Structured debugging workflow. Only when user explicitly asks for help debugging.
Provides structured debugging workflow when user explicitly requests help. Uses systematic approach: observe outputs, reproduce issue, isolate scope, investigate evidence, apply targeted fix, and verify with CI before committing.
/plugin marketplace add settlemint/agent-marketplace/plugin install devtools@settlemintThis skill inherits all available tools. When active, it can use any tool Claude has access to.
<quick_start> Debugging workflow:
<observe_before_editing> CRITICAL: Confirm what the system actually produced before editing code.
Outputs don't lie. Code might. Check outputs first.
# Check if expected files were created
ls -la [path]
# Check logs for errors
tail [logfile]
# Run the failing command manually to see actual error
<command>
# Verify the issue exists before fixing it
DON'T:
<quality_gate> MANDATORY: Run CI before every commit. No exceptions.
# Full quality gate (REQUIRED before any commit)
bun run ci
# Auto-fix issues
bunx biome check --write
bunx prettier --write
# Shell scripts
shellcheck <file>
shfmt -w <file>
DON'T:
<common_issues> Build failures:
# Clear all caches
rm -rf node_modules .next dist .turbo
bun install
bun run build
Type errors:
# Regenerate types
bun run typecheck
# Check for missing dependencies
bun install
Database issues:
# Reset database
bun run db:push
# Check migrations
bun run db:migrate
# View in studio
bun run db:studio
API errors:
# Check server logs
# Verify environment variables
# Test endpoint directly with curl
curl -X POST http://localhost:3000/api/route -H "Content-Type: application/json" -d '{}'
</common_issues>
<debugging_tools> TypeScript:
console.log strategicallybun run typecheckReact:
Database:
.toSQL()Network:
Blockchain:
<error_patterns> "Module not found":
"Type X is not assignable to Y":
"ECONNREFUSED":
"Hydration mismatch":
<investigation_strategy>
git diff what changed<simplicity_first> Always prefer the simplest change possible.
DO:
_unused prefixes)DON'T:
<mcp_for_debugging> Use MCP to research error patterns:
// Search for similar issues
mcp__octocode__githubSearchCode({
keywordsToSearch: ["error message keywords"],
owner: "relevant-org",
repo: "relevant-repo",
path: "issues",
mainResearchGoal: "Find similar reported issues",
researchGoal: "Get solutions from issues",
reasoning: "May find documented fix",
});
// Get current documentation
mcp__context7__query_docs({
libraryId: "/library/id",
query: "How do I handle errors and troubleshoot common issues?",
});
</mcp_for_debugging>
<success_criteria>
bun run ci)This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.