Documentation

Why We Need a Multi-Model Adapter

Different models are trained on different corpora, aligned with different methods, and use different reasoning paradigms. A prompt or skill that's optimal for Claude is rarely optimal for GPT, Gemini, DeepSeek-R1, or Kimi. Writing one prompt for all of them means only one model performs well — the others degrade in quality or output stability.

Where the Differences Come From

DimensionDescription
Training dataAnthropic used lots of XML-styled data — Claude is highly sensitive to tag structure. OpenAI prefers Markdown instructions
AlignmentRLHF / DPO / Constitutional AI — each favors different prompt style (strict vs minimal)
Reasoning paradigmNative reasoning models (o1 / R1 / QwQ) produce their own CoT — adding "think step by step" hurts quality
Context lengthKimi / Gemini have huge context → inline entire docs. Claude → progressive disclosure works better
Tool protocolAnthropic tool_use / OpenAI function calling / Google function_declarations / Chinese platform DSL all differ
Language preferenceChinese models handle direct Chinese best; international models prefer Markdown + English

The Cost of "One Prompt Fits All"

Common failure modes when swapping models:

  • XML prompt written for Claude → dropped into GPT → quality drops, structure unstable
  • "Let's think step by step" written for GPT → dropped into o1 / R1 → reasoning models get misled, waste reasoning budget
  • Claude's progressive-disclosure skill → Kimi → wastes Kimi's huge context ability
  • Chinese prompt unchanged → Gemini → noticeably worse than English equivalent
  • Chinese workflow platforms (Coze / Bailian / Qianfan) need DAG DSL → a flat prompt cannot be deployed directly

CAUTION

"Barely runs" ≠ "performs optimally". A production-grade prompt/skill system must render differently per model.

PromptMan's Approach

PromptMan ships a "Canonical Skill Spec + Model Adapter" system:

01

Canonical (vendor-neutral) middle layer

Describe identity, goal, steps, inputs, output, constraints, examples, tools — without any vendor-specific syntax

02

Adapter layer

Every mainstream model (Claude / GPT / Gemini / Qwen / DeepSeek / Kimi / GLM / ERNIE / Doubao + reasoning variants) has a dedicated adapter that renders to its best-practice format

03

Unified entrypoint

renderSkill(spec, family) and a REST API — render one spec to all models in a single call

04

Playground

Visit /adapters to compare 12 model renderings live in the browser