yao-meta-skill/reports/prompt-quality-profile.json

{
  "skill_name": "yao-meta-skill",
  "relevance": "prompt-heavy",
  "primary_task_family": {
    "key": "execution_operation",
    "label": "Execution operation",
    "matched_keywords": [
      "workflow",
      "runbook"
    ]
  },
  "task_families": [
    {
      "key": "execution_operation",
      "label": "Execution operation",
      "score": 2,
      "matched_keywords": [
        "workflow",
        "runbook"
      ],
      "role_guidance": "Use an operator role with explicit boundaries, inputs, outputs, and failure handling.",
      "task_guidance": "Convert the job into ordered steps with validation checks and stop conditions.",
      "format_guidance": "Return a runbook-like handoff with commands, checks, owners, and next actions when relevant."
    },
    {
      "key": "dialogue_interaction",
      "label": "Dialogue interaction",
      "score": 2,
      "matched_keywords": [
        "dialogue",
        "conversation"
      ],
      "role_guidance": "Use a conversational role that asks only high-leverage questions and remembers the user's goal.",
      "task_guidance": "Clarify intent, resolve uncertainty, and converge toward a recommendation instead of a long option list.",
      "format_guidance": "Return concise prompts, decision points, and reviewer-visible assumptions."
    },
    {
      "key": "creative_generation",
      "label": "Creative generation",
      "score": 1,
      "matched_keywords": [
        "content"
      ],
      "role_guidance": "Use a taste-aware creator role with clear audience, tone, and originality boundaries.",
      "task_guidance": "Generate variants, explain selection logic, and preserve the user's distinctive constraints.",
      "format_guidance": "Return options with rationale, selection criteria, and refinement paths."
    },
    {
      "key": "prompt_engineering",
      "label": "Prompt engineering",
      "score": 1,
      "matched_keywords": [
        "prompt"
      ],
      "role_guidance": "Use a prompt engineer role only when role design materially improves execution.",
      "task_guidance": "Map Role, Task, and Format into skill behavior rather than copying a large prompt template.",
      "format_guidance": "Return a compact prompt contract plus tests, quality matrix, and usage notes."
    }
  ],
  "complexity": {
    "band": "expert",
    "score": 27,
    "reason": "multiple task families plus governance, evaluation, or expert-level constraints"
  },
  "need_model": {
    "explicit_need": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
    "implicit_need": "The reusable skill needs a stable role, task, and output contract rather than a one-off prompt.",
    "scenario": "rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions, an existing skill directory that needs refactor, evaluation, packaging, or governance hardening, target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution, benchmark references, local constraints, desired maturity tier, and review standards",
    "user_level": "infer from examples and standards; ask only if it changes output depth",
    "success_standard": "trigger boundaries must be tested with should-trigger and should-not-trigger cases, production and higher maturity work needs output eval, trust, runtime conformance, and Review Studio evidence, governed work needs owner, review cadence, permission approvals, registry metadata, package verification, and install simulation, generated reports should be bilingual or reviewer-friendly when they are user-facing, each new asset must earn its place by reducing ambiguity, risk, or repeated work"
  },
  "rtf_to_skill": {
    "role": "Use an operator role with explicit boundaries, inputs, outputs, and failure handling.",
    "task": "Convert the job into ordered steps with validation checks and stop conditions.",
    "format": "Return a runbook-like handoff with commands, checks, owners, and next actions when relevant."
  },
  "quality_matrix": [
    {
      "key": "completeness",
      "label": "Completeness",
      "score": 100,
      "matched_signals": [
        "output",
        "constraint",
        "standard"
      ],
      "repair": "Name missing inputs, outputs, constraints, or success standards before deepening the package."
    },
    {
      "key": "clarity",
      "label": "Clarity",
      "score": 85,
      "matched_signals": [
        "clear"
      ],
      "repair": "Replace broad verbs with observable actions and define what done means."
    },
    {
      "key": "consistency",
      "label": "Consistency",
      "score": 90,
      "matched_signals": [
        "aligned",
        "boundary"
      ],
      "repair": "Check that role, task, format, exclusions, and examples do not contradict each other."
    },
    {
      "key": "practicality",
      "label": "Practicality",
      "score": 90,
      "matched_signals": [
        "use",
        "workflow"
      ],
      "repair": "Add runnable steps, examples, or verification cues instead of abstract advice."
    },
    {
      "key": "specificity",
      "label": "Specificity",
      "score": 80,
      "matched_signals": [],
      "repair": "Anchor wording in the user's audience, domain nouns, and target outcome."
    }
  ],
  "overall_quality_score": 89.0,
  "self_repair_checks": [
    "Check explicit need, implicit need, scenario, user level, and success standard before deepening.",
    "Map Role, Task, and Format into skill behavior, not decorative prompt labels.",
    "Ask one focused clarification only when missing information changes the package boundary.",
    "Add tests or examples for prompt-heavy behavior before treating it as reusable.",
    "Keep prompt methodology in references and reports instead of bloating SKILL.md."
  ],
  "reviewer_note": "Use this profile when the package depends on prompt behavior, role design, output contracts, or conversation quality."
}