integrating-agent-platforms
Use when installing, updating, packaging, or troubleshooting Flow integrations across Claude Code, Gemini CLI, Codex CLI, OpenCode, Cursor, VS Code/Copilot, OpenClaw, or Google Antigravity.
Best use case
integrating-agent-platforms is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when installing, updating, packaging, or troubleshooting Flow integrations across Claude Code, Gemini CLI, Codex CLI, OpenCode, Cursor, VS Code/Copilot, OpenClaw, or Google Antigravity.
Teams using integrating-agent-platforms should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/integrating-agent-platforms/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How integrating-agent-platforms Compares
| Feature / Agent | integrating-agent-platforms | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when installing, updating, packaging, or troubleshooting Flow integrations across Claude Code, Gemini CLI, Codex CLI, OpenCode, Cursor, VS Code/Copilot, OpenClaw, or Google Antigravity.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Integrating Agent Platforms ## Overview Use official host-native install and update flows first. Keep the shared mental model consistent across hosts: install source, update path, cache behavior, local-vs-shared scope, and restart requirements. <workflow> 1. Prefer the platform's official marketplace, extension, or plugin system. 2. Use git-backed installs where the host officially supports them. 3. Reserve local links and wrapper files for development or hosts without a first-class git install story. 4. Explain what is copied, what is linked, what is cached, and when a restart is required. - **Claude Code:** Prefer marketplace install and marketplace update commands. - **Gemini CLI:** Prefer `gemini extensions install` from GitHub and `gemini extensions update`. Use `link` only for local development. - **Codex CLI:** Treat the plugin manifest and marketplace as the source of truth. Distinguish repo marketplace metadata from the installed cached copy. - **OpenCode:** Follow local plugin directory and skills discovery rules. Do not imply undocumented git-url plugin installs are the default. - **Google Antigravity:** Prefer workspace-local `.agents` customization when supported by the current build; keep global fallback guidance available. </workflow> <guardrails> - Prefer user-scoped installs for personal tooling. - Use project-scoped or workspace-scoped registration only when the team should inherit it. - When local-only ignores are needed, prefer `.git/info/exclude` before `.gitignore`. - Do not present undocumented install paths as if they were official. - Distinguish source checkout, installed copy, and cache behavior when the host does. </guardrails> <validation> Before giving host-integration guidance, verify: - [ ] The install path is host-native when one exists - [ ] Update/refresh commands are current for the target host - [ ] Scope is clear: user, project, workspace, or local - [ ] Cache/copy/link behavior is explained when it affects updates - [ ] Restart requirements are called out when relevant </validation> <example> Example framing: - "Gemini CLI should use the GitHub-backed extension install flow. Use `link` only for local development against a checkout." </example> ## Reference Read [references/host-matrix.md](references/host-matrix.md) when you need exact host-by-host guidance.
Related Skills
flow-memory-keeper
Use at task, phase, flow, sync, archive, finish, revise, or failure checkpoints to keep Flow specs clean, capture learnings and failures, elevate durable patterns, and refine this skill with project-specific nuances
vue
Use when editing Vue projects, .vue files, vue.config.js, Vue 3 components, Composition API, <script setup>, SFC state, deployment workflows, or Vue CI configuration.
vite
Use when editing Vite projects, vite.config.ts, vite.config.js, Vite plugins, HMR, asset bundling, frontend build settings, deployment config, or Litestar/Vite integration.
uvicorn
Use when deploying ASGI apps with uvicorn, editing uvicorn CLI commands, Config or Server usage, workers, reload, event loop selection, SSL, lifespan, logging, or development server behavior.
tracer
Use when tracing execution paths, mapping dependencies, understanding unfamiliar code, following data flow, investigating end-to-end behavior, debugging call chains, or deciding which files to read next.
testing
Use when writing or refactoring tests, editing test_*.py, *.test.ts, *.spec.ts, conftest.py, vitest.config.ts, pytest fixtures, mocks, coverage, async tests, anyio, or test failure debugging.
terraform
Use when creating, adopting, refactoring, or operating Terraform, *.tf files, .terraform.lock.hcl, terragrunt.hcl, root modules, backends, state, workspaces, imports, CI plan/apply, tests, or policy checks.
tanstack
Use when editing TanStack code, @tanstack imports, useQuery, createRouter, React Query, TanStack Router, Table, Form, Store, file-based routing, data fetching, or SPA state management.
tailwind
Use when styling with Tailwind CSS, editing tailwind.config.ts, tailwind.config.js, @tailwind directives, utility classes, responsive layouts, @apply, cn(), @theme config, dark mode, or forms.
svelte
Use when editing Svelte components, .svelte files, svelte.config.js, Svelte 5 runes, $state, $derived, SvelteKit, component state, or migrating away from Svelte 4 patterns.
sqlserver
Use when writing T-SQL, editing SQL Server .sql files, using sqlcmd, SQL Server connection strings, stored procedures, execution plans, indexes, Always On, JSON, security, or connector code.
sqlalchemy
Use when editing SQLAlchemy code, sqlalchemy imports, mapped_column, DeclarativeBase, ORM models, relationships, select() queries, async sessions, engines, events, or migrations.