notque/vexjoy-agent / skills/meta/toolkit
toolkit
VerifiedToolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.
references/agent-comparison/socratic-debugging-trigger-tasks.json
View on GitHub[
{
"query": "help me think through this bug step by step",
"should_trigger": true,
"complexity": "simple",
"description": "explicit request for guided reasoning"
},
{
"query": "walk me through debugging this",
"should_trigger": true,
"complexity": "simple",
"description": "guided debugging with user doing the work"
},
{
"query": "I need coaching on how to debug this problem",
"should_trigger": true,
"complexity": "simple",
"description": "coaching/teaching framing"
},
{
"query": "teach me to find the root cause myself",
"should_trigger": true,
"complexity": "simple",
"description": "explicit teach-me framing"
},
{
"query": "guide me to the root cause with questions",
"should_trigger": true,
"complexity": "simple",
"description": "question-based guidance request"
},
{
"query": "rubber duck debug with me",
"should_trigger": true,
"complexity": "simple",
"description": "rubber duck debugging is a known trigger"
},
{
"query": "ask me questions to help me figure out the bug",
"should_trigger": true,
"complexity": "simple",
"description": "explicit ask-me-questions pattern"
},
{
"query": "help me learn to find bugs myself instead of just telling me the answer",
"should_trigger": true,
"complexity": "simple",
"description": "pedagogical debugging preference"
},
{
"query": "just fix this bug for me",
"should_trigger": false,
"complexity": "simple",
"description": "direct fix request, not guided learning"
},
{
"query": "what's wrong with this code",
"should_trigger": false,
"complexity": "simple",
"description": "direct answer expected, not guided"
},
{
"query": "debug this crash and tell me what to change",
"should_trigger": false,
"complexity": "simple",
"description": "wants answer, not coaching"
},
{
"query": "review my code for bugs",
"should_trigger": false,
"complexity": "simple",
"description": "code review, not debugging coaching"
},
{
"query": "run the tests and find what's failing",
"should_trigger": false,
"complexity": "simple",
"description": "automated test run, not guided debugging"
},
{
"query": "investigate this production failure and give me a root cause analysis",
"should_trigger": false,
"complexity": "medium",
"description": "wants RCA output, not teaching"
},
{
"query": "check for performance bugs in this service",
"should_trigger": false,
"complexity": "simple",
"description": "performance audit, not debugging coaching"
},
{
"query": "find the security issue in this authentication code",
"should_trigger": false,
"complexity": "simple",
"description": "security review, not pedagogical debugging"
}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |