Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/Testing & QA
joshuadavidthomas avatar

Test Skill

joshuadavidthomas/opencode-agent-skills

This is purely a testing utility for developers building or debugging Claude Code skills. It's designed to verify that all four plugin API methods work correctly: use_skill, read_skill_file, run_skill_script, and find_skills. You get a handful of sample files (markdown docs, a JSON config) and basic scripts (one that greets, another that echoes arguments back) to confirm your integration is wired up properly. It's not meant for production work. If you're building skills or troubleshooting the plugin system, this gives you a quick sanity check. Otherwise, you won't need it.

GitHub stars
229
last updated
May 9, 2026
View on GitHubSave

Install

$ npx -y skills add joshuadavidthomas/opencode-agent-skills --skill test-skill --agent claude-code

Installs into .claude/skills of the current project.

Files

Test Skill

This skill exists to verify the OpenCode Skills Plugin API works correctly.

Testing Checklist

Use this skill to verify:

  1. use_skill - You're reading this, so it works!
  2. read_skill_file - Load example-config.json or helper-docs.md
  3. run_skill_script - Execute greet or echo-args scripts
  4. find_skills - Should list this skill and others

Available Files

  • SKILL.md - This file (the main skill content)
  • helper-docs.md - Additional documentation to test read_skill_file
  • example-config.json - Sample config file to test non-markdown loading
  • scripts/greet - Simple script that prints a greeting
  • scripts/echo-args - Script that echoes back its arguments

Example Workflow

1. find_skills              # List available skills
2. use_skill test-skill     # Load this skill (you're here!)
3. read_skill_file test-skill helper-docs.md    # Load supporting docs
4. run_skill_script test-skill greet            # Run a script
5. run_skill_script test-skill echo-args --foo bar  # Run with args

Expected Outputs

When everything works:

  • use_skill returns "Skill 'test-skill' loaded." with scripts listed
  • read_skill_file returns "File 'X' from skill 'test-skill' loaded."
  • run_skill_script greet returns "Hello from test-skill!"
  • run_skill_script echo-args returns the arguments passed to it
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/joshuadavidthomas/opencode-agent-skills
Categories
Testing & QA, AI & Agent Building, Automation & Workflows
License
MIT
First seen
Jun 11, 2026

More from joshuadavidthomas/opencode-agent-skills

All 2
  • Git Helper

Recommended

More Testing & QA
1laolaoshiren avatartest-generatorlaolaoshiren/claude-code-skills-zh自动生成单元测试:识别函数逻辑、覆盖边界条件、生成可运行测试代码0installs
2microsoft avatarplaywright-rollmicrosoft/playwright-pythonRoll Playwright Python to a new version0installs
3microsoft avatarinvestigate-integration-testmicrosoft/github-copilot-for-azureInvestigate a failing integration test from a GitHub issue. Downloads logs/artifacts, analyzes the failure, examines relevant skills, and suggests fixes. TRIGGE0installs
4nkeonye-akumah avatartest-with-spannernkeonye-akumah/decentralized-storage-gatewayRun unit tests that require the Spanner emulator. Use this skill when the user wants to run tests in packages like satellite/metabase, satellite/metainfo, or an0installs
5odradekai avatartestingodradekai/bundles-forgeThis is the runtime counterpart to auditing.0installs
6odradekai avatarusing-testodradekai/bundles-forgeThis is essentially a discovery tool that runs at session start to show you what skills are available in your environment.0installs