mcp-skill
MCP Skill
Use this skill when you need MCP capabilities such as browser automation, documentation lookup, repository reading, web search, or remote URL reading.
OpenCode is intentionally configured with no global MCP servers. Heavy MCP servers must be called on demand through MCPorter so small containers do not start Playwright, Chrome DevTools, Context7, or Z.AI MCP processes at session startup.
Rules
- Use
mcporterthrough the shell; do not add servers toopencode.json. - Always pass
--config ~/.mcporter/mcporter.json. - Prefer HTTP MCPs (
context7,web-search-prime,web-reader,zread) over local stdio MCPs when they satisfy the task. - Use local stdio MCPs (
playwright,chrome-devtools,context7-local,zai-mcp-server) only when required. - Keep calls scoped and short; avoid prewarming or daemon mode in small containers.
- Do not print secrets or inspect credential files.
Common commands
List configured MCP servers:
mcporter list --config ~/.mcporter/mcporter.json
Inspect one MCP server schema:
mcporter list context7 --schema --config ~/.mcporter/mcporter.json
Call Context7 docs:
mcporter call context7.resolve-library-id libraryName=react --config ~/.mcporter/mcporter.json
mcporter call context7.get-library-docs context7CompatibleLibraryID=/websites/react_dev topic=hooks --config ~/.mcporter/mcporter.json
Call Z.AI web search / reader:
mcporter call web-search-prime.web_search_prime search_query="OpenCode MCP lazy loading" --config ~/.mcporter/mcporter.json
mcporter call web-reader.webReader url=https://example.com --config ~/.mcporter/mcporter.json
Call local browser MCP only when necessary:
mcporter list playwright --schema --config ~/.mcporter/mcporter.json
mcporter call playwright.<tool_name> --args '{"key":"value"}' --config ~/.mcporter/mcporter.json
If a tool name is unclear, run mcporter list <server> --schema first.
More from atomlink-ye/my-claude-plugins
debug-workflow
Unified debug workflow skill for real-world issue reproduction, especially browser/UI/Web3 problems that need Playwright, shared Chrome/CDP, or agent-wallet. Use this whenever the user wants to confirm whether a workflow can reproduce real issues from walkthrough docs, issue lists, QA notes, or live bug reports. Start with the debug index, route to the right lane, and prefer deterministic local reproduction over fragile preview environments.
11task-iteration
Orchestrate end-to-end feature implementation from an exec-plan document. Use this whenever the user wants a structured Plan → Generate → Evaluate loop for a feature. It keeps planning and acceptance in Claude, pushes bounded coding/test execution to OpenCode companion sessions, reuses warm sessions across fix rounds, and gates completion on independent evaluation plus an advisory review.
11paseo-companion
Paseo CLI companion. Load whenever the user mentions paseo, paseo agents, paseo run/send/wait/logs/attach/ls, agent IDs, sending follow-ups to a running agent, loops, schedules, terminals, worktrees, chat, permits, daemon operations, or host/port targeting.
11google-workspace
Read, create, and edit Google Workspace documents using the `gws` CLI. Use this skill whenever the user mentions Google Docs, shares a docs.google.com URL, references a Google Doc ID, or wants to read/write/create Google documents. Also trigger on 'GDoc', 'gdoc', 'Google Doc', 'gws docs', or any Google Workspace document operation. Will expand to cover Drive, Sheets, Gmail, Calendar, and other GWS services.
11opencode-orchestrator
Aggressively load this skill BEFORE any delegation decision — explore, plan, implement, review, adversarial second-opinion, bounded investigation, or any medium/heavy coding request. Also triggers for manager-vs-executor routing, OpenCode session reuse, multi-step coding orchestration, and work that likely exceeds 10 tool calls, 5 files, or repeated read/edit/test loops. When the live snapshot below shows OpenCode serve is reachable, this skill's routing takes precedence over the caller's generic delegation defaults across every delegated action, not only bounded coding execution. If serve is unreachable, fall back silently to the caller's defaults.
11opencode-companion
OpenCode runtime companion. Load for OpenCode task/review/status/serve/rescue requests, session IDs, timeout recovery, attach/resume decisions, background jobs, and result forwarding.
11