terraphim/terraphim-ai-desktop/post-llm-check
Claude Code and agent skill by terraphim/terraphim-ai-desktop
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Install
npx vskill@latest install terraphim/terraphim-ai-desktop/post-llm-checkSKILL.md
The same SKILL.md was published earlier as terraphim/terraphim-ai/post-llm-check.
Post-LLM Checklist Validation
Use this skill to validate LLM outputs against domain checklists. Ensures outputs meet required standards before acceptance.
When to Use
- After receiving LLM-generated code or content
- To verify domain compliance (security, code review, etc.)
- As a quality gate before committing AI-generated changes
- To ensure AI outputs follow project standards
Available Checklists
code_review
Validates code-related outputs for:
- ✓ tests - Test coverage mentioned/included
- ✓ documentation - Docs or comments present
- ✓ error_handling - Error handling addressed
- ✓ security - Security considerations noted
- ✓ performance - Performance implications considered
security
Validates security-related outputs for:
- ✓ authentication - Auth mechanisms present
- ✓ authorization - Access control addressed
- ✓ input_validation - Input sanitization included
- ✓ encryption - Data protection considered
- ✓ logging - Audit logging mentioned
Validation Commands
Validate Against Code Review Checklist
Output:
Validate Against Security Checklist
Workflow Example
Integration with Hooks
Automate via post-tool-use hook:
Best Practices
- Choose Appropriate Checklist: Match checklist to output type
- Iterative Refinement: If validation fails, prompt LLM for specific improvements
- Combine Checklists: Run multiple validations for critical outputs
- Document Exceptions: When skipping validation, document the reason
Custom Checklists
Add custom checklists in docs/src/kg/checklists/:
Then use: terraphim-agent validate --checklist my_checklist "text"
Security
- Security scanPassed, 95 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/post-llm-check/skill.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
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/terraphim/terraphim-ai-desktop/post-llm-check)