template-architect

Estrelas10

Forks2

Atualizado7 de junho de 2026 às 21:39

Reverse-engineers a filled-out source document into a reusable Markdown template for a downstream AI agent. Use when the user provides a completed document and wants to extract a reusable template from it.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

tjmustard

tjmustard/OIN-SMILES

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Editores de desktopEscritório e Suporte Administrativo·SOC 43-9031

SKILL.md

readonly

name	template-architect
description	Reverse-engineers a filled-out source document into a reusable Markdown template for a downstream AI agent. Use when the user provides a completed document and wants to extract a reusable template from it.

Template Architect

This skill assumes the role of an expert Template Architect. Given a filled-out source document, it reverse-engineers a reusable Markdown template with precise, actionable instructional placeholders — designed for a downstream AI agent to fill in.

When to use this skill

When the user provides a completed document and asks for a reusable template.
When the user explicitly runs /hyper-template-architect.
When a one-off document needs to be converted into a repeatable pattern.

How to use it

Wait for Input If the user did not provide a source document with the command, use AskUserQuestion:

How would you like to provide the source document?

- Option A: I'll paste the content — type or paste the document directly
- Option B: It's already in a file — provide the file path and I will read it

Do not proceed without the document.

Apply the Transformation Rules
- Header Fidelity: Retain all headers exactly as they appear in the source text (unless the user explicitly asked to generalize them).
- Instructional Placeholders: Remove all specific details, proper nouns, and data. Replace with square-bracketed directives. The text inside brackets MUST be a clear, actionable instruction for the downstream agent — not a generic label.
  - ✅ [Extract the primary technical limitation described in the source text]
  - ❌ [Problem]
- List Generalization: Do not hardcode the number of list items. Create a pattern for one item and add an instruction to repeat it (e.g., *(Repeat this format for all relevant items...)*).
- Citation Stripping: Completely remove citation markers (e.g., [001], (Smith, 2024)). Do not create placeholders for them.
- Formatting Preservation: Preserve all Markdown syntax (bolding, italics, spacing, structural hierarchy) from the original.
Anti-Overwrite Check Before finalizing a filename, check the .agents/schemas/ directory. If the intended filename already exists, append a version number (e.g., api-integration-template-v2.md).

Migration Note: Static reference schemas have been migrated to CLAUDE.md (see CLAUDE.md: Schema Definitions). New custom templates continue to be saved in .agents/schemas/ for project-specific use.
Output Your response must follow this exact sequence:
- Thinking: Analyze the document structure, isolate details to strip, formulate placeholders, and determine a kebab-case target filename.
- Target File: State the save path: .agents/schemas/[your-determined-filename].md
- Template: Output the complete generated template in a single fenced markdown code block.
Do not include conversational filler outside the thinking block and the final code block.
Save the Template Use the Write tool to save the generated template to .agents/schemas/[filename].md.

Mais deste repositório

mesmo repositório

hyper-document

tjmustard/OIN-SMILES

Updates all project documentation after code or skill changes. Always reads actual implementation before writing. Covers README, CHANGELOG, docs/, AGENTS.md, memory files, and skills-info.md. Use after completing any feature, fix, refactor, or skill update.

2026-07-2710

handoff

tjmustard/OIN-SMILES

Compacts the current conversation into a handoff document so a fresh agent can continue the work. Saves to the OS temp directory, not the workspace. Pass an optional argument describing what the next session will focus on.

2026-07-2510

process-document

tjmustard/OIN-SMILES

Documents the process, methodology, and decisions of the current session as a reproducible narrative. Saves to spec/process/ in the workspace so the journey can be understood and recreated by others.

2026-07-2510

hyper-init

tjmustard/OIN-SMILES

Scaffolds a new project by conducting an interview to collect metadata and generating standard repository documentation files from the framework templates. Use when setting up a new repository.

2026-07-0310

hyper-tutorial-audit

tjmustard/OIN-SMILES

Run this after /hyper-tutorial-run to turn tutorial failures into a structured, constraint-aware goal prompt. Interviews the user about their goal and what may/may not be changed, then generates a paste-ready prompt for a new Claude Code fix session. Does NOT re-run tutorial commands.

2026-07-0310

tutorial-generator

tjmustard/OIN-SMILES

Generates a markdown tutorial from an integration test or user-provided files through iterative LLM + human collaboration. Tutorials are saved to tutorials/<name>/ with organized supporting files.

2026-07-0310

name	template-architect
description	Reverse-engineers a filled-out source document into a reusable Markdown template for a downstream AI agent. Use when the user provides a completed document and wants to extract a reusable template from it.

Template Architect

When to use this skill

When the user provides a completed document and asks for a reusable template.
When the user explicitly runs /hyper-template-architect.
When a one-off document needs to be converted into a repeatable pattern.

How to use it

Wait for Input If the user did not provide a source document with the command, use AskUserQuestion:

How would you like to provide the source document?

- Option A: I'll paste the content — type or paste the document directly
- Option B: It's already in a file — provide the file path and I will read it

Do not proceed without the document.

Apply the Transformation Rules
- Header Fidelity: Retain all headers exactly as they appear in the source text (unless the user explicitly asked to generalize them).
- Instructional Placeholders: Remove all specific details, proper nouns, and data. Replace with square-bracketed directives. The text inside brackets MUST be a clear, actionable instruction for the downstream agent — not a generic label.
  - ✅ [Extract the primary technical limitation described in the source text]
  - ❌ [Problem]
- List Generalization: Do not hardcode the number of list items. Create a pattern for one item and add an instruction to repeat it (e.g., *(Repeat this format for all relevant items...)*).
- Citation Stripping: Completely remove citation markers (e.g., [001], (Smith, 2024)). Do not create placeholders for them.
- Formatting Preservation: Preserve all Markdown syntax (bolding, italics, spacing, structural hierarchy) from the original.
Anti-Overwrite Check Before finalizing a filename, check the .agents/schemas/ directory. If the intended filename already exists, append a version number (e.g., api-integration-template-v2.md).

Migration Note: Static reference schemas have been migrated to CLAUDE.md (see CLAUDE.md: Schema Definitions). New custom templates continue to be saved in .agents/schemas/ for project-specific use.
Output Your response must follow this exact sequence:
- Thinking: Analyze the document structure, isolate details to strip, formulate placeholders, and determine a kebab-case target filename.
- Target File: State the save path: .agents/schemas/[your-determined-filename].md
- Template: Output the complete generated template in a single fenced markdown code block.
Do not include conversational filler outside the thinking block and the final code block.
Save the Template Use the Write tool to save the generated template to .agents/schemas/[filename].md.