Latest release: v1.0.0Download zip
Capabilities
Compatibility
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name/description (multi‑agent NPD validation) matches the included files and runtime instructions: multiple evaluator agent prompts, a consensus director, devil's advocate, and orchestrator SKILL.md. Declared requirements are minimal and proportional — web search/WebFetch and subagent behavior in the agent prompts are expected for market research and multi‑agent orchestration.
Instruction Scope
The SKILL.md and agent files instruct agents to perform many web searches, read/write local workspace files (data/*.md), and produce evaluation artifacts — all consistent with the stated purpose. This also means the skill will access any user-provided data placed under data/user_provided/ (explicitly used by the Commercial Viability agent). That is reasonable for the task but is a potential privacy/exposure point: do not place highly sensitive secrets in the workspace unless you intend the plugin to use them.
Install Mechanism
There is no automated install spec (instruction-only), which is low risk. However, the repository includes openclaw-install.sh (9KB) that, if executed, writes workspace files (SOUL.md, AGENTS.md, MEMORY.md, copies agent prompts, seeds memory). Review this script before running; it will create files on disk in the target directory. No remote downloads, URL fetches, or obscure binaries are present in the manifest.
Credentials
The skill declares no required environment variables or credentials. The agent prompts request WebSearch/WebFetch/SubAgent tool usage, which is appropriate for web research. There are no unrelated credential or config path requests. Note: evaluators explicitly prefer and may read user-provided commercial data (data/user_provided/), which is necessary for accurate economics assessment — make sure sensitive business data is shared intentionally.
Persistence & Privilege
always:false (default) and disable-model-invocation:false (normal). The Consensus Director agent is allowed to spawn SubAgent operations and use WebFetch; that capability is coherent with a multi-agent pipeline but increases the plugin's operational blast radius if it runs autonomously. This is expected here, but you should be comfortable granting web access and subagent execution in the environment where you install it.
Assessment
This plugin appears internally consistent with its stated purpose. Before installing or running it: (1) review openclaw-install.sh — it will create workspace files on disk; only run it in a safe/isolated directory; (2) be aware the agents perform many web searches and use WebFetch/SubAgent and will read/write data/*.md — do not place secrets or unintended proprietary files in the plugin workspace; (3) the plugin does not request external credentials, but because it can autonomously spawn subagents and fetch web data, prefer running it in an environment without access to sensitive system-level files or hidden credentials; (4) if you need tighter controls, limit web access or run the skill in a sandboxed account/workspace.Verification
Tags
NPD Validator — Claude Code Plugin
Multi-agent product validation pipeline that orchestrates 8 specialized subagents to evaluate new product concepts and produce evidence-based launch recommendations.
What It Does
When you run /npd-validator:validate-product, the plugin:
- Research Coordinator gathers market data, competitor profiles, and category facts
- 5 Independent Evaluators each run in their own context window — no anchoring bias:
- Market Demand Analyst (category size, demand signals, timing)
- Competitive Intelligence Analyst (white space, competitor weakness, barriers)
- Brand Fit Strategist (brand alignment, portfolio coherence, audience fit)
- Commercial Viability Analyst (pricing power, unit economics, channels)
- Consumer & Trend Analyst (social sentiment, trend momentum, cultural fit)
- Devil's Advocate reads all 5 evaluations and builds the strongest case NOT to launch
- Consensus Director identifies conflicts, challenges evaluators, and produces the final report
Each evaluator is a real subagent with its own context window — not one model pretending to be multiple perspectives. This ensures genuine analytical independence.
Install
claude --plugin-dir /path/to/npd-validator-plugin
Or from a marketplace:
/plugin install npd-validator
Usage
/npd-validator:validate-product A caffeine-infused body moisturizer targeting 25-35 year old
women, priced at $28-35, positioned as clean beauty with an energy boost angle, for Frank Body
Or start with a rough idea:
/npd-validator:validate-product I think there's a gap in men's skincare for something simple
Output
A comprehensive validation report with:
- Verdict: GO / CONDITIONAL GO / REVISIT / NO-GO
- Composite Score: weighted average of 15 scored dimensions
- Master Scorecard: all 15 dimensions with scores and confidence
- Competitor Map: top competitors with positioning analysis
- Pricing Benchmarks: category pricing tiers
- Trend Evidence: social signals and cultural alignment
- Devil's Advocate Case: strongest counter-arguments with kill shot rating
- Deliberation Log: how conflicts were identified and resolved
- Recommended Next Steps: specific actions
Iteration
After the report, you can:
- Pivot: "What if we repositioned as premium?" → re-runs pipeline
- Deepen: "Dig deeper on competitive landscape" → re-runs that evaluator
- Challenge: "I disagree with the brand fit score because..." → evaluator re-assesses
- Reweight: "Brand fit matters more for us" → recalculates composite
Architecture
npd-validator-plugin/
├── .claude-plugin/
│ └── plugin.json ← Plugin manifest
├── skills/
│ ├── validate-product/
│ │ └── SKILL.md ← Main /validate-product command (orchestrator)
│ └── npd-methodology/
│ └── SKILL.md ← Scoring rubrics and templates (reference)
├── agents/
│ ├── npd-research-coordinator.md
│ ├── npd-market-demand.md
│ ├── npd-competitive-intel.md
│ ├── npd-brand-fit.md
│ ├── npd-commercial-viability.md
│ ├── npd-consumer-trends.md
│ ├── npd-devils-advocate.md
│ └── npd-consensus-director.md
└── README.md
Requirements
- Claude Code with subagent support
- Web search enabled (essential for market research)
- Recommended: Opus for Consensus Director, Sonnet for evaluators
Credits
Built by AutoSolutions.ai. Methodology inspired by Karpathy's autoresearch.