notque/vexjoy-agent / skills/meta/toolkit
toolkit
VerifiedToolkit management: create and evaluate skills and agents, manage routing tables, generate Claude.md.
references/agent-comparison/do-creation-compliance-tasks.json
View on GitHub{
"tasks": [
{
"name": "create-agent-prometheus",
"split": "train",
"complexity": "complex",
"query": "create a new Prometheus alerting agent",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "scaffold-skill-migration",
"split": "train",
"complexity": "complex",
"query": "scaffold a new skill for database migration safety",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "build-pipeline-security",
"split": "train",
"complexity": "complex",
"query": "build a pipeline for automated security scanning",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "create-hook-sql",
"split": "train",
"complexity": "simple",
"query": "create a PostToolUse hook that detects SQL injection patterns",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "new-feature-webhooks",
"split": "train",
"complexity": "complex",
"query": "new feature: add webhook support for deployment notifications",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "scaffold-perses-plugin",
"split": "train",
"complexity": "complex",
"query": "scaffold a Perses dashboard plugin with CUE schema and React component",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "implicit-create-rails-agent",
"split": "train",
"complexity": "simple",
"query": "I need an agent for Ruby on Rails development",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "add-linting-pipeline",
"split": "train",
"complexity": "simple",
"query": "add a new linting pipeline to the toolkit",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "new-voice-profile",
"split": "train",
"complexity": "complex",
"query": "create a new voice profile from my blog writing samples",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "build-agent-rust",
"split": "train",
"complexity": "simple",
"query": "build a Rust development agent with cargo integration",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "create-reviewer-agent",
"split": "test",
"complexity": "complex",
"query": "create a new code review agent focused on accessibility compliance",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "scaffold-etl-pipeline",
"split": "test",
"complexity": "complex",
"query": "scaffold an ETL pipeline skill with data validation phases",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "new-session-hook",
"split": "test",
"complexity": "simple",
"query": "new SessionStart hook that loads team configuration from a YAML file",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "create-monitoring-skill",
"split": "test",
"complexity": "simple",
"query": "create a skill for monitoring Kubernetes pod health across namespaces",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "build-terraform-agent",
"split": "test",
"complexity": "complex",
"query": "build a Terraform infrastructure agent with plan-apply-verify phases",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "implicit-create-java-skill",
"split": "test",
"complexity": "simple",
"query": "we need a Java Spring Boot development skill",
"should_trigger": true,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-debug-go-tests",
"split": "train",
"complexity": "complex",
"query": "debug why the Go tests are failing in CI",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-review-pr-security",
"split": "train",
"complexity": "complex",
"query": "review this PR for security issues",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-optimize-db",
"split": "train",
"complexity": "simple",
"query": "optimize the database query performance",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-explain-routing",
"split": "train",
"complexity": "simple",
"query": "explain how the routing system works",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-update-errors",
"split": "train",
"complexity": "simple",
"query": "update the error messages in the auth handler",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-research-rbac",
"split": "train",
"complexity": "complex",
"query": "research best practices for Kubernetes RBAC",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-check-ci",
"split": "train",
"complexity": "simple",
"query": "check the CI status on this branch",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-fix-import",
"split": "train",
"complexity": "simple",
"query": "fix the broken import in agents/INDEX.json",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-refactor-middleware",
"split": "train",
"complexity": "complex",
"query": "refactor the authentication middleware to use context propagation",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-run-tests",
"split": "train",
"complexity": "simple",
"query": "run the Python quality gate on the scripts directory",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-check-coverage",
"split": "test",
"complexity": "simple",
"query": "check test coverage for the voice validation module",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-deploy-staging",
"split": "test",
"complexity": "complex",
"query": "deploy the latest version to the staging environment",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-audit-deps",
"split": "test",
"complexity": "simple",
"query": "audit dependencies for known CVEs in the Python packages",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-compare-agents",
"split": "test",
"complexity": "complex",
"query": "compare the golang-general-engineer and golang-compact agents on error handling tasks",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-investigate-memory-leak",
"split": "test",
"complexity": "complex",
"query": "investigate the memory leak in the webhook processing service",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
},
{
"name": "neg-merge-pr",
"split": "test",
"complexity": "simple",
"query": "merge PR 205 after CI passes",
"should_trigger": false,
"eval_mode": "behavioral",
"artifact_glob": "adr/*.md"
}
]
}
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: 471k | 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 |