terraform, production Docker Compose, release readiness, deployment scripts, preflight flows, and operator-facing documentation.
Agent Claude Code
Use proactively for code review, regression hunting, validation gaps, deployment impact analysis, and documentation drift checks. Findings should come first.
Settings file Claude Code
Agent settings configuring permissions.
Instructions file CodexOpenCode
Instructions for hoangsonww/PetSwipe-Match-App, covering agents.md -- petswipe flywheel operating manual, rule 0: override prerogative, rule 1: core safety rules, project overview and repo map.
Instructions file
Instructions for hoangsonww/PetSwipe-Match-App, covering petswipe claude code memory, purpose, working style, repo map and commands that matter.
Skill Claude CodeCodex
Backend-local workflow for health endpoints, readiness behavior, Swagger/OpenAPI exposure, and runtime contract changes in PetSwipe. Use when backend work touches backend/src/app.ts, startup behavior, docs endpoints, or deployment-sensitive runtime behavior.
Skill Claude CodeCodex
Docs-local workflow for keeping PetSwipe product pages, deployment docs, architecture docs, and operational claims aligned with the current repository. Use when working inside docs or when multiple docs need to be updated together.
Skill Claude CodeCodex
Frontend-local workflow for PetSwipe chart overflow, tooltip, dark mode text, clipping, and responsive layout issues inside frontend pages and shared chart components. Use when working in frontend and the issue is specifically about charts or mobile layout behavior.
Skill Claude CodeCodex
Frontend-local workflow for navbar behavior, route ordering, icon-only links, mobile menu UX, and page discoverability in PetSwipe. Use when working in frontend and the task touches Navbar, route links, or mobile navigation.
Skill Claude CodeCodex
Kubernetes-local workflow for manifest hardening, renderability, overlays, quotas, network policies, and rollout safety in PetSwipe. Use when working inside k8s and the task is specifically about manifest correctness or production posture.
Skill Claude CodeCodex
Terraform-local workflow for backend.hcl, tfvars examples, operator bootstrap, and plan/apply readiness in PetSwipe. Use when working inside terraform and the task is about making the Terraform workflow clearer, safer, or more deployable.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Scaffold a new Forge subagent (planner/architect/executor/reviewer/debugger/memory-style).
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Scaffold a new model provider for Forge — class, registry wiring, providerEnum entry, local-catalog classification, router check, and a unit test with mocked transport.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Scaffold a new Forge tool end-to-end — implementation, registration, permission/risk metadata, sandbox routing, and a unit test.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or emitting wrong tool calls.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Translate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan. Use after the plan has converged.
hoangsonww/Forge-Agentic-Coding-CLI
Skill Claude CodeCodex
Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.