원클릭으로 Manus에서 모든 스킬 실행

model-portability-adapter

스타4

포크0

업데이트2026년 6월 9일 14:19

Adapt skills, workflows, prompts, and tool instructions so they work across Claude, ChatGPT, Gemini, Codex, local agents, and other MCP-enabled systems. Use when the user wants cross-model compatibility or asks to make instructions vendor-neutral.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

ntaffzii

ntaffzii/Skill-Agents

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Model Portability Adapter

Use this skill to make agent instructions portable across model providers and clients.

Portability Principle

Write for agent capability, not provider branding.

Good:

Use available file-reading tools.
Use available command execution tools.
Use available web/search tools.
Use the client's artifact/document feature if present.

Avoid:

Hardcoding one client's tool name.
Assuming one model's memory, browsing, artifact, or MCP behavior.
Depending on hidden system prompts.

Compatibility Targets

This skill is intended for:

Claude or Claude Code
ChatGPT or custom GPT-style agents
Gemini or Gems-style agents
Codex or coding agents
Local agents with MCP servers
Multi-agent systems with their own tool registry

Workflow

Identify the instruction type
- Skill: behavior or domain process.
- Workflow: ordered multi-step job.
- Tool instruction: executable action mapping.
- Prompt: one-off request or reusable template.
Remove vendor coupling
- Replace exact tool names with capability names.
- Replace client-specific UI assumptions with generic alternatives.
- Keep any vendor-specific notes in an adapter section, not the core skill.
Normalize structure
- Use clear frontmatter when supported.
- Put trigger guidance in the description.
- Keep the body procedural.
- Include verification and output expectations.
Add adapter notes
- Claude: can use SKILL.md style folders when the client supports skills.
- ChatGPT: can paste the core instructions into custom instructions or project instructions.
- Gemini: can use the core instructions as Gem or agent guidance.
- Local MCP agents: map capability names to registered MCP tools.
Validate portability
- Check that the skill still makes sense without exact tool names.
- Check that a model without file tools can still ask for files or explain the blocker.
- Check that a model with tools knows when to inspect, act, and verify.

Rules

Keep provider-specific details optional.
Do not promise that every platform loads SKILL.md natively.
Do not rely on one model's hidden behavior.
Prefer short, explicit instructions over platform lore.

Output Format

End with:

Portable core
Provider-specific notes
Tool capability mapping
Compatibility risks

이 저장소의 다른 Skills

같은 저장소

deprecated

ntaffzii/Skill-Agents

Retire, preserve, explain, or replace old skills without silently deleting useful history. Use when the user asks to deprecate a skill, replace a skill, audit stale skills, or understand why a skill should no longer be used.

2026-07-084

in-progress

ntaffzii/Skill-Agents

Manage draft skills that are not ready to ship yet. Use when the user asks to prototype, sketch, test, evaluate, or promote an experimental skill from in-progress into a stable skill bucket.

2026-07-084

skill-management

ntaffzii/Skill-Agents

Manage a skill repository: create, classify, improve, deprecate, or reorganize agent skills with clean buckets, clear SKILL.md metadata, progressive disclosure, and installable structure. Use when the user asks to make skills, organize skills, compare skill quality, or maintain a skills repo.

2026-07-084

obsidian-vault-workflow

ntaffzii/Skill-Agents

Operate across an Obsidian vault: organize notes, maintain links, normalize tags and properties, create indexes, update maps of content, and preserve vault conventions. Use when the user asks to clean, organize, connect, refactor, or maintain an Obsidian vault.

2026-07-084

personal

ntaffzii/Skill-Agents

Manage personal-only skills and private agent preferences that should not be promoted into public or team skill buckets. Use when the user asks to add personal rules, local setup guidance, private workflows, preferences, or machine-specific instructions.

2026-07-084

ui-design-engineering

ntaffzii/Skill-Agents

Design, implement, harden, and review production-grade user interfaces for web apps, dashboards, SaaS products, admin tools, forms, and responsive frontend components. Use when building or improving UI/UX, translating Figma or requirements into code, styling React/Vue/Svelte/HTML views, reviewing frontend quality, fixing accessibility or motion, refining interaction states, improving performance, or validating responsive layout and visual polish. Integrates with Skill-Agents frontend workflows and browser, Playwright, Figma, package, test, and validation MCP tools.

2026-06-104

name	model-portability-adapter
description	Adapt skills, workflows, prompts, and tool instructions so they work across Claude, ChatGPT, Gemini, Codex, local agents, and other MCP-enabled systems. Use when the user wants cross-model compatibility or asks to make instructions vendor-neutral.

Model Portability Adapter

Use this skill to make agent instructions portable across model providers and clients.

Portability Principle

Write for agent capability, not provider branding.

Good:

Use available file-reading tools.
Use available command execution tools.
Use available web/search tools.
Use the client's artifact/document feature if present.

Avoid:

Hardcoding one client's tool name.
Assuming one model's memory, browsing, artifact, or MCP behavior.
Depending on hidden system prompts.

Compatibility Targets

This skill is intended for:

Claude or Claude Code
ChatGPT or custom GPT-style agents
Gemini or Gems-style agents
Codex or coding agents
Local agents with MCP servers
Multi-agent systems with their own tool registry

Workflow

Identify the instruction type
- Skill: behavior or domain process.
- Workflow: ordered multi-step job.
- Tool instruction: executable action mapping.
- Prompt: one-off request or reusable template.
Remove vendor coupling
- Replace exact tool names with capability names.
- Replace client-specific UI assumptions with generic alternatives.
- Keep any vendor-specific notes in an adapter section, not the core skill.
Normalize structure
- Use clear frontmatter when supported.
- Put trigger guidance in the description.
- Keep the body procedural.
- Include verification and output expectations.
Add adapter notes
- Claude: can use SKILL.md style folders when the client supports skills.
- ChatGPT: can paste the core instructions into custom instructions or project instructions.
- Gemini: can use the core instructions as Gem or agent guidance.
- Local MCP agents: map capability names to registered MCP tools.
Validate portability
- Check that the skill still makes sense without exact tool names.
- Check that a model without file tools can still ask for files or explain the blocker.
- Check that a model with tools knows when to inspect, act, and verify.

Rules

Keep provider-specific details optional.
Do not promise that every platform loads SKILL.md natively.
Do not rely on one model's hidden behavior.
Prefer short, explicit instructions over platform lore.

Output Format

End with:

Portable core
Provider-specific notes
Tool capability mapping
Compatibility risks