Client-Ready Prose Generation

Generates publication-ready YAML section prose from structural outlines and evidence materials.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill client-ready-prose-generation-gozonerd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Client-Ready Prose Generation
Source: https://github.com/gozonerd/shadow-ai-assessment/tree/main/.claude/skills/dmis/task_type/TT-04_Client_Ready_Prose_Generation
Command: npx skills add https://github.com/gozonerd/shadow-ai-assessment --skill client-ready-prose-generation-gozonerd

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve? Converting structured outlines and research evidence into polished, client-facing prose is slow and error-prone, especially when every factual claim must be traceable and comply with strict accuracy rules. This Skill automates that conversion while enforcing citation and terminology compliance. ## Core Features & Use Cases - Outline-to-Prose Conversion: Transforms structural outlines (from pipeline stage P3) and evidence materials (from P2) into flowing, narrative section prose delivered as validated YAML. - Accuracy & Anti-Fabrication Enforcement: Applies 9 Critical Accuracy Rules (ACC-001 through ACC-009) and 6 Anti-Fabrication Rules (AFR-001 through AFR-006) so every claim carries a traceable citation. - Automated Output Validation: Ships a Python validator that checks required fields, version, and full accuracy-rule coverage before delivery. - Use Case: A consulting team needs a stakeholder-ready section on digital health platform selection; provide the outline and evidence library, and receive polished prose with verified citations to sources like the Digital Public Goods Registry. ## Quick Start Generate a client-ready prose section from my structural outline and evidence materials, then validate the YAML output with the included script.

Frequently Asked Questions about Client-Ready Prose Generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate client-ready prose from an outline?

Provide the structural outline, evidence materials, and style standards as inputs. The Skill parses the outline, drafts narrative prose, embeds citations, and outputs a YAML document conforming to the TT-04 schema with section prose, integration points, and quality indicators.

How do I validate TT-04 prose output YAML?

Run scripts/validate_output.py with the output file path. It checks required fields (title, task_type, version, section_prose, section_title, citations), verifies the version contains v02, and confirms all nine accuracy rules appear in accuracy_compliance.

What are the ACC and AFR accuracy rules in prose generation?

ACC-001 through ACC-009 are Critical Accuracy Rules covering terminology and factual distinctions, such as distinguishing CommCare from Dimagi. AFR-001 through AFR-006 are Anti-Fabrication Rules requiring traceable sources for every claim and flagging uncertain content as [NEEDS VERIFICATION].

What input does the prose generation pipeline require?

It requires a structural outline from pipeline stage P3, evidence materials from P2, organizational prose standards, and integration instructions. Without these inputs the Skill cannot produce compliant, citation-backed prose.

What are the limitations of automated prose generation with citation rules?

The Skill depends entirely on supplied evidence materials and cannot verify claims beyond them. Outputs failing schema validation or missing any of the nine accuracy rules are rejected, so incomplete upstream outlines or evidence will block delivery.