28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools
JavaScript agent-skillsai-toolsanthropicclaudeclaude-codecritical-thinkingdecision-makingfirst-principlesmental-modelsproblem-solvingsystems-thinking
{
"skill": "effectuation",
"primary_value_surface": "paired reasoning quality",
"primary_metric": "pairwise_win_rate_vs_placebo",
"secondary_metrics": ["judge_agreement", "format_length_controlled_win_rate", "means_inventory_completeness", "affordable_loss_calibration"],
"distractors": {
"off_target_set": "Goals with clear paths and predictable outcomes; mature markets with established playbooks; optimization problems with known variables; meta-questions about effectuation",
"description": "Items where the future is predictable enough for causal planning, and effectuation's means-driven approach adds no value"
},
"calibration_range": [0.40, 0.70],
"calibration_exception": null,
"min_sample_primary": 80,
"min_sample_replication": 80,
"planned_comparison": "trigger",
"decision_gate": {
"elevate": "primary_delta_pp >= 5 AND paired_test_p < 0.05 AND replication_delta_pp >= 5 AND replication_paired_test_p < 0.05 AND replication_direction_matches_primary AND format_length_control_pass",
"directional_not_replicated": "primary_delta_pp >= 5 AND paired_test_p < 0.05 AND (replication_delta_pp < 5 OR replication_paired_test_p >= 0.05 OR replication_direction_opposite)",
"no_lift": "primary_delta_pp < 5 OR paired_test_p >= 0.05",
"quarantine_redirect": "primary_delta_pp < 0 OR format_length_bias_detected",
"trigger_only": "trigger_card_delta_pp >= full_guide_delta_pp AND trigger_paired_test_p < 0.05",
"ceiling_needs_harder_data": "placebo_baseline > 0.70"
},
"eval_family": "Conceptual reframes"
}