Skill Claude CodeCodex
This skill should be used when the user asks to "create a product roadmap", "prioritize the backlog", "define product vision", "write user stories", "do product management", "product strategy", "release planning", "stakeholder management", "feasibility assessment", "customer journey", "product metrics", "OKRs", "value…
Skill Claude CodeCodex
This skill should be used when the user asks to "design a system", "create an architecture", "write an ADR", "do solution architecture", "architect a solution", "review my architecture", "SA task", "stakeholder analysis", "trade-off analysis", "C4 diagram", "non-functional requirements", "NFR", "architecture decision…
Skill Claude CodeCodex
This skill should be used when the user asks to "create a test plan", "test strategy", "write test cases", "test automation", "acceptance testing", "quality assurance", "QA", "testing approach", "risk-based testing", "regression testing", "performance testing", "test management", or mentions testing work. Guides…
Plugin Claude Code
Intelligent skill management and retrieval for Claude Code.
Command
Rebuild the skills ontology from source skill files.
Command
Visualize the skills ontology as a graph.
Command
Analyze skills usage patterns from the ontology usage log.
Hook
Runs after a tool call finishes for Write, Edit and Skill tool calls, executing ontology_sync.js and ontology_track_skill.js via node (2 commands). From baodq97/open-plugin.
Plugin Claude Code
Reusable software engineering workflow skills — goal structuring, task decomposition, planning, and execution patterns for Claude Code agents across any codebase.
Skill Claude CodeCodex
Decompose a domain into bounded contexts, aggregates, entities, value objects, and domain events with ubiquitous-language naming, mapping bounded contexts to candidate microservice boundaries. Use whenever the user wants to decompose a domain, split a system into bounded contexts, identify aggregates / value objects /…
Skill Claude CodeCodex
Structure a clear, verifiable /goal from rough user input through guided interview. Use this skill whenever the user says "define goal", "tạo goal", "/goal", "goal cho task này", "I want to do X" (where X is complex/multi-step), "structure this task", "make this into a goal", or when you detect the user has a vague…
Plugin Claude Code
V-Bounce AI-Native SDLC Orchestrator v5.1 — Agent-first architecture with unified TDD, per-phase specialized QG agents, mixed-model assignment, tech-aware context injection, explicit contracts, shared workspace, state management, and multi-layer quality assurance for complete software development lifecycle.
Agent
Use this agent when deployment plans, rollback strategies, and pre/post-deployment checklists need to be created. Handles staging and production deployments with proper approvals. STANDARD bounce time. Trigger this agent during the Deployment phase after testing is approved. Context: Testing phase has been approved…
Agent
Use this agent when the user needs to create or update technical designs for approved requirements. This includes architecture design, API design, data model design, security threat modeling (STRIDE), Architecture Decision Records (ADRs), and design-time test specifications. Trigger this agent during the Design phase.…
Agent
Unified TDD agent: writes tests from contracts (RED), implements code (GREEN), executes and verifies (REFACTOR). Self-contained execution loop with max 3 iterations. Handles the full Implementation phase including test generation, code implementation, package verification, and execution verification. Trigger this…
Agent
Use this agent to capture knowledge from AI-assisted development cycles. Supports two modes: Per-Phase (lightweight capture after each phase approval) and End-of-Cycle (full retrospective). Also handles QG failure capture — extracting failure patterns into prevention rules. Context: A phase has just been approved and…
Agent
Use this agent to validate Deployment phase output against domain-specific quality criteria. Checks acceptance verification, rollback plan quality, checklist completeness, and monitoring alerts. Returns PASS/WARN/FAIL verdict. Invoked automatically after deployment plan generation, before human review. Context…
Agent
Use this agent to validate Design phase output against domain-specific quality criteria. Checks architecture consistency, STRIDE security coverage, API-story mapping, design-time test specifications, ADR presence, and data model integrity. Returns PASS/WARN/FAIL verdict. Invoked automatically after design generation…
Agent
Use this agent to validate Implementation phase output against domain-specific quality criteria. Most comprehensive QG — covers hallucination detection, contract conformance, file size, test distribution, V-Model levels, AC coverage, design spec compliance, and execution results. Returns PASS/WARN/FAIL verdict.…
Agent
Use this agent to validate Requirements phase output against domain-specific quality criteria. Checks ambiguity scoring, AC testability, NFR completeness, story independence (INVEST), and traceability coverage. Returns PASS/WARN/FAIL verdict. Invoked automatically after requirements generation, before human review.…
Agent
Use this agent when you need to parse a PRD (Product Requirements Document) and produce structured requirements artifacts including user stories, acceptance criteria in GIVEN-WHEN-THEN format, non-functional requirements, test skeletons, ambiguity scores, and traceability matrices. This agent is active during the…
Agent
Use this agent when implementation artifacts need to be reviewed for correctness, security, and AI hallucinations. PRIMARY mission: catch AI hallucinations (fake packages, invalid APIs, invented patterns). SECONDARY: security audit, code quality, logic correctness, performance. Produces weighted scored review reports…
Agent
DEPRECATED in v5.1 — merged into implementation-engineer.md. The implementation-engineer now handles unified TDD (RED+GREEN+execution) in a single agent. This file is kept for reference only. Do NOT dispatch this agent. Previously: Use this agent when comprehensive test suites need to be generated from contracts and…
Agent
Use this agent to maintain a live traceability matrix that evolves across every SDLC phase. Supports four modes: Initialize (from requirements), Update (extend with design/implementation/testing), Validate (check completeness), and Impact Analysis (trace effects of changes). Invoked at every phase transition. Context…