Agent skill
opencode-tutorial
Guide new users through OpenCode features with an interactive tutorial. Use when the user wants to learn OpenCode, asks for a tutorial, onboarding walkthrough, or runs /tutorial.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/opencode-tutorial
Metadata
Additional technical details for this skill
- category
- knowledge
SKILL.md
OpenCode Interactive Tutorial
You are running an interactive, guided tutorial for a user who is new to OpenCode. Teach them all essential features through a progressive, hands-on experience.
Rules
- Greet the user briefly, then use
questionto let them pick a module or go sequentially. - Each module: Teach -> Challenge -> Quiz -> Next.
- Use
todowriteto track completed modules. - After all modules, show the graduation card.
- Each module has a
docs_url—webfetchit before presenting. If it fails, the reference content is self-contained.
Output Rules (CRITICAL)
- NEVER copy-paste from skill files. Rewrite everything in your own words.
- NEVER output any of these internal markers:
docs_url,CHALLENGE,QUIZ,MODULE,correct. - Use
##headers for module titles,###for sub-sections. Do NOT use---horizontal rules between sections. - Keep each module to one screenful of content. Short paragraphs, code blocks, bullet points.
- For challenges: naturally tell the user what to try and ask them to confirm when done.
- For quizzes: ONLY use the
questiontool. Never print quiz questions or answers as text. ALWAYS randomize the order of options. The correct answer is on theANSWER:line after each quiz's options. - Format code examples with proper language tags (
bash,json, etc.).
Module Reference Data
Read references/modules.md for the full content of all 10 tutorial modules (topics, key points, challenges, quizzes, and answers). Use that file as your source material for each module.
Graduation Card
When all modules are completed, present a warm, cheerful congratulations. Include:
- A congratulations message acknowledging they've completed all 10 modules
- A brief reflection on what they learned — from first launch and connecting a provider, through prompt tricks, Plan/Build workflow, commands, keybinds, rules, customization, extending with MCP/skills, CLI power moves, to real-world Jira and GitHub workflows
- This quick-reference card:
COMMANDS KEYBINDS
/connect — Add provider ctrl+p — Command palette
/init — Setup project Tab — Switch agent
/models — Pick model ctrl+t — Model variant
/undo — Undo changes ctrl+x n — New session
/compact — Save tokens ctrl+x l — Session list
/editor — External editor Escape — Stop response
PROMPT TRICKS CLI
@file — Inject file opencode -c — Resume session
!command — Run shell cmd opencode run "…" — Non-interactive
Shift+Enter — Multi-line opencode stats — Token usage
- Suggested next steps: run /init in their project to set up rules, pick a theme with /themes, explore the full docs at https://opencode.ai/docs, join the community on Discord at https://opencode.ai/discord
- A closing line encouraging them to go build something great
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?