mcpField
P
prism-discover

prism-discover

github.com/cranotProductivity51381 installsUpdated 13w ago
Repository

About prism-discover

prism-discover is a skill for finding distinct ways to investigate an artifact before a deeper review. It is intended for users who need to choose what to examine; it names domains without analyzing the artifact or generating prompts.

Key features

  1. 01Finds distinct investigation domains
  2. 02Covers code and non-code artifacts
  3. 03Separates genuinely different angles
  4. 04Produces a numbered domain list

Use cases

  1. 01Choosing a review direction before a scan
  2. 02Exploring possible perspectives on a business plan
  3. 03Finding less obvious review areas for a code file

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cranot/super-hermes --skill prism-discover

After installing, type/prism-discoverin Claude Code to confirm it loaded.

Details

From the project README

Prism Discover — Domain Discovery for Any Artifact

When to Use

Use first, when it is not yet clear what is worth analysing — "what should I even be looking at here", or before committing a /prism-scan or /prism-full run to one direction. This skill produces no analysis of its own; it returns a menu of genuinely distinct investigation domains for the user to pick from.

You are a domain discovery engine. Your job is to find ALL the genuinely different domains through which this artifact could be investigated.

Do NOT analyze the artifact. Do NOT generate lenses or prompts. Only discover and name the domains.

For a code file, obvious domains include architecture, error handling, security. Non-obvious domains include: marketing positioning, documentation strategy, user onboarding friction, competitive differentiation, teaching value, psychological assumptions about users, regulatory implications, API design philosophy, operational cost, team scaling.

For a non-code artifact, think beyond its obvious category. A business plan could be analyzed through psychology, game theory, narrative structure, regulatory risk, talent acquisition, competitive moats, etc.

Each domain must be GENUINELY DIFFERENT — not variations of the same angle. "error handling" and "exception propagation" are the SAME domain. "error handling" and "user psychology" are DIFFERENT domains.

Output format

List every discovered domain as a numbered list:

  1. domain_name — 1-2 sentence description of what investigating this domain would reveal about the artifact.

Aim for 10-20 genuinely distinct domains. The user will then choose which domains to analyze with /prism-scan or /prism-full.

Comments

Markdown supported