danhdue/d3nexus

Generates a standardized Network Module, API Interface, Remote Data Source, Repository, UseCase, Models, and ViewModel updates for Android using the Hybrid Network Architecture and MVI Pattern.

Read-only Android quality assurance provider implementing the common quality contract. Executes project-configured Gradle, Spotless, Detekt, and Konsist capabilities from .agents/quality/android-quality.json, enforces BCV and architecture policies, and outputs structured results bound to repository SHA.

Audits Jetpack Compose and Android UI code for recomposition stability, state hoisting, Material3 design system adherence, and modifier best practices.

Automate the end-to-end process of handling a new API request, from model generation to Data Source integration.

Audits code changes for Clean Architecture, Domain purity, feature module isolation, MVI state immutability, and concurrency discipline across Android Native, Flutter, and iOS Native projects.

Use when auditing Antigravity profiles for account block vulnerabilities, cloned machine IDs, cross-account trajectory leaks, rate-limit risks, or remediating profile security to prevent 403 Terms of Service suspensions.

Asks which kind of work a request is for, then routes to the matching inception skill. Use it whenever someone asks to brainstorm, explore or design something without making clear whether the deliverable is code or a document. When the deliverable is already known, invoke dev-brainstorming or doc-brainstorming directly and skip this skill.

Use this skill to systematically clear Flutter build and analyzer errors. Captures the full analyzer report, groups errors by cause (missing imports, missing codegen, type mismatch, lint), then fixes and re-runs until clean.

Shows the interactive Antigravity Multi-Profile Quota Dashboard (Dark Mode Visual Companion) or prints terminal quota cards with model details, countdowns, and quick actions across all configured accounts.

Enforces a checklist to verify that all required secure configuration files (google-services.json, GoogleService-Info.plist, environment-configs.json) are present for all environments (dev, stg, prd).

Audits code changes for clean code standards, function sizing (<20 lines), argument limits (<=2 params), strict null-safety (banning !! in Kotlin, ! in Dart, and !/try! in Swift), and idiomatic practices across Android Native, Flutter, and iOS Native projects.

Copies secure configuration files (google-services.json, GoogleService-Info.plist) from the secureFiles directory to Android and iOS project paths.

Guide for creating a new feature or subfeature following the project's Clean Architecture + MVI pattern.

Reviews implemented code, commits, and diffs using external frontier models (Claude CLI, Codex CLI, Antigravity CLI, Kiro CLI) or local Ollama models with evidence-grounded triage.

Writes Architecture Decision Records in Michael Nygard's format, and spike reports that state what would refute them. Use it when a technical decision needs recording, when one is being reversed, or after an investigation that produced a recommendation.

Turns an idea for code work into an approved design spec through collaborative dialogue — clarifying questions, two or three alternatives, and a design the user approves section by section. Use it before creating features, building components, adding functionality or changing behaviour. When the deliverable is a document rather than code, use doc-brainstorming instead.

Use when analyzing high-level requirements to design a complete software Epic across Web Applications, Flutter, Android Native, iOS Native, Python, or Rust projects, including High-Level Design (HLD), Mermaid diagrams, Integration Test Plans, and Kanban task breakdowns with BDD & TDD specifications.

Use when an epic already has an approved HLD and Kanban task files (.devtool/epic/<epic_dir>/ + .devtool/features/task_*.md) and you need to actually execute those tasks against the codebase, in the right order, inside an isolated worktree across Web Applications, Flutter, Android Native, iOS Native, Python, or Rust projects.

Use this skill to orchestrate epic-scale work from idea to merged branch. It owns the sequence and the five approval gates connecting dev-brainstorming, dev-designer, dev-implementation, and quality_check — which skill runs next, what each stage must hand over, and what to do when a gate fails. Activate it when a request spans multiple components or needs an HLD plus a Kanban task breakdown, when routing an approved spec, or whenever it is unclear which epic stage the work is currently in.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Turns an idea or a document request into an approved content spec through collaborative dialogue — what the document must say, what it deliberately will not cover, and one thing the reader can do afterwards. Use it before writing a runbook, handbook, guide, proposal, strategy document or set of reference pages. When the work changes a file that ships in the build, use dev-brainstorming instead.

