ReddRadar
Agent skill
comprehensive-validation
Language, style, and comment quality guidelines for plugin content
Install this agent skill to your Project
npx add-skill https://github.com/chkim-su/forge-editor/tree/main/skills/comprehensive-validation
SKILL.md
Comprehensive Validation
Guidelines for content quality: language usage, emoji placement, and comment hygiene.
Core Principle
English for LLM consumption, localized text only for user-facing output.
When to Use
- Before
plugin_publishworkflow - When W037 (Korean) or W038 (emoji) warnings appear
- Reviewing documentation quality
- Cleaning up debug artifacts
Quick Reference
| Content Type | Rule | Example |
|---|---|---|
| Skill/Agent descriptions | English only | description: "Analyze code quality" |
| Code comments | English only | # Check file existence |
| CLI output (print/console.log) | OK to localize | print("Success") or print("OK") |
| Error messages in exceptions | English preferred | raise ValueError("Invalid input") |
| Frontmatter fields | English only | Never use emoji/Korean in YAML |
| Markdown headers | English preferred | ## Process not ## 프로세스 |
Validation Codes
| Code | Check | Enforcement |
|---|---|---|
| W037 | Korean in non-localized content | Warning (BLOCKING for publish) |
| W038 | Emoji in inappropriate locations | Warning (BLOCKING for publish) |
Enforcement Levels
| Workflow | W037/W038 |
|---|---|
skill_creation |
WARNING |
agent_creation |
WARNING |
command_creation |
WARNING |
plugin_publish |
BLOCKING |
quick_fix |
WARNING |
analyze_only |
WARNING |
Cleanup Commands
# Run validation to detect issues
python3 scripts/validate_all.py . --content-quality
# Detailed semantic analysis (uses content-quality-analyzer agent)
# Requires Task tool invocation with form-selection-auditor
References
references/language-guidelines.md- When Korean vs Englishreferences/style-guidelines.md- Emoji and formatting rulesreferences/comment-hygiene.md- TODO/FIXME/debug code rules
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
chkim-su/forge-editor
forge-analyzer
Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories. Front-end for clarifying ambiguous requests before routing to appropriate skillmaker tools.
chkim-su/forge-editor
hook-system
Claude Code Hook system entry point. Guides you to the right skill based on your needs.
chkim-su/forge-editor
mcp-gateway-patterns
MCP Gateway design patterns for Agent Gateway, Subprocess, and Daemon isolation. Use when designing MCP integrations.
chkim-su/forge-editor
workflow-state-patterns
Hook-based state machine patterns for multi-phase workflows. Use when designing sequential workflows with quality gates.
chkim-su/forge-editor
mcp-daemon-isolation
Context isolation for query-type MCP tools (LSP, search, database) via external CLI. Use when MCP query results consume too many context tokens.
chkim-su/forge-editor
critical-analysis-patterns
Philosophical/meta project analysis - critical analysis framework that asks "why?"
Didn't find tool you were looking for?