MA

maintain-cross-platform

A meta-skill for validating 3-platform architectural compatibility, synchronizing version files, and managing configuration alignment.

Install

mkdir -p .claude/skills/maintain-cross-platform && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3992" && unzip -o skill.zip -d .claude/skills/maintain-cross-platform && rm skill.zip

Installs to .claude/skills/maintain-cross-platform

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's 3-platform architecture.
173 chars✓ has a “when” trigger
Advanced

Key capabilities

  • →Align version fields across 11 disparate project files
  • →Validate platform-specific installation paths
  • →Run CI pre-push hooks for platform compatibility
  • →Synchronize configuration formats (JSON/TOML)
  • →Ensure accuracy of cross-platform documentation

How it works

Applies a set of transformation rules and validators to sync configurations, commands, and agent directories across three distinct CLI environments.

Inputs & outputs

You give it
Code changes, version update commands
You get back
Validation reports across platforms

When to use maintain-cross-platform

  • →Preparing project releases
  • →Validating cross-platform compatibility
  • →Updating installation infrastructure

About this skill

Maintain cross-platform AgentSys

AgentSys installs the agent-sh plugins on Claude Code, OpenCode, Codex CLI, Cursor and Kiro. The plugins live in their own repos; this repo owns the marketplace, the installer, the transforms and the docs. Use this skill to find where a cross-platform concern lives and what to run.

Platform details (config formats, frontmatter, env vars, label limits) are in checklists/cross-platform-compatibility.md and docs/CROSS_PLATFORM.md; release steps are in checklists/release.md and agent-docs/release.md. Read them for the current facts instead of relying on memory.

Where things live

ConcernLocation
Marketplace, one entry per plugin pinned by tag and commit.claude-plugin/marketplace.json; re-pin with node scripts/pin-marketplace.js [--dry-run] (needs gh)
Installerbin/cli.js: installForClaude, installForOpenCode, installForCodex, installForCursor, installForKiro. Claude Code installs from the marketplace; the others fetch plugin sources into ~/.agentsys/plugins/<name> and transform them.
Transforms (frontmatter, tools to permissions, plugin-root paths, namespaces)lib/adapter-transforms.js. lib/ is maintained in this repo, so edit it here.
Platform adaptersadapters/opencode-plugin/ (native OpenCode plugin), adapters/opencode/, adapters/codex/; scripts/gen-adapters.js keeps generated files fresh
Dev installsnode bin/dev-cli.js dev-install [tool] (scripts/dev-install.js)
Versionspackage.json is the source; npx agentsys-dev bump X.Y.Z stamps package-lock.json, .claude-plugin/plugin.json, marketplace.json and site/content.json. Plugin repos version independently.
Generated doc sections<!-- GEN:START:... --> blocks, rewritten by npx agentsys-dev gen-docs

Platform differences behind most bugs

  • Plugin root: ${CLAUDE_PLUGIN_ROOT} in Claude Code, ${PLUGIN_ROOT} in OpenCode and Codex; Cursor and Kiro get the install path inlined. Normalize backslashes in require() paths (.replace(/\\/g, '/')), because a Windows path such as C:\Users\... turns into escape sequences.
  • State directory: use AI_STATE_DIR (.opencode, .codex, .cursor, .kiro; unset means .claude) instead of a hardcoded .claude/. validate paths catches hardcoded ones.
  • OpenCode: model fields are stripped by default (--no-strip keeps them), tools become permission: entries, and AskUserQuestion labels longer than 30 characters fail.
  • Codex has no commands or agents: commands become skills invoked as $name, so every skill description needs trigger phrases ("Use when ...").
  • Kiro: commands become prompts in ~/.kiro/prompts/, agents become JSON in ~/.kiro/agents/, and two combined reviewer agents fit its 4-subagent limit. Each skill directory is copied whole to ~/.kiro/skills/<name>/, away from its plugin, so the installer and the Kiro transforms point plugin-root wording ("two directories up from this skill"), relative links that leave the skill directory, and versioned-cache globs (**/<plugin>/*/) at ~/.agentsys/plugins/<plugin>.

Checks

CommandCovers
npm run validateplugins, cross-platform, consistency, paths, counts, platform-docs, agent-skill-compliance
npm testJest suite
npm run gen-docs:check, node scripts/expand-templates.js --check, node scripts/gen-adapters.js --checkGenerated content is fresh (CI runs all three)
npx agentsys-dev preflight [--all|--release]Change-aware checklist checks. The pre-push hook runs it, runs agnix on changed agent configs, and runs --release when a v* tag is pushed.
node bin/dev-cli.js validate opencode-installA real OpenCode install (not part of validate)
npm pack --dry-runThe package builds

Before a release, smoke-test the installer: npm pack, npm install -g ./agentsys-*.tgz, run agentsys, and check each platform's install directory as checklists/release.md lists.

If this skill or a checklist no longer matches the code, fix it in the same change.

Output

## Cross-Platform Compatibility Check

### Validations run
- [OK|ERROR] <validator>: <one line>

### Issues
- <file:line>: <problem> - <fix>

### Docs out of date
- <file>: <what no longer matches>

### Actions taken
- <files changed>

### Next steps
- <remaining work, or "none">

When not to use it

  • →Single-platform specific repository maintenance
  • →General software project releases

Limitations

  • →Bound to the specific 3-platform matrix
  • →Requires update if CI infrastructure changes
  • →Strict enforcement of file paths

How it compares

Acts as a maintenance meta-skill specifically for a multi-platform architecture rather than a general release automation tool.

Compared to similar skills

maintain-cross-platform side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
maintain-cross-platform (this skill)18moReviewAdvanced
gcp-cloud-run58moReviewIntermediate
flow-nexus-platform68moReviewBeginner
smithery-mcp-deployment81yReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

gcp-cloud-run

aj-geddes

Deploy containerized applications on Google Cloud Run with automatic scaling, traffic management, and service mesh integration. Use for container-based serverless computing.

5107

flow-nexus-platform

ruvnet

Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges

691

smithery-mcp-deployment

CaullenOmdahl

Best practices for creating, optimizing, and deploying MCP servers to Smithery. Use this skill when:(1) Creating new MCP servers for Smithery deployment(2) Optimizing quality scores (achieving 90/100)(3) Troubleshooting deployment issues (0/0 tools, missing annotations, low scores)(4) Migrating existing MCP servers to Smithery format(5) Understanding Smithery's schema format requirements(6) Adding workflow prompts, tool annotations, or documentation resources(7) Configuring smithery.yaml and package.json for deployment

881

deployment-pipeline-design

wshobson

Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use when architecting deployment workflows, setting up continuous delivery, or implementing GitOps practices.

670

vercel-deployment

davila7

Expert knowledge for deploying to Vercel with Next.js Use when: vercel, deploy, deployment, hosting, production.

359

netlify-deploy

openai

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.

740

Search skills

Search the agent skills registry