Skip to content

MiaoDX/roboclaws / skills/report-performance-analysis

report-performance-analysis

Verified

Use this skill whenever the user asks whether a Roboclaws live-agent report run is faster, wants to compare Agent SDK/Codex/Claude cleanup reports, asks about model-call work, residual latency, speedup validity, or report performance under provider/network variance. The skill extracts sanitized JSON metrics first and answers only from generated metric/comparison artifacts, not from report.html scraping or raw prompts.

FileKindSize
SKILL.mdskill md3.4 KB
references/metric-contract.mdmarkdown1.8 KB
skill.jsonconfig1.8 KB
templates/comparison-manifest.jsonconfig340 B

skill.json

View on GitHub
{
  "schema": "roboclaws_skill_manifest_v1",
  "name": "report-performance-analysis",
  "summary": "Extract and compare sanitized live-agent report performance metrics.",
  "abstraction_level": "agent_skill",
  "role": "artifact_analysis",
  "status": "active",
  "mcp": {
    "profiles": [],
    "required_tools": [],
    "optional_tools": [],
    "privileged_tools": [],
    "boundary_notes": "Post-run report analysis skill. It consumes completed artifacts and does not call robot MCP tools or expose private evaluator truth."
  },
  "capability_requirements": {
    "profiles": [],
    "backend_variants": ["artifact_only"],
    "notes": "Uses completed live-agent run directories, model_call_metrics.jsonl, and report performance packets."
  },
  "scripts": [
    {
      "path": "../../scripts/reports/extract_live_report_metrics.py",
      "kind": "extractor",
      "owner": "repo",
      "summary": "Extract one run's sanitized report performance packet."
    },
    {
      "path": "../../scripts/reports/compare_live_report_metrics.py",
      "kind": "comparison",
      "owner": "repo",
      "summary": "Compare two runs or a manifest of report performance packets."
    },
    {
      "path": "../../scripts/reports/calibrate_model_latency.py",
      "kind": "calibration",
      "owner": "repo",
      "summary": "Build calibration data for normalized model-latency estimates."
    }
  ],
  "evidence_outputs": [
    "roboclaws_report_performance_metrics_v1",
    "roboclaws_report_performance_comparison_v1"
  ],
  "lifecycle": {
    "refactor_signals": [
      "metric extraction starts duplicating live-report parsing code",
      "comparison packets need a stable schema consumed by CI or dashboards"
    ],
    "promote_to_mcp_when": [
      "never by default; report-performance analysis is post-run artifact analysis, not a robot capability"
    ]
  }
}
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: 471kUpdated 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