Test Skill
A test skill to verify all plugin tools work correctly - use_skill, read_skill_file, run_skill_script, find_skills
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/joshuadavidthomas/opencode-agent-skills --skill test-skillThe instruction itself
5 sections, as written by the authorTest Skill
This skill exists to verify the OpenCode Skills Plugin API works correctly.
Testing Checklist
Use this skill to verify:
- use_skill - You're reading this, so it works!
- read_skill_file - Load
example-config.jsonorhelper-docs.md - run_skill_script - Execute
greetorecho-argsscripts - 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_fileexample-config.json- Sample config file to test non-markdown loadingscripts/greet- Simple script that prints a greetingscripts/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_skillreturns "Skill 'test-skill' loaded." with scripts listedread_skill_filereturns "File 'X' from skill 'test-skill' loaded."run_skill_script greetreturns "Hello from test-skill!"run_skill_script echo-argsreturns the arguments passed to it
Other skills for the same job
different authors, same section of the catalogue
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
Use when working with error debugging multi agent review
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.
Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.
Use when working with error debugging multi agent review
Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.
Ultimate multi-agent framework for Google Antigravity. Orchestrates specialized domain agents (PM, Frontend, Backend, Mobile, QA, Debug) via Serena Memory.
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
How to use it
Take joshuadavidthomas/test-skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.