game-concept

Game concept design

Decide what game to make, without writing code, numeric tables, or scene-by-scene level scripts.

Read concept-method.md. The input must include SOURCE_BIBLE.md and PRODUCT_BRIEF.md; if either is missing, stop and state the gap, do not fill it in on behalf of upstream.

The output language is locked by PRODUCT_BRIEF.md ; when not locked, follow the conversation language and do not default to producing Chinese.

Decision boundaries

Directly inherit the platform, input, audience, rating, duration, target market, and non-goals already locked by the brief; if they are found to clearly conflict with the original work, return to the main entry point for revision rather than silently changing values at the concept stage. Treat the original language, cultural context, target market, and interface language separately; do not automatically infer one from another.

Interactive narrative is a mature gameplay form, and its standards are not lowered just because it is carried by reading and dialogue; its verbs can be reading the situation, probing, comparing information, taking a stance, concealing, handing over, and bearing echoes.

The concept must also determine the validation form: when it can be expressed with mature interaction grammar, explain “existing grammar + how the original work changes it”; when the core depends on real-time feel, space, sightlines, physics, or unique controls, explicitly go with a custom greybox. Do not treat a text prototype as the universal prerequisite layer for all experiences, and do not let a template decide the gameplay for the original work just because one is available.

Comparison scope

First list the locked dimensions of the brief and the dimensions still open, and compare only directions that can reveal real trade-offs, without padding the number of concepts or difference dimensions. Examine credible alternatives only when the direction is still open; when the user has already chosen a direction or no valid alternative exists, explain why, switch to validating that direction’s risks, and do not reopen the choice.

Choice

First eliminate one by one according to concept-method’s hard vetoes, without calculating a total score, then choose according to its comparison dimensions.quick Automatically choose the direction with the strongest evidence;director only give recommendations for directions not yet decided and wait for the user to choose.

Output

Generate a concepts/CONCEPT.md, containing only:

1. the brief’s locked values and open dimensions;
2. the experience promise and its observable phenomena and failure phenomena;
3. a compact precedent explanation;
4. candidate concept cards: primary type,experienceProfile, gameplay precedents borrowed/rejected, core actions and loop, pressure, failure, world response; explain how the player identity forms repeated actions, execution resistance, and observable change, without requiring independent fixed key names. signature_command Write values or N/Aaccording to the method “identity-specific command”; finally explain how the original work’s tension is enacted by the player, the signature image, the minimum validation slice, the biggest risk, and the veto observation;
5. hard veto results, key trade-offs, recommendations, and choice status;
6. the chosen direction’s player agency contract and non-negotiable experience promise;
7. minimum validation questions and open questions.

narrative-led or hybrid narrative layer must also choose a branching structure grammar and explain the content budget. Before handoff, confirm that the chosen direction can be made into a complete slice within the scope of the brief.