Turns a document request into a brief, an outline and one task per section. Establishes who the document is for, classifies it into exactly one Diátaxis type, and enforces Gate 2 of the document lifecycle. Use it at the start of any documentation work large enough to break down.

Drafts an approved document outline section by section — one worktree, one commit per section, the outline kept truthful. Hands the draft to doc_quality_check at Gate 3 and holds Gate 4 for sign-off. Use it at Stage 2 of the document lifecycle.

Orchestrates work whose deliverable is a document rather than code — a runbook, handbook, onboarding guide or set of reference pages. Owns the sequence and the four approval gates connecting doc-brainstorming, doc-designer, doc-implementation and doc_quality_check. Use it when a document spans enough sections to need a breakdown.

Quality gate for documentation. Runs mechanical checks, Diátaxis type conformance and a content audit, and refuses outright if the change touches files that ship in the build. Use it in place of quality_check whenever the deliverable is prose.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Read-only Flutter quality assurance provider implementing the common quality contract. Executes project-configured Melos, FVM, and Dart capabilities from .agents/quality/flutter-quality.json, enforces module boundaries and license headers, and outputs structured results bound to repository SHA.

Audits Flutter UI code for widget rebuild optimization, const discipline, state hoisting, controller disposal, and design token adherence.

Performs 4-layer impact, blast radius, bridge contract, and upstream git conflict analysis before editing code (Shift-Left) and at final quality check (Shift-Right Bookend).

Read-only iOS quality assurance provider implementing the common quality contract. Executes project-configured Tuist, SwiftPM, SwiftFormat, and SwiftLint capabilities from .agents/quality/ios-quality.json, enforces ArchTests architecture rules and module boundaries, and outputs structured results bound to repository SHA.

Audits SwiftUI and iOS UI code for body re-evaluation efficiency, state hoisting, Task lifecycle cancellation, AppUIKit design tokens, and Slang-style localization.

Parse JSON and create freezed object classes following project conventions.

Use when identifying a target customer segment, building needs-based personas, running customer discovery interviews, or quantifying which customer needs are underserved — before any feature, technology or design is chosen. Covers steps 1 and 2 of Dan Olsen's Lean Product Process and produces the Gate 1 problem space specification.

Use when scoping an MVP feature set, writing user stories, breaking features into chunks, prioritizing a backlog by ROI, deciding what ships in v1 versus later, or preparing a validated backlog for engineering. Covers step 4 of Dan Olsen's Lean Product Process and produces the Gate 3 MVP feature backlog.

Use when a user brings a product idea, wants to validate an idea before building it, asks what to build first, or needs to reach product-market fit. Orchestrates Dan Olsen's Lean Product Process across market discovery, value strategy, and MVP scoping, enforcing problem-space discipline and three human approval gates before any engineering begins.

Use when defining a product's value proposition, classifying benefits with the Kano model, comparing against competitors or the customer's current workaround, choosing a differentiator, or deciding what the product deliberately will not do. Covers step 3 of Dan Olsen's Lean Product Process and produces the Gate 2 value proposition specification.

Use this skill when dependencies change, after pulling changes, or when "file not found" or missing generated-code errors appear in a Flutter melos workspace. Syncs packages and re-runs code generation in the correct order.

Converts raw JSON structures into clean, production-ready Moshi DTOs for the Android_Digital_Wallet project.

Performs comprehensive Pull Request reviews by delegating quality verification to quality_check with profile pr, validating project-registered provider contracts, and consuming the unified executive report.

Performs Shift-Left architectural and task design document reviews (HLD, BDD, Tasks, RFC) against source code before implementation begins.

Read-only Python quality assurance provider implementing the common quality contract. Executes project-configured capabilities from .agents/quality/python-quality.json, enforces architecture policies via import-linter, and outputs structured results bound to repository SHA.

Platform-neutral quality gatekeeper and orchestrator that discovers project-registered providers from .agents/quality/check_quality.json, validates versioned contracts, aggregates verdicts (FAIL > BLOCKED > PASS), and renders immutable SHA-bound executive reports.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Pings Claude Code and Codex CLIs or configures daily scheduled daemons to refresh and pre-warm 5-hour rolling session windows with minimum token consumption and zero skill initialization. Use when pre-warming rolling quota windows, setting up daily auto-refresh schedules, or resetting session timers without loading repository context.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Restores project architectural awareness, active epic states, recent programmer activity, and Kanban task progress across multi-repository workspaces on session startup or account rotation while enforcing the Tri-Role Governance Model.

Read-only Rust quality assurance provider implementing the common quality contract. Executes project-configured Cargo capabilities from .agents/quality/rust-quality.json, enforces Konsist-equivalent architecture policies via xtask, and outputs structured results bound to repository SHA.

Persists architectural decisions, active epic states, and programmer activity logs under fcntl.flock concurrency protection, emits role-bound handoff prompts, or completes and archives epic features into the permanent project ledger.

Use this skill when the project needs to build but the secureFiles/ directory is missing. Detects whether provisioning already happened, decodes the SECURE_FILES environment variable as a fallback, and tells the user exactly what to run if neither is available.

Audits code changes for mobile fintech security, OWASP Mobile Top 10 (2024), financial precision (BigDecimal in Kotlin, Decimal in Dart, Decimal in Swift), secure storage, and privacy controls across Android Native, Flutter, and iOS Native projects.

Use this skill at the start of a new working session to establish the session name, focus area, and the project context the agent should load before doing anything else.

Sets up and verifies shared contract topologies, canonical templates (api_contract, architecture_and_flow, gaps_and_rfcs), relative symlinks, and governance rules across Hub and Satellite repositories.

Use this skill to make a Flutter checkout buildable - verify secure files are present, copy them into their platform locations, optionally configure dev/stg/prd build variants, and confirm the environment by building one flavor. Use it on a fresh clone, a new worktree, or after secure files change.

Merges workspace keybindings (.vscode/keybindings.json) into the user's global IDE configuration (VS Code, Cursor, Windsurf, Antigravity, etc.).

Merges workspace keybindings into IDE user profile configurations (e.g., ~/antigravity-profile-2/User/keybindings.json).

Inspects repository structure, auto-detects platforms (Flutter, Android, iOS, Rust, or Polyglot), and scaffolds standardized quality provider configurations adhering to canonical templates.

Automates the setup of build variants (flavors) for Android and iOS in a default Flutter project, including signing and VS Code launch configuration.

Use when executing implementation plans with independent tasks in the current session

Audits shared contract deltas (check), generates requirements briefs with snapshot watermarks (brief), and records scope-bound acknowledgements (ack) across Satellite and Hub repositories with dev-lifecycle integration.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Monitors task execution for skill improvement opportunities. Use during ANY multi-step task, agentic workflow, or work session where the agent uses tools and produces deliverables. Captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers in post-task feedback discussions and when the user mentions skill observations, improvements, the observation log, skill taxonomy, or asks the agent to watch for skill opportunities. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: invoke this skill before the FIRST tool call of any session and before writing or proposing a plan — any turn that will involve a tool call counts, however simple the opener looks. This sentence is the session-start trigger and the only activation layer that survives an unreachable config file; pair it with a CLAUDE.md instruction or a harness session-start hook (references/environments.md) — description matching alone is not enforceable.

Use when implementing any feature or bugfix, before writing implementation code

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Read-only Web quality assurance provider implementing the common quality contract. Executes project-configured capabilities from .agents/quality/web-quality.json for Astro TypeScript and Vanilla JavaScript projects, and outputs structured results bound to repository SHA.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating new skills, editing existing skills, or verifying skills work before deployment