Skip to content

aiskillstore/marketplace / skills/7spade/doc-coauthoring

doc-coauthoring

Verified

Guide 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.

FileKindSize
SKILL.mdskill md15.4 KB
skill-report.jsonconfig14.8 KB

skill-report.json

View on GitHub
{
  "schema_version": "2.0",
  "meta": {
    "generated_at": "2026-07-04T17:24:03.285Z",
    "slug": "7spade-doc-coauthoring",
    "source_url": "https://github.com/7Spade/ng-dragon/tree/main/.github/skills/doc-coauthoring",
    "source_ref": "main",
    "model": "codex",
    "analysis_version": "3.0.0",
    "source_type": "community",
    "content_hash": "b32381e692b3773a2c37bdce7b1adf084aaaaedfcae15e6d2d7a9f5662f2369b",
    "tree_hash": "b49a95f453e149fc929cca6d235a1f4f811c92475fa74fc86e492ebfc21daa1c",
    "provenance": {
      "model_requested": "gpt-5.5:high",
      "model_effective": "codex:gpt-5.5:high",
      "fallback_chain": [
        {
          "agent": "codex",
          "model": "gpt-5.5",
          "effort": "high",
          "outcome": "success"
        }
      ],
      "analysis_version": "3.0.0"
    }
  },
  "skill": {
    "name": "doc-coauthoring",
    "description": "Guide users through a structured workflow for co-authoring documentation, proposals, technical specs, decision docs, and RFCs.",
    "summary": "Structured coauthoring workflow for drafting, refining, and reader-testing important documents.",
    "icon": "πŸ“¦",
    "version": "1.0.0",
    "author": "7Spade",
    "license": "MIT",
    "category": "writing",
    "tags": [
      "documentation",
      "technical-writing",
      "proposals",
      "reader-testing",
      "collaboration"
    ],
    "supported_tools": [
      "claude",
      "codex",
      "claude-code"
    ],
    "risk_factors": [
      "external_commands",
      "network"
    ]
  },
  "security_audit": {
    "risk_level": "safe",
    "is_blocked": false,
    "safe_to_publish": true,
    "analysis_status": "ok",
    "summary": "All static findings appear to be false positives caused by backticked tool names, a normal Claude URL, and documentation prose about gathering user context. No prompt injection, exfiltration intent, or unsafe command execution was found in SKILL.md.",
    "remediation": [],
    "risk_factor_evidence": [
      {
        "factor": "external_commands",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 135,
            "line_end": 135
          },
          {
            "file": "SKILL.md",
            "line_start": 144,
            "line_end": 144
          },
          {
            "file": "SKILL.md",
            "line_start": 188,
            "line_end": 188
          },
          {
            "file": "SKILL.md",
            "line_start": 208,
            "line_end": 208
          },
          {
            "file": "SKILL.md",
            "line_start": 367,
            "line_end": 367
          },
          {
            "file": "SKILL.md",
            "line_start": 368,
            "line_end": 368
          }
        ]
      },
      {
        "factor": "network",
        "evidence": [
          {
            "file": "SKILL.md",
            "line_start": 303,
            "line_end": 303
          }
        ]
      }
    ],
    "static_findings": [
      {
        "id": "external_commands:SKILL.md:135:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 135,
        "line_end": 135,
        "snippet": "Use `create_file` to create an artifact. This gives both Claude and the user a scaffold to work from"
      },
      {
        "id": "external_commands:SKILL.md:144:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 144,
        "line_end": 144,
        "snippet": "Create a markdown file in the working directory. Name it appropriately (e.g., `decision-doc.md`, `te"
      },
      {
        "id": "external_commands:SKILL.md:188:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 188,
        "line_end": 188,
        "snippet": "Use `str_replace` to replace the placeholder text for this section with the actual drafted content."
      },
      {
        "id": "external_commands:SKILL.md:208:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 208,
        "line_end": 208,
        "snippet": "- Use `str_replace` to make edits (never reprint the whole doc)"
      },
      {
        "id": "external_commands:SKILL.md:367:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 367,
        "line_end": 367,
        "snippet": "- Use `create_file` for drafting full sections"
      },
      {
        "id": "external_commands:SKILL.md:368:ruby-shell-backtick-execution",
        "category": "external_commands",
        "severity": "medium",
        "pattern": "Ruby/shell backtick execution",
        "file": "SKILL.md",
        "line_start": 368,
        "line_end": 368,
        "snippet": "- Use `str_replace` for all edits"
      },
      {
        "id": "network:SKILL.md:303:hardcoded-url",
        "category": "network",
        "severity": "low",
        "pattern": "Hardcoded URL",
        "file": "SKILL.md",
        "line_start": 303,
        "line_end": 303,
        "snippet": "1. Open a fresh Claude conversation: https://claude.ai"
      },
      {
        "id": "blocker:SKILL.md:66:network-reconnaissance",
        "category": "blocker",
        "severity": "low",
        "pattern": "Network reconnaissance",
        "file": "SKILL.md",
        "line_start": 66,
        "line_end": 67,
        "snippet": "- Info dump stream-of-consciousness"
      }
    ],
    "finding_verdicts": [
      {
        "id": "external_commands:SKILL.md:135:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 135 references the `create_file` tool name in prose for artifact creation. It is not Ruby backtick execution or a shell command."
      },
      {
        "id": "external_commands:SKILL.md:144:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.95,
        "reason": "Line 144 suggests creating a Markdown file and includes example filenames in inline code formatting. There is no executable shell syntax or user-controlled command."
      },
      {
        "id": "external_commands:SKILL.md:188:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 188 names the `str_replace` editing tool in documentation text. It does not invoke a command interpreter or execute external code."
      },
      {
        "id": "external_commands:SKILL.md:208:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 208 instructs the assistant to use `str_replace` for document edits. This is a safe editing workflow instruction, not shell backtick execution."
      },
      {
        "id": "external_commands:SKILL.md:367:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 367 lists `create_file` as an artifact management instruction. The backticks are Markdown formatting around a tool name, not command execution."
      },
      {
        "id": "external_commands:SKILL.md:368:ruby-shell-backtick-execution",
        "verdict": "false_positive",
        "confidence": 0.96,
        "reason": "Line 368 lists `str_replace` as the preferred editing method. The text does not contain executable Ruby or shell syntax."
      },
      {
        "id": "network:SKILL.md:303:hardcoded-url",
        "verdict": "false_positive",
        "confidence": 0.94,
        "reason": "Line 303 tells the user to open a fresh Claude conversation at https://claude.ai for reader testing. It does not make an outbound request or transmit data."
      },
      {
        "id": "blocker:SKILL.md:66:network-reconnaissance",
        "verdict": "false_positive",
        "confidence": 0.93,
        "reason": "Line 66 says the user may provide an info dump during context gathering. It is ordinary documentation workflow guidance, not network reconnaissance."
      }
    ],
    "semantic_findings": [],
    "critical_findings": [],
    "high_findings": [],
    "medium_findings": [],
    "low_findings": [],
    "dangerous_patterns": [],
    "files_scanned": 1,
    "total_lines": 376,
    "audit_model": "codex",
    "audited_at": "2026-07-04T17:24:03.285Z",
    "agent_auto_install_policy": "allowed",
    "manual_install_policy": "allowed"
  },
  "content": {
    "user_title": "Draft Reader-Tested Documentation",
    "value_statement": "Important documents often fail because key context stays in the author's head. This skill guides Claude, Codex, or Claude Code through context gathering, structured drafting, iterative refinement, and reader testing.",
    "seo_keywords": [
      "Claude",
      "Codex",
      "Claude Code",
      "documentation workflow",
      "technical writing",
      "decision docs",
      "RFC drafting",
      "proposal writing",
      "reader testing",
      "collaborative writing"
    ],
    "actual_capabilities": [
      "Guides users through context gathering before drafting begins.",
      "Creates a section-by-section structure for documents, proposals, specs, and RFCs.",
      "Supports brainstorming, curation, drafting, and focused edits for each section.",
      "Prompts reader testing with a fresh Claude context to find gaps.",
      "Encourages final checks for facts, links, audience fit, and desired impact."
    ],
    "limitations": [
      "Requires the user to provide accurate source context and review the final document.",
      "Cannot access Slack, Teams, Drive, or SharePoint unless connectors are available and authorized.",
      "Does not verify external facts, technical claims, or links without additional tools.",
      "May take longer than freeform drafting because it emphasizes iteration and reader testing."
