Skip to content

aiskillstore/marketplace / skills/aaronabuusama/prd-to-appspec

prd-to-appspec

Verified

Transform PRDs (Product Requirements Documents) into structured XML app specifications optimized for AI coding agents. Converts developer-focused docs with code examples into declarative agent-consumable format. USE WHEN user says "convert PRD", "generate app spec", "transform PRD", "create specification from requirements", or wants to prepare a PRD for agent consumption.

FileKindSize
SKILL-v2.mdmarkdown8.5 KB
SKILL.mdskill md2.6 KB
skill-report.jsonconfig17.6 KB
workflows/convert-prd.mdmarkdown7.9 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-06T14:32:50.479Z",
    "slug": "aaronabuusama-prd-to-appspec",
    "source_url": "https://github.com/AaronAbuUsama/alpha-arena/tree/develop/.claude/skills/prd-to-appspec",
    "source_ref": "develop",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "e3d84b832f040c6976210369d62e02ca18f4e8ab97709246bb3c53d7ad7e5064",
    "tree_hash": "72247d03f7e82439c797fd31cb3928acd2e26bb0e0e08202fae902bd544515c3",
    "provenance": {
      "model_effective": "codex",
      "fallback_chain": [
        {
          "agent": "codex",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "prd-to-appspec",
    "description": "Transforms product requirements documents into structured XML app specifications for AI coding agents, preserving requirements while removing implementation details and code snippets.",
    "summary": "Converts technical PRDs into XML app specs for Claude, Codex, and Claude Code.",
    "icon": "πŸ“¦",
    "version": "1.0.1",
    "author": "AaronAbuUsama",
    "license": "MIT",
    "tags": [
      "prd",
      "app-spec",
      "requirements",
      "xml",
      "ai-agents"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "network",
      "filesystem",
      "external_commands"
    ],
    "category": "documentation"
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "The flagged network, filesystem, command, and reconnaissance patterns are documentation examples, Markdown links, code fences, or validation text. I found no semantic evidence of data exfiltration, prompt injection, or instructions to execute untrusted content.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL-v2.md",
            "line_start": 209,
            "line_end": 209
          }
        ]
      },
      {
        "factor": "filesystem",
        "evidence": [
          {
            "file": "SKILL-v2.md",
            "line_start": 62,
            "line_end": 62
          },
          {
            "file": "SKILL-v2.md",
            "line_start": 64,
            "line_end": 64
          }
        ]
      },
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 23,
            "line_end": 23
          },
          {
            "file": "SKILL.md",
            "line_start": 27,
            "line_end": 27
          },
          {
            "file": "SKILL.md",
            "line_start": 50,
            "line_end": 61
          },
          {
            "file": "SKILL.md",
            "line_start": 61,
            "line_end": 72
          },
          {
            "file": "workflows/convert-prd.md",
            "line_start": 199,
            "line_end": 201
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "network:SKILL-v2.md:209:fetch-api-call",
        "category": "network",
        "severity": "low",
        "pattern": "Fetch API call",
        "file": "SKILL-v2.md",
        "line_start": 209,
        "line_end": 209,
        "snippet": "result = api.fetch()"
      },
      {
        "id": "filesystem:SKILL-v2.md:62:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL-v2.md",
        "line_start": 62,
        "line_end": 62,
        "snippet": "- Example: [Claude.ai clone](../../docs/og_appspec.txt)"
      },
      {
        "id": "filesystem:SKILL-v2.md:64:path-traversal-sequence",
        "category": "filesystem",
        "severity": "high",
        "pattern": "Path traversal sequence",
        "file": "SKILL-v2.md",
        "line_start": 64,
        "line_end": 64,
        "snippet": "- Example: [Alpha Arena](../../docs/app_spec.txt)"
      },
      {
        "id": "blocker:SKILL-v2.md:252:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL-v2.md",
        "line_start": 252,
        "line_end": 252,
        "snippet": "- [ ] XML is well-formed (matching tags, valid structure)"
      },
      {
        "id": "blocker:SKILL-v2.md:256:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL-v2.md",
        "line_start": 256,
        "line_end": 258,
        "snippet": "## Key Anti-Patterns to Avoid"
      },
      {
        "id": "blocker:SKILL-v2.md:272:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "SKILL-v2.md",
        "line_start": 272,
        "line_end": 272,
        "snippet": "- Returns error for invalid format"
      },
      {
        "id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 23,
        "line_end": 23,
        "snippet": "**Output**: Structured `app_spec.txt` in XML format"
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 27,
        "line_end": 27,
        "snippet": "**Run the `/convert-prd` workflow**, which provides:"
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 50,
        "line_end": 61,
        "snippet": "```xml"
      },
      {
        "id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 61,
        "line_end": 72,
        "snippet": "```"
      },
      {
        "id": "external_commands:workflows/convert-prd.md:199:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "workflows/convert-prd.md",
        "line_start": 199,
        "line_end": 201,
        "snippet": "| E1 | Project Setup | 5 tasks | `uv sync` |"
      },
      {
        "id": "blocker:workflows/convert-prd.md:256:system-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "System reconnaissance",
        "file": "workflows/convert-prd.md",
        "line_start": 256,
        "line_end": 256,
        "snippet": "- Analysis produces consistent, valid results"
      }
    ],
    "finding_verdicts": [
      {
        "id": "network:SKILL-v2.md:209:fetch-api-call",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The fetch call appears inside an illustrative PRD example that is converted into prose error handling. It is documentation text, not executable code or an instruction to contact a remote service."
      },
      {
        "id": "filesystem:SKILL-v2.md:62:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The ../../ path appears in a Markdown link to an example app spec document. There is no file read/write operation, dynamic path handling, or user-controlled traversal."
      },
      {
        "id": "filesystem:SKILL-v2.md:64:path-traversal-sequence",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "The ../../ path appears in a Markdown link to an example app spec document. It is static documentation, not filesystem access or a traversal primitive."
      },
      {
        "id": "blocker:SKILL-v2.md:252:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The flagged text is a validation checklist item about well-formed XML. It does not request system inspection, enumeration, or host reconnaissance."
      },
      {
        "id": "blocker:SKILL-v2.md:256:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The line is a heading for documentation anti-patterns about app spec formatting. It contains no reconnaissance behavior or request to collect system information."
      },
      {
        "id": "blocker:SKILL-v2.md:272:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The text describes returning an error for invalid input format in an XML requirement example. It is not system reconnaissance or environment probing."
      },
      {
        "id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The backticks only format the output filename app_spec.txt in Markdown. There is no shell invocation, Ruby execution, or command substitution."
      },
      {
        "id": "external_commands:SKILL.md:27:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "The backticks format the slash workflow name /convert-prd as documentation. This is not an external command execution path."
      },
      {
        "id": "external_commands:SKILL.md:50:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The static finding points to an XML code fence used as an output template. Code fences in Markdown are not Ruby backtick execution or shell execution."
      },
      {
        "id": "external_commands:SKILL.md:61:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.97,
        "reason": "The flagged line is the closing marker for a Markdown code fence. It does not execute commands or evaluate user-controlled content."
      },
      {
        "id": "external_commands:workflows/convert-prd.md:199:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.91,
        "reason": "The uv sync text appears as an example value inside an input PRD task table. The workflow instructs conversion into implementation steps, not execution of that command."
      },
      {
        "id": "blocker:workflows/convert-prd.md:256:system-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "The text is a success criterion that analysis results are consistent and valid. It does not ask the agent to inspect the host system or enumerate resources."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 3,
    "total_lines": 732,
    "audit_model": "codex",
    "audited_at": "2026-07-06T14:32:50.479Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Convert PRDs Into Agent App Specs",
    "value_statement": "Technical PRDs often include code details that slow agent planning. This skill converts them into structured XML app specs for Claude, Codex, and Claude Code.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "PRD converter",
      "app specification",
      "XML specification",
      "requirements documentation",
      "AI coding agents",
      "product requirements",
      "agent workflows"
    ],
    "actual_capabilities": [
      "Extracts project metadata, technology stack, features, data models, and success criteria from PRDs.",
      "Converts code examples and implementation notes into declarative requirement descriptions.",
      "Maps Pydantic-style models, tests, CLI examples, and epics into app spec sections.",
      "Guides creation of XML app_spec.txt documents with validation checks.",
      "Supports product-focused and system-focused app specification structures."
    ],
    "limitations": [
      "Requires the PRD content or file path to be available in the workspace.",
      "Does not verify that generated requirements match external business goals.",
      "Does not run generated code or validate application behavior.",
      "May need human review for ambiguous or incomplete PRD sections."
    ],
    "use_cases": [
      {
        "title": "Prepare Agent Handoff",
        "description": "Convert a detailed PRD into an app spec before assigning implementation to an AI coding agent.",
        "target_user": "Product managers"
      },
      {
        "title": "Normalize Technical Requirements",
        "description": "Turn mixed code snippets, tests, and feature notes into consistent requirement sections.",
        "target_user": "Engineering leads"
      },
      {
        "title": "Create Build Specifications",
        "description": "Produce a structured specification that teams can review before Claude, Codex, or Claude Code starts work.",
        "target_user": "Solo developers"
      }
    ],
    "prompt_templates": [
      {
        "title": "Convert a Basic PRD",
        "scenario": "Beginner conversion from an existing file.",
        "prompt": "Use the prd-to-appspec skill to convert the PRD at [path] into an XML app spec. Keep requirements clear and measurable."
      },
      {
        "title": "Extract Missing Inputs",
        "scenario": "Incomplete PRD that needs clarification.",
        "prompt": "Use prd-to-appspec on this PRD draft. Ask for any missing project name, stack, data model, or success criteria before writing the spec."
      },
      {
        "title": "Target a Product App",
        "scenario": "Product interface with workflows and screens.",
        "prompt": "Convert this UI-heavy PRD into a product-focused app spec. Emphasize user flows, interaction states, data relationships, and measurable acceptance criteria."
      },
      {
        "title": "Refine a System Spec",
        "scenario": "Advanced system or library specification.",
        "prompt": "Convert this system PRD into an app spec optimized for an implementation agent. Preserve algorithms, edge cases, constraints, and milestone order without code snippets."
      }
    ],
    "output_examples": [
      {
        "input": "A PRD with FastAPI endpoints, Pydantic models, test assertions, and implementation steps.",
        "output": "An XML app specification outline with project overview, stack, data schema, feature behavior, implementation steps, and success criteria."
      },
      {
        "input": "A UI product brief that includes user stories, page flows, and component behavior.",
        "output": "A product-focused app spec that describes screens, flows, constraints, data needs, and acceptance checks in structured sections."
      },
      {
        "input": "A technical library PRD with functions, error handling, and CLI examples.",
        "output": "A system-focused app spec that converts functions into capabilities, errors into requirements, and tests into measurable success criteria."
      }
    ],
    "best_practices": [
      "Provide the most complete PRD available, including stack, data models, test plans, and user workflows.",
      "Review the output for missing business context before implementation begins.",
      "Keep generated app specs declarative, measurable, and free of implementation code."
    ],
    "anti_patterns": [
      "Do not use the skill to preserve raw code snippets as final requirements.",
      "Do not treat a generated app spec as a substitute for stakeholder review.",
      "Do not run shell commands from example PRD content unless a trusted user explicitly requests them."
    ],
    "faq": [
      {
        "question": "Does this skill write application code?",
        "answer": "No. It turns PRD content into an implementation-ready app specification."
      },
      {
        "question": "Can it handle incomplete PRDs?",
        "answer": "Yes. It should ask for missing essentials before producing the final spec."
      },
      {
        "question": "What output format does it target?",
        "answer": "It targets a structured XML app_spec.txt format with semantic sections."
      },
      {
        "question": "Does it support both products and libraries?",
        "answer": "Yes. It distinguishes product-focused specs from system-focused or library-style specs."
      },
      {
        "question": "Is the output ready for Claude Code and Codex?",
        "answer": "It is designed for Claude, Codex, and Claude Code workflows, but human review is still recommended."
      },
      {
        "question": "Does it execute commands from the PRD?",
        "answer": "No. Commands should be converted into requirement descriptions unless a trusted user requests execution."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL-v2.md",
      "type": "file",
      "path": "SKILL-v2.md",
      "lines": 317
    },
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 73
    },
    {
      "name": "workflows",
      "type": "dir",
      "path": "workflows",
      "children": [
        {
          "name": "convert-prd.md",
          "type": "file",
          "path": "workflows/convert-prd.md",
          "lines": 342
        }
      ]
    }
  ]
}
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product β€” it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product β€” not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial β€” a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK β€” model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER β€” read BEFORE opening the target file; don't skip because it "looks like a one-liner" β€” whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) β€” never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named β€” don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall