Skip to content

aiskillstore/marketplace / skills/aakashh242/gauntlet

gauntlet

Verified

Evidence-driven adversarial review and root-cause repair of code, designs, APIs, infrastructure, tests, and agent workflows. Use for deep reviews, red-team reviews, edge-case audits, production-readiness checks, or requests to find and fix defects iteratively. Supports sub-agents or a tracked solo workflow. Not for ordinary implementation or cosmetic edits unless explicitly invoked.

evals/triggers.json

View on GitHub
{
  "schema_version": 1,
  "execution_status": "not_run",
  "cases": [
    {
      "prompt": "Use Gauntlet on this architecture.",
      "should_trigger": true
    },
    {
      "prompt": "Adversarially review and fix this patch at the root cause.",
      "should_trigger": true
    },
    {
      "prompt": "Pressure-test this API for edge cases and verify the repairs.",
      "should_trigger": true
    },
    {
      "prompt": "Do a deep production-readiness review of this service.",
      "should_trigger": true
    },
    {
      "prompt": "Review this design for hidden contradictions and failure modes.",
      "should_trigger": true
    },
    {
      "prompt": "Run a red-team review of these agent tool permissions.",
      "should_trigger": true
    },
    {
      "prompt": "Find and fix the bug class, not just this one symptom.",
      "should_trigger": true
    },
    {
      "prompt": "Use gauntlet, but no sub-agents are available.",
      "should_trigger": true
    },
    {
      "prompt": "Review this migration for partial-failure and rollback gaps.",
      "should_trigger": true
    },
    {
      "prompt": "Recursively re-review these fixes within a four-round budget.",
      "should_trigger": true
    },
    {
      "prompt": "Say hello.",
      "should_trigger": false
    },
    {
      "prompt": "Translate this sentence into Bengali.",
      "should_trigger": false
    },
    {
      "prompt": "Change only this heading from old to new.",
      "should_trigger": false
    },
    {
      "prompt": "Explain what a Python list is.",
      "should_trigger": false
    },
    {
      "prompt": "Write a birthday greeting.",
      "should_trigger": false
    },
    {
      "prompt": "Draw a cat logo.",
      "should_trigger": false
    },
    {
      "prompt": "Format this JSON without changing its values.",
      "should_trigger": false
    },
    {
      "prompt": "Add a basic command-line option; no review requested.",
      "should_trigger": false
    },
    {
      "prompt": "Summarize the provided paragraph in one sentence.",
      "should_trigger": false
    },
    {
      "prompt": "What does the word gauntlet mean in medieval armor?",
      "should_trigger": false
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall