Skip to content

MiaoDX/roboclaws / skills/eval-evolution

eval-evolution

Verified

Prepare, run, review, and explicitly promote bounded Skill or existing-MCP Eval Evolution campaigns through the canonical eval facade.

FileKindSize
SKILL.mdskill md3.6 KB
skill.jsonconfig1.2 KB

skill.json

View on GitHub
{
  "schema": "roboclaws_skill_manifest_v1",
  "name": "eval-evolution",
  "summary": "Prepare, run, review, and explicitly promote bounded eval-driven Skill and existing-MCP campaigns.",
  "abstraction_level": "agent_skill",
  "role": "eval_orchestration",
  "status": "active",
  "mcp": {
    "profiles": [],
    "required_tools": [],
    "optional_tools": [],
    "privileged_tools": [],
    "boundary_notes": "This maintainer workflow exposes no robot capability and never gives optimizer agents private eval truth, shell, filesystem, git, network, or launch tools."
  },
  "capability_requirements": {
    "profiles": [],
    "backend_variants": [],
    "notes": "Live campaigns require the frozen OpenAI Agents SDK providers, product runtime, eval suites, and execution placement named by the campaign."
  },
  "evidence_outputs": [
    "candidate-summary.json",
    "selection-report.json",
    "candidates/by-sha256/<digest>/candidate.json"
  ],
  "lifecycle": {
    "refactor_signals": [
      "campaign orchestration escapes roboclaws.evals",
      "optimizer-visible tools expand beyond the three bounded functions",
      "selection or promotion policy diverges by target class"
    ],
    "promote_to_mcp_when": []
  }
}
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: 470kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall