Menu
SkillsMP has collected 42 skills from jb-612/tirvi. Open a skill to review its source and details.
Showing 40 of 42 collected skills.
DDD 7-Layer scaffold before TDD. Transforms approved user stories, acceptance criteria, functional design, and feature task breakdown into a production-grade, layered code skeleton — folders, interfaces, aggregates, value objects, domain events, test…
3-round multi-tier design review with 6 specialist reviewers (including HLD compliance), adversary challenge, cross-debate, and synthesis. Use during design pipeline stages 5/7 or standalone before TDD build.
Run design + review + TDD for 2-4 coupled features concurrently via native teams. Each feature gets a dedicated fresh-context designer + runner; team-lead brokers coupling decisions in real-time and runs a consolidated cross-feature review before the user…
Clean-slate architecture research for brownfield modernization. Evaluates open-source alternatives, design patterns, and build-vs-adopt decisions using multi-agent research teams with adversary debate. Part of the Brownfield Refactoring Toolkit.
Multi-perspective research with parallel agents — web research, codebase analysis, graph queries, and cost/risk analysis — synthesized into a structured report for design decisions.
11-stage pipeline — HLD-driven design, PRD-driven stories via meeting room brainstorm, 2-round review, HLD-traced task breakdown, user approval. ACM graph-compatible traceability.
Cross-module boundary tests between layers
Lightweight refactoring design skill — scaffolds workitems, fills design.md and tasks.md from existing research, single HITL gate. Skips user stories and multi-round review since behavior is already pinned by characterization tests.
Software/architecture design pipeline. Runs when @biz-functional-design has already produced stories + test plans for a feature. Extracted from @design-pipeline Stages 2, 2.5, 4, 4b, 5–11; skips PRD-driven story generation. ACM graph-compatible traceability.
Break a feature design into atomic, testable tasks with estimates, dependencies, and test paths. Reusable standalone skill invoked by @design-pipeline or independently.
Flutter/Dart TDD micro-cycle engine. Widget tests, Riverpod provider tests, golden tests, 3-agent separation, traceability updates.
Go-native TDD micro-cycle engine. Table-driven tests, *_test.go co-located, 3-agent separation, gocyclo CC≤5, traceability updates.
TDD router — validates prerequisites, detects language from task file paths, delegates to @tdd-go or @tdd-flutter. Use --accept-all to skip mode selection in the delegated skill.
Write Chicago-school functional, smoke, and regression test CODE from STD test definitions in traceability.yaml. Tests through public APIs with real collaborators, mocking only at system boundaries via shared fake registry.
Generate canonical fake implementations (working in-memory test doubles) from port interfaces in the hexagonal architecture. Maintains a shared fake registry in pkg/testutil/fakes/ that all test-writing skills import from.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or…
Code review for DDD 7L scaffold output. Skips Phase 1 quality gates (intentional NotImplemented failures expected) and runs design-aware Phase 2 review. Invoked at each gate during @ddd-7l-scaffold (after L1+L2, after L3, after L4+L5, after L6+L7). Outputs…
Produce epic-level Software Test Design (STD.md) with functional, smoke, regression tests and E2E anchors, plus feature-test traceability YAML.
Business functional design from PRD and market research — feature-by-feature user stories, DDD alignment, functional/behavioural test plans, ontology YAMLs, multi-agent review, adversarial loop, deferred-finding Git issues. Long-running; stops at design phase…
Cross-layer traceability queries. Answer "which tests cover X?", "what implements Y?", "find untested paths".
Adversarial testing loop inspired by autoresearch. Generate adversarial cases, run against agent, evaluate, accumulate findings.
Write dual-lens characterization tests — pinning code behavior AND validating product intent. Reads reverse PRD + behavioral spec + ACM graph to produce tests that catch both regressions and intent violations. Part of the Brownfield Refactoring Toolkit.
2-phase code review — Phase 1 automated quality gates, Phase 2 three-agent parallel manual review with master synthesis. Use when reviewing PRs, inspecting code, or auditing a module.
Conventional commits with traceability. Enforces commit format, runs pre-commit validation, and handles protected path HITL gate. Extracted from feature-completion.
Visualise the chain-of-thought of a design-pipeline run as light Mermaid diagrams. Reads a feature workitem's meeting-room + review-r1/r2/r3 markdown and emits 6 views (review DAG, meeting-room convergence, finding timelines, graveyard of overruled claims,…
Creates and updates Mermaid diagrams for architecture, workflows, and data flows. Auto-invoked during planning for architecture diagrams.
Create, update, classify, and archive docs in docs/. Enforces naming, versioning, folder placement, and lifecycle rules.
Post-code-review validation before commit. Lighter than @code-review — assumes automated gates + manual review already passed. Use when @code-review is done and tasks.md shows 100% complete.
Info-only answer lane. No artifact, no review, no design. Use for questions where the user wants information and does not intend to build or change anything yet. Offers an opt-in to save the exchange as an idea for @ideation.
Short design cycle for single-file / small-scope bug fixes. Skips @design-pipeline and @design-review (no meeting room, no adversary, no 6-specialist R1), but keeps a 1-page impact note, a 2-reviewer light check, @test-design scoped to the bug, /tdd,…
Produce a short idea memo for later research or design. Lightweight front door — no review ceremony, no design pipeline. Use when the user wants to capture a thought, not commit to building anything yet.
Produce impact review for unplanned changes
Takes a Markdown narrative + Mermaid diagrams (.md / .mmd) and a brand asset folder, and produces a print-ready, editorially-reviewed A4 PDF. Diagrams are pre-rendered to SVG/PNG, content is paginated by hand to avoid bottom-clipping, and the result passes…
Launch parallel AI code reviews with multiple reviewers, then synthesize results.
Generate PDF from Markdown with Mermaid diagrams. Pre-renders Mermaid to SVG, manages page breaks, converts via md-to-pdf.
Phase completion validation — verifies all features in a phase are complete, checks quality gates, and updates PLAN.md. Use when all features in a phase are done and ready for sign-off.
Reverse-engineer a Product Requirements Document from an existing codebase. Reconstructs product vision, personas, user stories, and business processes by analyzing code structure (ACM), runtime behavior (Sweep), and domain context. Part of the Brownfield…
Run a Claude Code coding agent inside a sandboxed Docker container with the claudeium SDLC harness pre-loaded. Use for autonomous coding tasks that need isolation from the host.
Analyze Runtime Sweep output — correlate with ACM knowledge graph, produce behavioral specifications and characterization test templates. Use after running sweep-observ against a target application.
Run quality gates — unit tests, linting, SAST, SCA, complexity, coverage. Use when running tests, checking code quality, or validating before commit.