Claude Skills by duc01226

[Category] Use when defining the standard skill description pattern.

[Architecture] Use when designing solution architecture — backend, frontend, data & consistency, integration & APIs, deployment, monitoring, testing, code quality.

[Architecture] Use when auditing the ENTIRE project architecture and production readiness in one pass; bundles architecture-review + scalability + production-readiness into one health report.

[Code Quality] Use when reviewing architecture compliance — layers, messaging, service boundaries, CQRS, repos, entity events, data/consistency/tenancy boundaries.

[Architecture] Use when grading architecture and scalability — build/CI scale, distributed-monolith risk, module isolation, coupling, horizontal scaling, clean architecture, observability.

[Code Quality] Use when reviewing artifact quality before handoff. Flag: --type={pbi|story|spec-tests|design}.

[Utilities] Use when answering a technical or architectural question.

[Content] Use when brainstorming as a PO/BA — ideation for problem-solving, new products, feature enhancement, or outcome-roadmap framing. Flag: --mode={roadmap|scope}.

[Git] Use when comparing branches, analyzing git diffs, or reviewing what changed between two refs.

[Project Management] Use when creating user stories, writing acceptance criteria, analyzing requirements, or mapping business processes.

[Content] Use when evaluating business idea viability — Business Model Canvas, financial projections, risk matrix, go-to-market, execution plan.

[Documentation] Use when generating or updating changelog entries.

[Code Quality] Use when looping /changes-review + /fix recursively over a fixed diff scope until one full pass clears the severity bar.

[Code Quality] Use when reviewing current changes, staged or unstaged diffs, or branch-to-branch diffs.

[Utilities] Use when saving analysis context to a checkpoint file for recovery.

[Utilities] Use when asking for the claudeKit usage guide.

[Utilities] Use when setting up, configuring, or troubleshooting the Claude Code CLI and its features.

[Documentation] Use when initializing, updating, or refactoring CLAUDE.md from project-config and codebase scans.

[Code Quality] Use when evaluating review feedback, requesting a targeted code-quality review, or verifying completion claims.

[Code Quality] Use when simplifying code for clarity, consistency, and maintainability while preserving behavior.

[Utilities] Use when setting the coding experience level that tailors explanations.

[Git] Use when asked to commit, stage and commit, or save changes. Flag: --push also pushes to remote.

[Utilities] Use when compressing context to reduce token usage.

[Utilities] Use when managing context window usage, compressing long sessions, or optimizing tokens.

[Utilities] Use when loading project context for the current session.

[Content] Use when writing high-converting copy for marketing, social, landing pages, email, or product descriptions.

[Content] Use when building course material — Bloom objectives, modules, lessons, exercises, assessments.

[AI & Tools] Use when creating, verifying, or enhancing Claude Code custom agent files.

[Utilities] Use when invoking, listing, saving, updating, or deleting a PROJECT-SPECIFIC saved prompt (playbook / recipe / runbook). Subcommands: list | <free-text> | save | update | delete.

[DevOps] Use when running or creating database migrations.

[Fix & Debug] Use when finding a bug''s root cause — reproduce, trace end-to-start, test hypotheses, pinpoint the defect before any fix.

[Research] Use when deeply researching the top sources surfaced by web-research.

[Documentation] Use when generating a demo guide, demo script, or sprint-demo walkthrough covering user stories and their test cases.

[Project Management] Use when mapping or visualizing feature dependencies between modules, services, and work items.

[Project Management] Use when creating UI/UX design specs from requirements, PBIs, or stories. Flag: --mode=wireframe converts sketches into structured specs.

[Design] Use when creating or describing a UI design. Flags: --mode={fast|good|describe|screenshot|video} (default fast), --lane={product|marketing} (default product).

[DevOps] Use when deploying to Cloudflare (Workers, R2, D1, KV, Pages), Docker, or GCP (Compute Engine, GKE, Cloud Run).

[Documentation] Use when initializing project reference docs via hook + scan skills.

[Documentation] Use when finding technical documentation for a library, framework, repository, or implementation topic.

[Documentation] Use when updating impacted documentation after code, spec, or test changes.

[Code Quality] Use when enhancing documentation, adding code comments, creating API docs, or updating READMEs.

[Document Processing] Use when converting Word DOCX files to Markdown with GFM support.

[Architecture] Use when analyzing the business domain — bounded contexts, aggregates, entities, ERD, domain events, cross-context integration.

[DDD Quality] Use when reviewing domain entities and value objects for DDD design quality.

[Code Quality] Use when validating a PBI against Definition of Ready before grooming.

[User-Invoked] Use ONLY when the user explicitly types /dual-ai — fans one prompt or workflow out to parallel Claude Code + Codex CLI sessions. NEVER auto-activate.

[Testing] Use when generating, updating, or maintaining E2E tests from recordings, specs, or code changes.

[Planning] Use when calibrating estimates against actual code, diff, PR scope, and developer time.

[Utilities] Use when visualizing workflows, architectures, or concepts as Excalidraw diagram JSON.

[Testing] Use when reviewing a running user experience or observable output (UI, API, CLI, service) — run it locally, drive it end to end like a user, gate on runtime/console logs and captured screens, set a baseline, or adjudicate a regression. Flag: --rounds=N (default 3; 0 = report-only).