{
  "skill_name": "plastic-intent-planning",
  "notes": "Intent 164, updated by 133a. Evals for the writing-plans skill: action-file enforcement at every tier (S/M consolidate the delivery into one real actions/ACTION_1.md, L writes one actions/ACTION_N.md per task) and the checklist FORM plus [ORCHESTRATOR] hard-gate item convention. All assertions are pending a real observed run per the plastic-evaluating-skills convention.",
  "evals": [
    {
      "id": 1,
      "scope": "behavior",
      "set": "train",
      "prompt": "spec.md is stamped Tier: M and describes a single subsystem change touching four files across two tasks. Write the plan.",
      "expected_output": "Produces plan.md plus checklist.md plus at least one real actions/ACTION_N.md. At M the planner consolidates the whole delivery into a single actions/ACTION_1.md (it may split into a few files if that reads cleaner); the actions/ directory is never left empty or .gitkeep-only. checklist.md mirrors plan.md's task list.",
      "files": [],
      "assertions": [
        {
          "type": "code",
          "check": "at least one real (non-empty, non-.gitkeep) file exists under actions/ for this intent; checklist.md exists and mirrors plan.md's task list",
          "result": "expect-pass"
        }
      ]
    },
    {
      "id": 2,
      "scope": "behavior",
      "set": "train",
      "prompt": "spec.md is stamped Tier: S and describes a single-file config change. Write the plan.",
      "expected_output": "Produces plan.md plus checklist.md plus one consolidated actions/ACTION_1.md carrying the whole ordered delivery (the steps plus the exact changes). The actions/ directory is never left empty or .gitkeep-only, matching the every-tier action-file rule.",
      "files": [],
      "assertions": [
        {
          "type": "code",
          "check": "at least one real (non-empty, non-.gitkeep) actions/ACTION_N.md exists under actions/ for this intent; no empty or .gitkeep-only actions/ dir remains",
          "result": "expect-pass"
        }
      ]
    },
    {
      "id": 3,
      "scope": "behavior",
      "set": "train",
      "prompt": "spec.md is stamped Tier: L and describes a cross-cutting redesign decomposed into eight independent tasks meant to be dispatched to separate subagents in parallel. Write the plan.",
      "expected_output": "Produces self-contained actions/ACTION_N.md, one file per task, each readable without the plan (full task text, code, and commands copied in). checklist.md has one item per task.",
      "files": [],
      "assertions": [
        {
          "type": "code",
          "check": "actions/ directory contains one ACTION_N.md per task; each action file is self-contained (no bare references like \"see Task 3\" without the content)",
          "result": "expect-pass"
        }
      ]
    },
    {
      "id": 4,
      "scope": "behavior",
      "set": "validation",
      "prompt": "spec.md names an owner decision (whether to delete or archive a legacy table) that must be ruled on before any code edit in the plan can proceed. Write the plan.",
      "expected_output": "checklist.md includes a checklist item prefixed [ORCHESTRATOR] that names the owner decision and states it blocks all code edits until the owner rules; this item is ordered before the sweeping edit tasks that depend on it. checklist.md follows the FORM: ## In Progress, ## Completed (empty), ## Session Log with Date | Items Completed | Notes columns.",
      "files": [],
      "assertions": [
        {
          "type": "human",
          "check": "an [ORCHESTRATOR] item exists, names the decision, states it blocks code edits, and precedes dependent tasks; checklist.md has the three FORM sections in the right shape",
          "result": "expect-pass"
        }
      ]
    },
    {
      "id": 5,
      "scope": "behavior",
      "set": "validation",
      "prompt": "spec.md is stamped Tier: S. A prior draft left actions/ with only a .gitkeep. Write the plan and its actions.",
      "expected_output": "Writes at least one real actions/ACTION_1.md (non-empty, not the placeholder sentinel, not a .gitkeep) that consolidates the whole S-tier delivery. Leaving actions/ empty or .gitkeep-only is a plan failure that would block the How gate; the planner never does this at any tier.",
      "files": [],
      "assertions": [
        {
          "type": "code",
          "check": "actions/ contains at least one real action file (non-empty *.md, first line not the placeholder sentinel); no .gitkeep-only or empty actions/ dir remains",
          "result": "expect-pass"
        }
      ]
    }
  ]
}