    ],
    "use_cases": [
      {
        "title": "Write a Technical Spec",
        "description": "Turn rough architecture notes into a structured spec with clear trade-offs, risks, and open questions.",
        "target_user": "Engineering teams"
      },
      {
        "title": "Prepare a Decision Document",
        "description": "Create a decision record that explains context, options, rationale, consequences, and stakeholder concerns.",
        "target_user": "Technical leads"
      },
      {
        "title": "Draft a Proposal",
        "description": "Shape project context and goals into a proposal that readers can evaluate without private background knowledge.",
        "target_user": "Product and operations teams"
      }
    ],
    "prompt_templates": [
      {
        "title": "Start a Document",
        "scenario": "Begin a new document with guided context gathering.",
        "prompt": "Help me use the doc coauthoring workflow to write a [document type]. The audience is [audience], and the desired impact is [impact]."
      },
      {
        "title": "Structure a Draft",
        "scenario": "Convert rough context into a document outline.",
        "prompt": "I have shared the main context. Suggest a section structure for this [document type], explain why each section belongs, and ask what I want to adjust."
      },
      {
        "title": "Refine One Section",
        "scenario": "Improve a specific section through focused iteration.",
        "prompt": "Work on the [section name] section. Ask clarifying questions, brainstorm possible points, help me choose what to keep, then draft the section."
      },
      {
        "title": "Run Reader Testing",
        "scenario": "Check whether the document works for readers without prior context.",
        "prompt": "Test this document like a fresh reader. Predict reader questions, identify ambiguity, list assumed knowledge, and recommend focused fixes."
      }
    ],
    "output_examples": [
      {
        "input": "Draft a decision doc for adopting a new deployment model.",
        "output": "A context interview, a decision-document outline, section drafts, targeted edit prompts, and reader-testing questions."
      },
      {
        "input": "Improve an existing technical spec before review.",
        "output": "A gap analysis, section-level refinement steps, ambiguity checks, and a final review checklist for facts and audience fit."
      },
      {
        "input": "Write a proposal from scattered project notes.",
        "output": "A structured proposal flow with goals, background, options, risks, stakeholder concerns, and next-step recommendations."
      }
    ],
    "best_practices": [
      "Provide audience, document type, desired impact, and constraints before drafting.",
      "Review each drafted section and give specific feedback about what to change.",
      "Run reader testing before sharing the document with stakeholders."
    ],
    "anti_patterns": [
      "Starting with polished prose before enough context is gathered.",
      "Skipping reader testing for documents that depend on hidden background knowledge.",
      "Treating the generated document as final without checking facts, links, and technical details."
    ],
    "faq": [
      {
        "question": "What kinds of documents does this skill support?",
        "answer": "It supports documentation, proposals, technical specs, decision docs, RFCs, and similar structured writing tasks."
      },
      {
        "question": "Does it write the whole document at once?",
        "answer": "No. It builds the document section by section so the user can refine content and style as work progresses."
      },
      {
        "question": "Can it use shared documents or team channels?",
        "answer": "Only when authorized connectors or integrations are available. Otherwise, the user must paste the relevant context."
      },
      {
        "question": "What is reader testing?",
        "answer": "Reader testing asks a fresh Claude context to answer likely reader questions and identify ambiguity or assumed knowledge."
      },
      {
        "question": "Is this useful for Codex or Claude Code?",
        "answer": "Yes. It can guide documentation work in Claude, Codex, and Claude Code when the workflow instructions are available."
      },
      {
        "question": "Who is responsible for the final document?",
        "answer": "The user remains responsible for final quality, factual accuracy, links, technical details, and stakeholder fit."
      }
    ]
  },
  "file_structure": [
    {
      "name": "SKILL.md",
      "type": "file",
      "path": "SKILL.md",
      "lines": 376
    }
  ]
}
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