tranhieutt/software_development_department

Software Development Department

This repository also configures its own agents. See what software_development_department tells them →

72Stars on the repository
155Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

tranhieutt/software_development_department

Skill Claude Code

Analyzes existing project artifacts to detect development stage, identify documentation gaps, and recommend next steps. Use when starting a new session on an existing project, or when the user mentions project analysis, stage detection, or gap analysis.

not rated 72 4mo ago A 50 tokens original MIT

prototype

74

tranhieutt/software_development_department

Skill Claude Code

Executes a rapid prototyping workflow that skips normal standards to quickly validate a product concept or core mechanic, producing throwaway code and a prototype report. Use when the user wants to quickly test an idea or mentions prototyping, proof of concept, or MVP spike.

not rated 72 4mo ago A 55 tokens original MIT

tranhieutt/software_development_department

Skill Claude Code

Provides Radix UI patterns for building accessible design systems with headless components, theming, and compound component architecture. Use when building UI with Radix UI primitives or when the user mentions Radix UI, headless components, or accessible component libraries.

not rated 72 4mo ago A 56 tokens original MIT

rag-engineer

76

tranhieutt/software_development_department

Skill Claude Code

Provides Retrieval-Augmented Generation patterns covering embedding models, vector databases, chunking strategies, and retrieval optimization. Use when building RAG systems or when the user mentions RAG, vector search, embeddings, or retrieval-augmented generation.

not rated 72 4mo ago A 51 tokens copy · 89% MIT

tranhieutt/software_development_department

Skill Claude Code

Processes code review feedback systematically by classifying findings, deciding fix or reject with evidence, applying approved fixes, and re-verifying before marking comments resolved.

not rated 72 4mo ago A 35 tokens original MIT

release-checklist

78

tranhieutt/software_development_department

Skill Claude Code

Generates a comprehensive pre-release validation checklist for software versions covering build verification, deployment readiness, and release risk. Use when preparing to release a product version or when the user mentions release checklist or pre-release validation.

not rated 72 4mo ago A 46 tokens original MIT

resume-from

79

tranhieutt/software_development_department

Skill Claude Code

Restores cognitive state from an atomic checkpoint in .tasks/checkpoints/[taskid].md, enabling instant recovery at the exact point of failure without re-running the full task.

not rated 72 4mo ago A 38 tokens original MIT

retrospective

80

tranhieutt/software_development_department

Skill Claude Code

Generates a sprint or milestone retrospective analyzing completed work, velocity, blockers, and patterns to produce actionable insights. Use when ending a sprint or milestone, or when the user mentions retrospective, retro, or sprint review.

not rated 72 4mo ago A 47 tokens original MIT

reverse-document

81

tranhieutt/software_development_department

Skill Claude Code

Generates missing design or architecture documentation by working backwards from existing code or prototypes. Use when documentation is missing for existing code or when the user mentions documenting existing implementation or reverse engineering docs.

not rated 72 4mo ago A 40 tokens original MIT

review-spec

82

tranhieutt/software_development_department

Skill Claude Code

Reviews a product, technical, API, UI, or implementation spec for completeness, testability, architectural fit, and readiness before planning or implementation.

not rated 72 4mo ago A 32 tokens original MIT

save-state

83

tranhieutt/software_development_department

Skill Claude Code

Saves current working context to production/session-state/active.md AND writes an atomic per-task checkpoint to .tasks/checkpoints/[taskid].md. Run before any major context reset, when context usage exceeds 60%, or when ending a work session.

not rated 72 4mo ago A 54 tokens original MIT

scope-check

84

tranhieutt/software_development_department

Skill Claude Code

Analyzes a feature or sprint for scope creep by comparing current scope against the original plan, flagging additions and recommending cuts. Use when a sprint feels bloated or when the user mentions scope creep, scope check, or feature bloat.

not rated 72 4mo ago A 51 tokens original MIT

security-audit

85

tranhieutt/software_development_department

Skill Claude Code

Conducts a comprehensive security audit covering web application vulnerabilities, API security, OWASP Top 10, and security hardening recommendations. Use when auditing a codebase for security or when the user mentions security audit, penetration testing, or vulnerability scan.

not rated 72 4mo ago A 53 tokens original MIT

senior-frontend

86

tranhieutt/software_development_department

Skill Claude Code

Next.js App Router specific patterns — Server Components, Client Components boundary, parallel fetching, bundle analysis, a11y. Use ONLY for Next.js 13+ App Router projects. For generic React/Vue patterns, use frontend-patterns instead.

not rated 72 4mo ago A 56 tokens original MIT

shadcn

87

tranhieutt/software_development_department

Skill Claude Code

Provides shadcn/ui component integration patterns, theming, and design system composition for React projects. Use when working with shadcn/ui or when the user mentions shadcn, shadcn/ui, or building a component library.

not rated 72 4mo ago A 52 tokens copy · 84% MIT

tranhieutt/software_development_department

Skill Claude Code

Generate a polished internal technical HTML document following the SDD visual design system. Use when asked to "tạo tài liệu kỹ thuật", "generate HTML reference", "visual report", "technical doc", "tạo report HTML", "làm tài liệu ná»™i bá»™", or when asked to document a subsystem (hooks, memory, agents…

not rated 72 4mo ago A 115 tokens original MIT

tranhieutt/software_development_department

Skill Claude Code

Grounds framework, library, API, and platform-specific technical decisions in official documentation before implementation. Use when current docs, version-specific behavior, best practices, deprecations, or external API correctness matter.

not rated 72 4mo ago A 45 tokens original MIT

spec-evolution

91

tranhieutt/software_development_department

Skill Claude Code

Resolves mismatches between an approved spec and implementation reality by proposing controlled spec changes before code or plan changes continue.

not rated 72 4mo ago A 27 tokens original MIT

springboot-patterns

92

tranhieutt/software_development_department

Skill Claude Code

Provides Spring Boot architecture patterns for REST APIs, layered services, JPA data access, caching, async processing, and logging. Use when working with Java Spring Boot files (.java, pom.xml) or when the user mentions Spring Boot, Spring Framework, or Java backend.

not rated 72 4mo ago A 59 tokens copy · 81% MIT

sprint-plan

93

tranhieutt/software_development_department

Skill Claude Code

Generates or updates sprint plans with task breakdowns, capacity estimates, dependencies, and risk flags based on milestone goals and past velocity. Use when starting a new sprint, updating sprint progress, or checking sprint status.

not rated 72 4mo ago A 47 tokens original MIT

tranhieutt/software_development_department

Skill Claude Code

Provides SQL optimization patterns for query performance, indexing strategies, schema design, and database tuning. Use when optimizing slow queries, designing indexes, or tuning database performance.

not rated 72 4mo ago A 38 tokens original MIT

start

95

tranhieutt/software_development_department

Skill Claude Code

Guides first-time onboarding by asking where the user is in their project journey, then routing them to the right workflow. Use at the beginning of a new session without context, or when the user runs /start for the first time.

not rated 72 4mo ago A 49 tokens original MIT

style-review

96

tranhieutt/software_development_department

Skill Claude Code

Reviews Markdown prose against the pinned agent-style v0.3.5 rules and optionally writes a polished copy beside the source. Use for specs, ADRs, PR bodies, release notes, and technical docs when prose quality or evidence discipline matters.

not rated 72 4mo ago A 52 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: