Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By AppsVortex
Automate full greenfield project lifecycle zero-config: from AI-assisted product discovery, brand naming, competitive analysis, architecture vision, use cases, visual/interactive prototyping, expert debates, stress testing (pre-mortems, interviews, PR/FAQ), to scaffolding buildable React/Svelte/Tauri apps with dev environments, visual regression testing, and issue tracking integration.
npx claudepluginhub appsvortex/arness --plugin arn-sparkThis agent should be used when the arn-spark-naming skill needs brand strategy expertise to analyze a product's brand DNA, generate name candidates across multiple naming categories, score candidates using the Six Senses framework, or conduct linguistic screening for brand names. Also applicable when a user wants standalone brand naming guidance, needs help evaluating an existing name candidate, or when a future skill requires naming expertise. <example> Context: Invoked by arn-spark-naming skill during Step 1 to analyze brand DNA user: "name my product" assistant: (invokes arn-spark-brand-strategist with product context and competitive landscape) <commentary> Brand DNA analysis initiated. Strategist analyzes target audience vocabulary, brand personality, and competitor name landscape, then recommends naming categories for the creative sprint. </commentary> </example> <example> Context: User wants to evaluate an existing name candidate user: "is Lumina a good name for my analytics product?" assistant: (invokes arn-spark-brand-strategist in scoring mode with the candidate name) <commentary> Standalone name evaluation. Strategist scores the name on the Six Senses framework and flags any linguistic or trademark concerns. </commentary> </example> <example> Context: Invoked by arn-spark-naming skill during Step 2 for creative generation user: "naming" assistant: (invokes arn-spark-brand-strategist with brand DNA and category constraints) <commentary> Creative sprint initiated. Strategist generates 50-80 candidates per category using mind mapping, thesaurus mining, word hacking, and etymology exploration. </commentary> </example> <example> Context: Invoked by arn-spark-naming skill during Step 4 for linguistic screening user: "check these names in Spanish and French" assistant: (invokes arn-spark-brand-strategist with finalist names and target languages) <commentary> Linguistic screening initiated. Strategist checks each finalist for negative connotations, phonetic conflicts, and cultural issues in target languages. </commentary> </example>
This agent should be used when the arn-spark-dev-setup skill needs to create development environment infrastructure files such as dev containers, Docker configurations, setup scripts, CI workflows, toolchain pins, and onboarding documentation. Also applicable when a user needs specific dev environment files generated for their project. <example> Context: Invoked by arn-spark-dev-setup skill after environment decisions user: "dev setup" assistant: (invokes arn-spark-dev-env-builder with environment type, platforms, CI provider, and toolchain versions) <commentary> Dev environment setup initiated. Builder creates setup scripts, CI workflows, toolchain pin files, and CONTRIBUTING.md with prerequisites for all target platforms. </commentary> </example> <example> Context: User needs a dev container for their project user: "set up a dev container for this project" <commentary> Dev container creation. Builder creates .devcontainer/devcontainer.json, .devcontainer/Dockerfile, and VS Code extension recommendations based on the project's stack. </commentary> </example> <example> Context: User wants CI configured for cross-platform builds user: "add GitHub Actions CI with matrix builds for Linux, macOS, and Windows" <commentary> CI workflow generation. Builder creates .github/workflows/ci.yml with a platform matrix, appropriate system dependency installation steps, and build/test jobs for each platform. </commentary> </example>
This agent should be used when the arn-spark-report skill needs diagnostic investigation of an Arness Spark workflow issue. Analyzes Spark configuration, directory structure, and skill behavior against expected patterns documented in the spark knowledge base. Reports only Spark-specific issues — never reads or reports user project code or business logic. <example> Context: Invoked by arn-spark-report skill during investigation phase user: "spark report" assistant: (invokes arn-spark-doctor with user description + config context) </example> <example> Context: User reports prototype build failure user: "the clickable prototype keeps failing to build" assistant: (invokes arn-spark-doctor to check Playwright, scaffold, style brief, prototype config) </example> <example> Context: User reports discovery output missing user: "arn-spark-discover finished but there's no product concept file" assistant: (invokes arn-spark-doctor to check Vision directory config, product-concept.md existence, ensure-config state) </example>
This agent should be used when the arn-spark-stress-premortem skill needs to investigate hypothetical product failure using Gary Klein's pre-mortem methodology. The agent accepts the premise that the product has already launched and failed, then works backward to identify root causes, early warning signals, and mitigation strategies. <example> Context: Invoked by arn-spark-stress-premortem skill for standard pre-mortem investigation user: "stress premortem" assistant: (invokes arn-spark-forensic-investigator with full product concept, product pillars, and competitive landscape) <commentary> Pre-mortem investigation initiated. The forensic investigator accepts the premise that the product launched and was shut down 12 months later, then generates 3 distinct root causes with causal chains, early warning signals, and mitigation strategies. Each root cause targets a different failure category: core experience flaw, trust/security blind spot, and target audience assumption error. </commentary> </example> <example> Context: Invoked by arn-spark-stress-premortem skill with a targeted failure angle user: "stress premortem" assistant: (invokes arn-spark-forensic-investigator with product concept and a specific failure scenario to investigate deeply) <commentary> Targeted investigation initiated. The forensic investigator focuses on a specific failure angle (e.g., "the product failed because enterprise customers never adopted it despite strong indie traction") and produces a deep-dive analysis with extended causal chains, historical precedents from real product failures, and granular mitigation strategies. </commentary> </example>
This agent should be used when the arn-spark-discover skill needs competitive landscape research to identify alternatives in a product's problem space, or when the arn-spark-stress-competitive skill needs deep feature-level competitive analysis. Also applicable when a user wants to validate claims about competitor capabilities or weaknesses with web-grounded evidence. <example> Context: Invoked by arn-spark-discover skill during product discovery when user cannot name competitors user: "discover" assistant: (invokes arn-spark-market-researcher in identification mode with product description and problem space) <commentary> Product discovery initiated. Market researcher plans search queries across multiple angles, executes parallel web searches, and consolidates a tiered list of validated competitors for user review. </commentary> </example> <example> Context: User names some competitors and the skill wants to fill gaps in the landscape user: "I know about Figma and Sketch but there must be others" assistant: (invokes arn-spark-market-researcher in identification mode with known competitors as seeds) <commentary> Partial landscape provided. Market researcher uses known competitors as comparison-focused search seeds and expands the landscape with additional alternatives across problem-focused and community-focused angles. </commentary> </example> <example> Context: Invoked by a future Gap Analysis skill for deep competitive analysis user: "gap analysis" assistant: (invokes arn-spark-market-researcher in deep-analysis mode with identified competitors) <commentary> Deep analysis requested. Market researcher performs thorough feature-level research on each identified competitor, builds comparison matrices, and synthesizes positioning opportunities. </commentary> </example> <example> Context: User wants to validate assumptions about competitor weaknesses user: "is it true that Notion's offline support is limited?" assistant: (invokes arn-spark-market-researcher with specific validation question) <commentary> Validation request. Market researcher uses WebSearch to verify the specific claim with current evidence, source URLs, and confidence tags. </commentary> </example>
This skill should be used when the user says "brainstorming", "arn brainstorming", "brainstorm", "let's brainstorm", "start brainstorming", "brainstorming session", "greenfield wizard", "arn spark wizard", "greenfield pipeline", "walk me through greenfield", "guided greenfield", "full greenfield pipeline", "greenfield flow", "explore to feature backlog", "greenfield start to finish", "run the greenfield pipeline", "guide me through greenfield", "greenfield guided mode", "greenfield setup", "new project wizard", "add a feature", "new feature", "I need another feature", "add feature to greenfield", "one more feature", or wants to be walked through the entire Arness greenfield exploration pipeline in a single continuous session with guided decision gates instead of invoking each skill manually. Also triggers when the user wants to add a new feature to an existing greenfield project after the clickable prototype is complete.
This skill should be used when the user says "arch vision", "architecture vision", "arn arch vision", "define the architecture", "tech stack", "what technology should I use", "design the system", "system architecture", "how should I build this", "technology choices", "choose technologies", "pick a tech stack", or wants to explore technology options and define the high-level architecture for a greenfield project. Takes a product concept as input and produces an architecture-vision.md document capturing the technology stack, system design, protocols, packaging strategy, and known risks.
This skill should be used when the user says "clickable prototype teams", "arn clickable prototype teams", "team clickable prototype", "debate clickable prototype", "collaborative interaction review", "clickable prototype with debate", "team-based interaction review", "interaction debate", "review interactions as a team", "interactive prototype teams", "team prototype review", or wants to create a clickable interactive prototype with linked screens and validate it through iterative expert debate cycles where product strategist and UX specialist discuss their scores and findings before producing a combined review, with Playwright-based interaction testing, per-criterion scoring, an independent judge verdict, and versioned output. Supports Agent Teams for parallel debate or sequential simulation as fallback. For standard lower-of-two-scores interaction review, use /arn-spark-clickable-prototype instead.
This skill should be used when the user says "clickable prototype", "arn clickable prototype", "interactive prototype", "test interactions", "validate UX", "user journeys", "test navigation", "make it clickable", "prototype interactions", "test the prototype", "build the screens", "create the UI", "screen mockups", or wants to generate a clickable interactive prototype with linked screens and validate it through iterative build-review cycles with Playwright-based interaction testing, per-criterion scoring, an independent judge verdict, and versioned output.
This skill should be used when the user says "concept review", "review concept", "update product concept", "synthesize stress tests", "stress test review", "apply stress test findings", "review stress test results", "concept update", "merge stress test recommendations", or wants to synthesize findings from completed stress tests into a reviewed and updated product concept document. Scans for stress test reports, consolidates recommendations, resolves conflicts using product pillars, presents the full changeset for user approval, and produces an updated product-concept.md alongside a concept-review-report.md.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Development toolkit for Claude Code — plan, implement, ship, review, and assess features with AI-assisted workflows. Progressive zero-config init: auto-configures with sensible defaults on first skill invocation, no upfront ceremony required. Three-tier ceremony model: swift (lightweight), standard (mid-ceremony spec-plan-execute), and thorough (full pipeline) with severity-aware scope routing. Five entry points: arn-planning (scope router, spec, plan), arn-implementing (execute plans, swift, or standard changes), arn-shipping (commit, push, PR), arn-reviewing-pr (PR feedback), arn-assessing (codebase health). Includes arn-code-sketch for UI preview, arn-code-swift for quick implementations, and arn-code-standard for mid-ceremony changes. Includes arn-code-catch-up for retroactive documentation of out-of-pipeline commits. Pipeline preference persistence for streamlined repeat sessions. Batch pipeline: arn-code-batch-planning (multi-feature planning), arn-code-batch-implement (parallel worktree execution), arn-code-batch-merge (conflict-aware merge), arn-code-batch-simplify (cross-feature quality).
Give soul to your workflow. 58 AI-powered skills across 17 roles — PM, Dev, Backend, Frontend, QA, UX, Data, Detect, WordPress, Release, Security, DevOps, and Core. Spec-to-ship pipeline: scaffold, implement, test, secure, deploy. Features two-phase workflow with human approval, quality-reviewer agent, token optimization, and continuous improvement via LEARN.md system.
Phase-based AI development framework with 16+ specialized agents, structured phases, and file-based handoffs. Works with greenfield and existing codebases.
Full-stack agents — frontend, backend, API, DevOps architects
Engineering discipline layer for Claude Code — 5 workflows, 69 commands, 21 rules, 29 skills, 9 agents organized in 12 packs
Full-cycle project development - brainstorm ideas, create specifications, plan architecture, initialize projects, and execute implementation with integrated workflows from superpowers and spec-kit
Development toolkit for Claude Code — plan, implement, ship, review, and assess features with AI-assisted workflows. Progressive zero-config init: auto-configures with sensible defaults on first skill invocation, no upfront ceremony required. Three-tier ceremony model: swift (lightweight), standard (mid-ceremony spec-plan-execute), and thorough (full pipeline) with severity-aware scope routing. Five entry points: arn-planning (scope router, spec, plan), arn-implementing (execute plans, swift, or standard changes), arn-shipping (commit, push, PR), arn-reviewing-pr (PR feedback), arn-assessing (codebase health). Includes arn-code-sketch for UI preview, arn-code-swift for quick implementations, and arn-code-standard for mid-ceremony changes. Includes arn-code-catch-up for retroactive documentation of out-of-pipeline commits. Pipeline preference persistence for streamlined repeat sessions. Batch pipeline: arn-code-batch-planning (multi-feature planning), arn-code-batch-implement (parallel worktree execution), arn-code-batch-merge (conflict-aware merge), arn-code-batch-simplify (cross-feature quality).
Infrastructure and deployment plugin for Arness with progressive zero-config init — auto-configures with sensible defaults on first skill invocation, no upfront ceremony required. 23 skills and 9 agents covering containerization, IaC generation, deployment, CI/CD pipelines, environment management, secrets, monitoring, migration, and structured change management pipeline. Can operate standalone or alongside the arn-code plugin.

Arness — H not required.
Structured AI workflows for Claude Code. From first idea to production deploy.
Seven entry commands. That's all you need to remember. Behind them, 134 specialist skills and agents handle the details across three independent plugins — ideation, development, and infrastructure.
Most AI coding tools help you write code faster. Arness helps you build software better. It gives your Claude Code session a structured pipeline: specs before code, plans before execution, reviews before shipping. Every stage produces a human-readable artifact that feeds the next. Nothing is hidden, nothing is locked in.

Most projects fail before the first commit — wrong problem, wrong audience, wrong architecture. Spark takes a raw idea and puts it through product discovery, stress testing, brand naming, use case writing, architecture evaluation, and interactive prototyping. By the time you write real code, you have a validated concept, a prioritized feature backlog, and a scaffolded codebase ready for development.
Start here: /arn-brainstorming | Full guide

The development pipeline that treats AI-assisted coding like engineering, not guesswork. Every feature flows through spec, plan, structure, execute, review, and ship — with three ceremony tiers (swift, standard, thorough) that scale process to match scope. A one-file fix gets a lightweight pass. A cross-cutting refactor gets phases, task dependencies, and quality gates.
Start here: /arn-planning | Full guide

A guided approach to containerization, IaC, deployment, and monitoring. Arness Infra audits your toolchain, generates Dockerfiles and IaC, configures environments and secrets, builds CI/CD pipelines, and walks you through deployment and verification. For complex changes, a structured change management pipeline mirrors the rigor of the development pipeline. Infra is experimental — the newest and least mature of the three plugins. Always review generated infrastructure before applying it. Feedback and suggestions are welcome.
Start here: /arn-infra-wizard | Full guide
Arness asks you questions once and remembers. Your role, tech stack, preferred frameworks, and development conventions are captured on first run and reused across every session and every project. No repeated configuration.
Every skill produces a Markdown or JSON artifact — specs, plans, task lists, review reports, PR descriptions — stored in .arness/ at your project root. Each artifact feeds the next stage in the pipeline, creating a traceable chain from initial idea to merged PR. You can read, edit, or version-control any of it.
Three ceremony tiers — swift, standard, and thorough — match process to scope automatically. A bug fix touching two files does not get the same pipeline as a new authentication system. Arness detects complexity and routes accordingly.
| Plain text, open source | All artifacts are Markdown and JSON. MIT licensed. Read, edit, or delete anything. |
| Learns your preferences | Captures your stack, role, and conventions once. Every session uses them. |
| Artifact-chain traceability | Spec feeds plan feeds tasks feeds code feeds review feeds PR. Nothing is orphaned. |
| Graduated ceremony | Swift (1-8 files), Standard (medium scope), Thorough (complex) — process scales to match the work. |
| Clean project structure | Everything lives in .arness/. Your source tree stays yours. |
| No vendor lock-in | Works with GitHub, Bitbucket, Jira, Figma, and Canva. Remove Arness and your code is untouched. |
# Add the Arness marketplace (one-time)
/plugin marketplace add AppsVortex/arness
# Install the plugins you need
/plugin install arn-spark@arn-marketplace # New product from scratch
/plugin install arn-code@arn-marketplace # Development pipeline
/plugin install arn-infra@arn-marketplace # Infrastructure & deployment
Then run the entry point that matches what you want to do — Arness auto-configures on first use:
/arn-brainstorming New product — discover, validate, prototype, extract features
/arn-planning Plan a feature or fix from scratch
/arn-implementing Pick up where you left off
/arn-shipping Commit, push, open a PR
/arn-reviewing-pr Handle PR feedback
/arn-assessing Deep-dive codebase review
/arn-infra-wizard Infrastructure end-to-end