abilityai/trinity-skills/self-diagnostic
Claude Code and agent skill by abilityai/trinity-skills
- community
Checking that the SKILL.md file is still in the repository.
Run self-diagnostics on the agent to verify skills, commands, agents, and dependencies are working. Use when troubleshooting, after configuration changes, or for regular health checks.
Install
npx vskill@latest install abilityai/trinity-skills/self-diagnosticSKILL.md
Agent Self-Diagnostic
Run comprehensive diagnostics to verify all agent components are functioning correctly.
Quick Start
Run full diagnostics:
Run specific test category:
Arguments
$ARGUMENTS
Safety Principles
CRITICAL: These diagnostics are READ-ONLY and NEVER modify data.
- All tests use read-only operations (list, read, check)
- NO file creation during tests
- NO API calls to paid services
- Test outputs go to
/tmp/agent-diagnostic/only
Diagnostic Categories
1. Infrastructure Tests
Verify core directories exist:
2. Dependency Tests
Verify external dependencies are installed:
3. Skills Validation Tests
Verify skills are properly configured:
4. Commands Validation Tests
Verify commands are properly configured:
5. Agents Validation Tests
Verify sub-agents are properly configured:
Output Format
Present results as:
Argument Handling
Based on $ARGUMENTS:
- No arguments or "full": Run all tests
- "skills-only": Only test skills validation
- "commands-only": Only test commands validation
- "agents-only": Only test agents validation
- "dependencies-only": Only test infrastructure + dependencies
- "quick": Only run validation tests (skip functional)
Extending This Diagnostic
To add custom tests for your agent:
- Create a
custom-tests.shin this skill directory - The diagnostic will source and run it if present
- Use the same PASS/FAIL/INFO output format
Example custom test:
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/self-diagnostic/SKILL.md
Popularity
- Repository forks
- 1
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/abilityai/trinity-skills/self-diagnostic)