Skip to content

aiskillstore/marketplace / skills/92bilal26/content-evaluation-framework

content-evaluation-framework

Verified

This skill should be used when evaluating the quality of book chapters, lessons, or educational content. It provides a systematic 6-category rubric with weighted scoring (Technical Accuracy 30%, Pedagogical Effectiveness 25%, Writing Quality 20%, Structure & Organization 15%, AI-First Teaching 10%, Constitution Compliance Pass/Fail) and multi-tier assessment (Excellent/Good/Needs Work/Insufficient). Use this during iterative drafting, after content completion, on-demand review requests, or before validation phases.

FileKindSize
SKILL.mdskill md11.9 KB
references/constitution-checklist.mdmarkdown18.6 KB
references/evaluation-template.mdmarkdown14.0 KB
references/rubric-details.mdmarkdown25.6 KB
skill-report.jsonconfig34.2 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-05T15:01:11.481Z",
    "slug": "92bilal26-content-evaluation-framework",
    "source_url": "https://github.com/92Bilal26/TaskPilotAI/tree/main/.claude/skills/content-evaluation-framework",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "c91e7941b416b9cc8f7ec6b798480f9c2c926cf7dbb00ba6d437d1724ca70bd6",
    "tree_hash": "9e050d593f7b47368917f84fa5382633bf49784cf3960afe7e99c9061569d7e1",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "content-evaluation-framework",
    "description": "Evaluate educational chapters, lessons, and drafts with a weighted rubric, constitution checklist, and structured reporting template.",
    "summary": "Review educational content with a structured rubric and evidence-based recommendations.",
    "icon": "📦",
    "version": "2.1.1",
    "author": "92Bilal26",
    "license": "MIT",
    "tags": [
      "content-review",
      "education",
      "rubric",
      "quality-assurance",
      "lesson-planning"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands"
    ],
    "category": "writing"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All static findings were adjudicated as false positives after reviewing the cited context. The apparent command, reconnaissance, and sensitive-file matches are Markdown fences, inline paths, readability metrics, and checklist text. No semantic prompt injection, data exfiltration, or hidden unsafe intent was found.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 62,
            "line_end": 65
          },
          {
            "file": "SKILL.md",
            "line_start": 65,
            "line_end": 75
          },
          {
            "file": "SKILL.md",
            "line_start": 75,
            "line_end": 76
          },
          {
            "file": "SKILL.md",
            "line_start": 76,
            "line_end": 78
          },
          {
            "file": "SKILL.md",
            "line_start": 78,
            "line_end": 84
          },
          {
            "file": "SKILL.md",
            "line_start": 84,
            "line_end": 86
          },
          {
            "file": "SKILL.md",
            "line_start": 86,
            "line_end": 96
          },
          {
            "file": "SKILL.md",
            "line_start": 96,
            "line_end": 98
          },
          {
            "file": "SKILL.md",
            "line_start": 98,
            "line_end": 110
          },
          {
            "file": "SKILL.md",
            "line_start": 110,
            "line_end": 120
          },
          {
            "file": "SKILL.md",
            "line_start": 120,
            "line_end": 123
          },
          {
            "file": "SKILL.md",
            "line_start": 123,
            "line_end": 137
          },
          {
            "file": "SKILL.md",
            "line_start": 137,
            "line_end": 139
          },
          {
            "file": "SKILL.md",
            "line_start": 139,
            "line_end": 241
          },
          {
            "file": "SKILL.md",
            "line_start": 241,
            "line_end": 242
          },
          {
            "file": "SKILL.md",
            "line_start": 242,
            "line_end": 243
          },
          {
            "file": "SKILL.md",
            "line_start": 243,
            "line_end": 251
          },
          {
            "file": "SKILL.md",
            "line_start": 251,
            "line_end": 255
          },
          {
            "file": "SKILL.md",
            "line_start": 255,
            "line_end": 257
          },
          {
            "file": "SKILL.md",
            "line_start": 257,
            "line_end": 259
          },
          {
            "file": "SKILL.md",
            "line_start": 259,
            "line_end": 269
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "sensitive:references/constitution-checklist.md:178:environment-file-access",
        "category": "sensitive",
        "severity": "high",
        "pattern": "Environment file access",
        "file": "references/constitution-checklist.md",
        "line_start": 178,
        "line_end": 178,
        "snippet": "- [ ] File organization matches professional conventions (src/, tests/, history/, .env) where applic"
      },
      {
        "id": "blocker:references/constitution-checklist.md:262:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/constitution-checklist.md",
        "line_start": 262,
        "line_end": 262,
        "snippet": "### For Hybrid Chapters (Mixed Content)"
      },
      {
        "id": "blocker:references/constitution-checklist.md:422:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/constitution-checklist.md",
        "line_start": 422,
        "line_end": 422,
        "snippet": "- [ ] Cross-references valid and accurate"
      },
      {
        "id": "blocker:references/constitution-checklist.md:490:network-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "Network reconnaissance",
        "file": "references/constitution-checklist.md",
        "line_start": 490,
        "line_end": 491,
        "snippet": "- Constitution compliance is a **GATE** — fails block all progress"
      },
      {
        "id": "blocker:references/evaluation-template.md:154:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/evaluation-template.md",
        "line_start": 154,
        "line_end": 154,
        "snippet": "- **Readability**: [Assessment - Flesch-Kincaid grade level, sentence length, paragraph structure]"
      },
      {
        "id": "blocker:references/evaluation-template.md:160:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/evaluation-template.md",
        "line_start": 160,
        "line_end": 160,
        "snippet": "- Flesch-Kincaid Grade Level: [X.X]"
      },
      {
        "id": "blocker:references/rubric-details.md:279:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/rubric-details.md",
        "line_start": 279,
        "line_end": 279,
        "snippet": "- Flesch-Kincaid Grade Level: 7-9 (optimal for target audience)"
      },
      {
        "id": "blocker:references/rubric-details.md:314:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/rubric-details.md",
        "line_start": 314,
        "line_end": 314,
        "snippet": "- Flesch-Kincaid Grade Level: 7-10 (appropriate range)"
      },
      {
        "id": "blocker:references/rubric-details.md:349:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/rubric-details.md",
        "line_start": 349,
        "line_end": 349,
        "snippet": "- Flesch-Kincaid Grade Level: 10-12 (somewhat difficult)"
      },
      {
        "id": "blocker:references/rubric-details.md:384:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "references/rubric-details.md",
        "line_start": 384,
        "line_end": 384,
        "snippet": "- Flesch-Kincaid Grade Level: 12+ (too difficult)"
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 62,
        "line_end": 65,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 65,
        "line_end": 75,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 75,
        "line_end": 76,
        "snippet": "- Relevant spec, plan, and tasks files from `specs/<feature>/`"
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 76,
        "line_end": 78,
        "snippet": "- Constitution file (`.specify/memory/constitution.md`)"
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 78,
        "line_end": 84,
        "snippet": "- Output style template used (`.claude/output-styles/lesson.md` or similar)"
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 84,
        "line_end": 86,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 86,
        "line_end": 96,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 96,
        "line_end": 98,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 98,
        "line_end": 110,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 110,
        "line_end": 120,
        "snippet": "1. **Review specific criteria** from `rubric-details.md` for that category"
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 120,
        "line_end": 123,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 123,
        "line_end": 137,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:137:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 137,
        "line_end": 139,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 139,
        "line_end": 241,
        "snippet": "```"
      },
      {
        "id": "external_commands:SKILL.md:241:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 241,
        "line_end": 242,
        "snippet": "- **`references/rubric-details.md`** - Comprehensive tier criteria for all 6 categories with specifi"
      },
      {
        "id": "external_commands:SKILL.md:242:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 242,
        "line_end": 243,
        "snippet": "- **`references/constitution-checklist.md`** - Pass/Fail checklist for constitutional compliance eva"
      },
      {
        "id": "external_commands:SKILL.md:243:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 243,
        "line_end": 251,
        "snippet": "- **`references/evaluation-template.md`** - Structured template for consistent evaluation reports"
      },
      {
        "id": "external_commands:SKILL.md:251:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 251,
        "line_end": 255,
        "snippet": "**User Request:** \"Please evaluate this lesson draft: `apps/learn-app/docs/chapter-3/lesson-2.md`\""
      },
      {
        "id": "external_commands:SKILL.md:255:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 255,
        "line_end": 257,
        "snippet": "1. **Read content:** `apps/learn-app/docs/chapter-3/lesson-2.md`"
      },
      {
        "id": "external_commands:SKILL.md:257:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 257,
        "line_end": 259,
        "snippet": "3. **Check constitution compliance:** `references/constitution-checklist.md`"
      },
      {
        "id": "external_commands:SKILL.md:259:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 259,
        "line_end": 269,
        "snippet": "4. **Load detailed rubric:** `references/rubric-details.md`"
      },
      {
        "id": "blocker:SKILL.md:56:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL.md",
        "line_start": 56,
        "line_end": 56,
        "snippet": "| **Writing Quality** | 20% | Readability (Flesch-Kincaid 8-10), voice, clarity, grade-level appropr"
      },
      {
        "id": "blocker:SKILL.md:190:network-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "Network reconnaissance",
        "file": "SKILL.md",
        "line_start": 190,
        "line_end": 191,
        "snippet": "- **Constitution Compliance:** Pass"
      }
    ],
    "finding_verdicts": [
      {
        "id": "sensitive:references/constitution-checklist.md:178:environment-file-access",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The line only mentions .env as an example of professional file organization in a review checklist. It does not instruct the agent to read environment files or disclose secrets."
      },
      {
        "id": "blocker:references/constitution-checklist.md:262:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The line is a section heading for evaluating hybrid educational chapters. It contains no reconnaissance behavior or request for system details."
      },
      {
        "id": "blocker:references/constitution-checklist.md:422:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line asks reviewers to check cross-references inside educational content. It does not inspect the host system or collect environment details."
      },
      {
        "id": "blocker:references/constitution-checklist.md:490:network-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The line describes a content-quality gate where failing compliance blocks progress. It is not network reconnaissance and makes no network request."
      },
      {
        "id": "blocker:references/evaluation-template.md:154:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line is part of a writing-quality template for readability metrics. It does not perform system reconnaissance or request host information."
      },
      {
        "id": "blocker:references/evaluation-template.md:160:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line is part of a writing-quality template for readability metrics. It does not perform system reconnaissance or request host information."
      },
      {
        "id": "blocker:references/rubric-details.md:279:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line defines Flesch-Kincaid readability ranges for grading educational prose. It is not system reconnaissance or an instruction to inspect the runtime environment."
      },
      {
        "id": "blocker:references/rubric-details.md:314:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line defines Flesch-Kincaid readability ranges for grading educational prose. It is not system reconnaissance or an instruction to inspect the runtime environment."
      },
      {
        "id": "blocker:references/rubric-details.md:349:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line defines Flesch-Kincaid readability ranges for grading educational prose. It is not system reconnaissance or an instruction to inspect the runtime environment."
      },
      {
        "id": "blocker:references/rubric-details.md:384:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The line defines Flesch-Kincaid readability ranges for grading educational prose. It is not system reconnaissance or an instruction to inspect the runtime environment."
      },
      {
        "id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:65:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:78:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:86:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:98:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:110:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:123:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:137:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The match is a Markdown code fence around formulas or report instructions. There is no Ruby execution, shell interpreter use, or dynamic command construction."
      },
      {
        "id": "external_commands:SKILL.md:241:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:242:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:243:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:251:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:255:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:257:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "external_commands:SKILL.md:259:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The match is Markdown inline code that names paths, references, or rubric steps for content review. It is documentation text, not an executable command."
      },
      {
        "id": "blocker:SKILL.md:56:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The line describes readability criteria for the writing-quality score. It does not request system discovery or runtime environment data."
      },
      {
        "id": "blocker:SKILL.md:190:network-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.98,
        "reason": "The line states a publication threshold for content evaluation. It does not perform network discovery or instruct any network access."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 4,
    "total_lines": 2021,
    "audit_model": "codex",
    "audited_at": "2026-07-05T15:01:11.481Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Evaluate Educational Content with a Rubric",
    "value_statement": "Educational drafts need consistent review before publication. This skill applies a weighted rubric and constitution checklist to produce evidence-based feedback.",
    "seo_keywords": [
      "Claude content evaluation",
      "Codex content review",
      "Claude Code education rubric",
      "educational content rubric",
      "lesson quality assessment",
      "chapter review framework",
      "AI teaching evaluation",
      "writing quality checklist",
      "pedagogy audit",
      "curriculum quality assurance"
    ],
    "actual_capabilities": [
      "Scores chapters and lessons across weighted quality categories.",
      "Applies a pass or fail constitution compliance gate.",
      "Classifies results as Excellent, Good, Needs Work, or Insufficient.",
      "Uses included rubric, checklist, and report template for consistency.",
      "Provides evidence-based findings, strengths, weaknesses, and next steps.",
      "Supports mid-draft checks, completion reviews, validation gates, and spot checks."
    ],
    "limitations": [
      "It depends on the content and context files supplied by the user.",
      "It does not verify external facts unless supporting sources are provided.",
      "It does not run code or compute metrics unless the assistant uses available tools.",
      "Its constitution checklist reflects a specific educational standard."
    ],
    "use_cases": [
      {
        "title": "Review a Lesson Draft",
        "description": "Assess a lesson before publication and identify the most important revisions.",
        "target_user": "Curriculum author"
      },
      {
        "title": "Standardize Editorial Feedback",
        "description": "Use the same rubric across chapters so feedback remains consistent and traceable.",
        "target_user": "Technical editor"
      },
      {
        "title": "Gate Validation Readiness",
        "description": "Check whether content meets minimum quality and constitution requirements before validation.",
        "target_user": "Program lead"
      }
    ],
    "prompt_templates": [
      {
        "title": "Quick Lesson Review",
        "scenario": "Beginner spot check",
        "prompt": "Evaluate this lesson draft using the content evaluation framework. Focus on the strongest issues and the most important fixes. Content path: [path]."
      },
      {
        "title": "Full Completion Review",
        "scenario": "Complete draft assessment",
        "prompt": "Review this completed chapter with the full rubric and constitution checklist. Provide category scores, evidence, strengths, weaknesses, and prioritized next steps. Content path: [path]."
      },
      {
        "title": "Pre-Validation Gate",
        "scenario": "Publication readiness decision",
        "prompt": "Determine whether this content is ready for validation. Apply the pass or fail constitution gate first, then calculate the weighted quality score. Content path: [path]."
      },
      {
        "title": "Advanced Rubric Calibration",
        "scenario": "Custom review with project context",
        "prompt": "Evaluate this content with the framework, using the provided spec, plan, learning objectives, and target audience. Call out any rubric assumptions that may need adjustment. Content path: [path]. Context paths: [paths]."
      }
    ],
    "output_examples": [
      {
        "input": "A writer asks for a review of a completed lesson about Python functions.",
        "output": "Overall result: Good. The lesson is technically sound and well structured, but the AI-first teaching section needs stronger guided practice. Recommended next steps include adding one co-learning exercise and simplifying two long explanations."
      },
      {
        "input": "A program lead asks whether a chapter can enter validation.",
        "output": "Verdict: Not ready for validation. Constitution compliance is incomplete because several required evidence items are missing. Resolve the gate items before using the weighted score as a publication signal."
      },
      {
        "input": "An editor asks for a quick spot check on one section.",
        "output": "Focused review: The section has clear examples and a logical flow. The main risk is dense language, so revise long paragraphs before a full completion review."
      }
    ],
    "best_practices": [
      "Provide the draft, learning objectives, and relevant project context together.",
      "Ask for line-referenced evidence so feedback is traceable.",
      "Use the same rubric across drafts to compare improvement."
    ],
    "anti_patterns": [
      "Using the framework as a substitute for subject matter expert review.",
      "Treating incomplete drafts as final publication decisions.",
      "Ignoring a failed constitution gate because the weighted score is high."
    ],
    "faq": [
      {
        "question": "What content can this skill review?",
        "answer": "It is designed for educational chapters, lessons, sections, and related learning materials."
      },
      {
        "question": "Does it produce a numeric score?",
        "answer": "Yes. It calculates a weighted score after the constitution compliance gate passes."
      },
      {
        "question": "Can it review partial drafts?",
        "answer": "Yes. Use a spot check or mid-draft review when the content is not complete."
      },
      {
        "question": "Does it replace a human editor?",
        "answer": "No. It standardizes review structure, but expert review is still useful for accuracy and tone."
      },
      {
        "question": "What inputs improve the review quality?",
        "answer": "Provide the draft, objectives, target audience, relevant specs, and any required constitution file."
      },
      {
        "question": "Can it be used with Claude, Codex, and Claude Code?",
        "answer": "Yes. The report lists support for Claude, Codex, and Claude Code workflows."
      }
    ]
  },
  "file_structure": [
    {
      "name": "references",
      "type": "dir",
      "path": "references",
      "children": [
        {
          "name": "constitution-checklist.md",
          "type": "file",
          "path": "references/constitution-checklist.md",
          "lines": 499
        },
        {
          "name": "evaluation-template.md",
          "type": "file",
          "path": "references/evaluation-template.md",
          "lines": 443
        },
        {
          "name": "rubric-details.md",
          "type": "file",
          "path": "references/rubric-details.md",
          "lines": 803
        }
      ]
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 276
    }
  ]
}
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