From product-lens
Use when the user wants a deep dive into a specific evaluation dimension for a product. Example: teardown moat, teardown journey. Goes deeper than the standard evaluation on one dimension.
npx claudepluginhub n0rvyn/indie-toolkit --plugin product-lensThis skill uses the workspace's default tool permissions.
Accept the dimension argument in both Chinese and English. Mapping:
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Guides agent creation for Claude Code plugins with file templates, frontmatter specs (name, description, model), triggering examples, system prompts, and best practices.
Accept the dimension argument in both Chinese and English. Mapping:
| English | Chinese | Dimension | File |
|---|---|---|---|
| demand | 需求真伪 | Demand Authenticity | 01-demand-authenticity.md |
| journey | 逻辑闭环 | Journey Completeness | 02-journey-completeness.md |
| market | 市场空间 | Market Space | 03-market-space.md |
| business | 商业可行 | Business Viability | 04-business-viability.md |
| moat | 护城河 | Moat | 05-moat.md |
| execution | 执行质量 | Execution Quality | 06-execution-quality.md |
Also accept partial matches and common aliases:
need / needs / demand / jtbd → Demand Authenticityloop / journey / flow / ux → Journey Completenessmarket / space / competition → Market Spacebusiness / revenue / money / viability → Business Viabilitymoat / defensibility / sherlock → Moatexecution / quality / tech / debt → Execution QualityIf the argument doesn't match any dimension, list the available options and ask the user to choose.
Same logic as evaluate skill:
**/product-lens/references/_calibration.md. From the same parent directory, resolve the path to:
_calibration.mdRead _calibration.md (preamble for the evaluator).
Read the target dimension file. Extract:
### iOS if iOS detected, otherwise ### Default)If iOS detected and the dimension has an iOS core question variant (blockquote under ### iOS), note it for the evaluator.
Merge universal + platform-specific into a single numbered list.
For dimensions that benefit from market data (Demand Authenticity, Market Space, Business Viability, Moat):
market-scanner agent with product infoFor other dimensions (Journey Completeness, Execution Quality):
Dispatch a single dimension-evaluator agent with:
_calibration.mddeepWait for completion.
Display the deep-dive report from the dimension-evaluator. The deep mode output includes:
Post-processing:
/evaluate for the full picture or /teardown [other dimension] for a focused follow-up