.claude/skills/team-feature/SKILL.md
Orchestrates a cross-functional feature team of product-manager, ux-designer, frontend-developer, backend-developer, and qa-tester to deliver a complete feature from specification to tested implementation. Use when a feature requires full-stack coordinated delivery.
npx skillsauth add tranhieutt/software_development_department team-featureInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When this skill is invoked, orchestrate the feature team through a structured delivery pipeline.
Decision Points: At each phase transition, use AskUserQuestion to present
the user with the subagent's proposals as selectable options. Write the agent's
full analysis in conversation, then capture the decision with concise labels.
The user must approve before moving to the next phase.
Use the Task tool to spawn each team member as a subagent:
subagent_type: product-managersubagent_type: ux-designersubagent_type: backend-developersubagent_type: frontend-developersubagent_type: qa-testerAlways provide full context in each agent's prompt (feature requirements, existing patterns, API conventions). Launch independent agents in parallel where the pipeline allows (e.g., backend + UX design can proceed in parallel after spec is approved).
Delegate to product-manager:
Launch in parallel:
Both must complete before Phase 3.
Use AskUserQuestion to get approval on:
Iterate until approved.
Once backend is done, frontend-developer integrates with real API.
Delegate to qa-tester:
/gate-check)A summary covering: acceptance criteria coverage, API status, UI status, test results, and any outstanding items.
testing
Generates high-fidelity architecture diagrams, sequence flows, and component maps for SDD projects. Use when finalizing a design phase, documenting system architecture, or visualizing agentic workflows. Default style: Style 6 (Claude Official).
data-ai
Provides vector database and semantic search patterns for Pinecone, Weaviate, Qdrant, Milvus, and pgvector in RAG and recommendation systems. Use when implementing vector search or when the user mentions vector database, semantic search, embeddings, or similarity search.
development
Updates docs/technical/CODEMAP.md by scanning the current codebase structure. Run after a significant feature merge, refactor, or when CODEMAP feels stale.
development
Unlocks the codebase after a release freeze or incident freeze period to resume normal development. Use when a freeze period ends or when the user mentions unfreezing or lifting the code freeze.