Skip to content

zwright8/OpenClaw-Code / skills/generated/0021-epistemic-plan-quality-evaluator

u0021-epistemic-plan-quality-evaluator

Verified

Build and operate the "Epistemic Plan Quality Evaluator" capability for Truth-Seeking and Epistemics. Trigger when this exact capability is needed in mission execution.

FileKindSize
SKILL.mdskill md3.1 KB
implementation.jsonconfig3.8 KB

implementation.json

View on GitHub
{
  "version": 1,
  "sourceFile": "SKILL_UPDATES_1000.md",
  "skillId": 21,
  "skillName": "u0021-epistemic-plan-quality-evaluator",
  "title": "Epistemic Plan Quality Evaluator",
  "domain": "Truth-Seeking and Epistemics",
  "domainSlug": "truth-seeking-and-epistemics",
  "reason": "We need this skill because decisions drift when claims are accepted without verification. This specific skill quantifies whether plans are complete, safe, and feasible.",
  "implementationGuide": [
    "Define the scope and success metrics for `Epistemic Plan Quality Evaluator`, including at least three measurable KPIs tied to false certainty and unverified assumptions.",
    "Design and version the input/output contract for claims, evidence, and confidence traces, then add schema validation and failure-mode handling.",
    "Implement the core capability using multi-criteria plan scoring, and produce plan quality scorecards with deterministic scoring.",
    "Integrate the skill into swarm orchestration: task routing, approval gates, retry strategy, and rollback controls.",
    "Add unit, integration, and simulation tests that explicitly cover false certainty and unverified assumptions, then run regression baselines.",
    "Deploy behind a feature flag, monitor telemetry/alerts for two release cycles, and iterate thresholds based on observed outcomes."
  ],
  "runtimeProfile": {
    "archetype": "general-capability",
    "coreMethod": "multi-criteria plan scoring",
    "primaryArtifact": "plan quality scorecards",
    "requiredSignals": [
      "claims",
      "evidence",
      "confidence traces"
    ],
    "kpiFocus": [
      "false certainty",
      "unverified assumptions",
      "decision drift"
    ],
    "scoringWeights": {
      "truth": 0.3196,
      "execution": 0.1532,
      "safety": 0.3296,
      "impact": 0.1976
    },
    "postureThresholds": {
      "readyMin": 73,
      "reviewMin": 53,
      "reviewRisk": 48,
      "criticalRisk": 87
    },
    "orchestration": {
      "routingTag": "truth-seeking-and-epistemics:general-capability",
      "approvalGates": [
        "policy-constraint-check",
        "human-approval-router"
      ],
      "retryPolicy": {
        "maxAttempts": 4,
        "baseDelayMs": 750,
        "backoff": "exponential"
      },
      "rollbackStrategy": "rollback-to-last-stable-baseline",
      "components": [
        "task routing",
        "approval gates",
        "retry strategy",
        "rollback controls"
      ]
    },
    "validation": {
      "suites": [
        "unit",
        "integration",
        "simulation",
        "regression-baseline"
      ],
      "baselineRequired": true
    },
    "rollout": {
      "featureFlag": "skill_0021_epistemic-plan-quality-evaluator",
      "releaseCycles": 2,
      "telemetryAlerts": true
    },
    "scoringSeed": "u0021-epistemic-plan-quality-evaluator:21:general-capability"
  },
  "traceability": {
    "scopeStep": "Define the scope and success metrics for `Epistemic Plan Quality Evaluator`, including at least three measurable KPIs tied to false certainty and unverified assumptions.",
    "contractStep": "Design and version the input/output contract for claims, evidence, and confidence traces, then add schema validation and failure-mode handling.",
    "coreStep": "Implement the core capability using multi-criteria plan scoring, and produce plan quality scorecards with deterministic scoring.",
    "orchestrationStep": "Integrate the skill into swarm orchestration: task routing, approval gates, retry strategy, and rollback controls.",
    "validationStep": "Add unit, integration, and simulation tests that explicitly cover false certainty and unverified assumptions, then run regression baselines.",
    "rolloutStep": "Deploy behind a feature flag, monitor telemetry/alerts for two release cycles, and iterate thresholds based on observed outcomes."
  }
}
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 197kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall