/writing-engine

name: writing-engine
description: >
  ALWAYS activate when the user writes, drafts, or revises any part of an academic paper.
  This is the core skill for overcoming writer's block and producing complete first drafts.
  Provides concrete sentence-level templates, paragraph formulas, and section blueprints 
  for IS/WI/BWL research papers. Works for journal papers (MISQ, BISE, EJIS), 
  conference papers (ICIS, ECIS, WI), and working papers.

> **Orchestration Log**: When this skill is activated, append a log entry to `outputs/orchestration_log.md`: > ``` > ### Skill Activation: Writing Engine > **Timestamp:** [current date/time] > **Actor:** AI Agent (writing-engine) > **Input:** [brief description of what the user asked to write/draft/revise] > **Output:** [brief description of what was produced — e.g., "Complete draft of Introduction (1,200 words)"] > ```

Writing Engine

Core Principle

The biggest barrier to writing is the blank page. This skill eliminates it by providing fill-in-the-blank templates at every level: sentence, paragraph, section, and full paper. Claude should NEVER give vague advice like "write a compelling introduction." Instead, Claude produces ACTUAL DRAFT TEXT that the researcher can edit.

When the User Says "Help Me Write" — What to Do

1. **Ask what section** (if not clear) 2. **Ask what the key inputs are** (RQ, findings, theory — whatever that section needs) 3. **PRODUCE A COMPLETE DRAFT** — not an outline, not bullet points, actual paragraphs 4. **Mark placeholders** with [BRACKETS] where specific data is needed 5. **Include inline citation placeholders** as (Author, Year) or [CITE] where references go

---

INTRODUCTION (Target: 1500-2000 words for journal, 800-1000 for conference)

The 6-Paragraph Formula

**Paragraph 1 — The Hook (Practical Relevance)** Open with a striking fact, trend, or problem from practice. Ground the reader immediately.

Template:

[Phenomenon] is transforming [domain/industry]. [Concrete statistic or trend, e.g., 
"By 2025, X% of organizations..."] (Source, Year). [Second sentence expanding scope]. 
This development raises fundamental questions about [broad challenge], particularly 
regarding [specific aspect your paper addresses].

Example for the GenAI/Agents paper:

Generative AI and autonomous AI agents are fundamentally reshaping how organizations 
operate, make decisions, and create value. According to [McKinsey/Gartner], [X]% of 
enterprises have initiated pilot projects with generative AI, while autonomous agents 
are projected to handle [Y]% of routine business processes by [year] (Source, Year). 
This rapid adoption raises pressing questions about how organizations can effectively 
implement these technologies while managing the profound organizational changes they entail.

**Paragraph 2 — Academic Context (What We Know)** Briefly position the topic in the scholarly conversation. Name 3-5 key streams.

Template:

The academic community has begun to examine [topic] from multiple perspectives. 
Research on [stream 1] has investigated [aspect] (Author1, Year; Author2, Year). 
Studies in [stream 2] have explored [aspect] (Author3, Year; Author4, Year). 
More recently, [stream 3] has examined [emerging aspect] (Author5, Year). 
Together, these streams provide important foundations, yet [transition to gap].

**Paragraph 3 — The Gap (What We Don't Know)** The most critical paragraph. Must be specific, non-trivial, and convincing.

Gap patterns (use ONE or combine):

• **Fragmented knowledge**: "While these streams provide valuable insights individually, they remain largely disconnected. No integrative framework exists that [combines X and Y]."
• **Missing context**: "Although [phenomenon] is well-understood in [context A], its dynamics in [context B] remain unexplored. This matters because [reason]."
• **Temporal gap**: "Much of the existing research predates the emergence of [new development]. Given that [what changed], updated investigation is needed."
• **Missing mechanism**: "Prior work establishes that [X influences Y], but the underlying mechanisms — specifically [what and how] — are insufficiently understood."
• **Methodological limitation**: "Existing studies rely predominantly on [method], which cannot capture [important dynamic]. A [different approach] is needed to [achieve what]."

Template:

However, several important gaps remain. First, [gap 1 — be specific]. Second, [gap 2]. 
Third, [gap 3 if applicable]. These gaps are consequential because [why it matters 
for theory AND practice]. Without [what's missing], [negative consequence for the field].

**Paragraph 4 — Research Objective & Questions** State exactly what the paper does.

Template:

To address these gaps, this study [verb: investigates/develops/examines/proposes] 
[specific object of research]. Specifically, we ask:

RQ1: [First research question — most important]
RQ2: [Second research question — if applicable]
[RQ3: Optional third question]

To answer [these questions/this question], we [brief method description: 
conduct a systematic literature review / develop a DSR artifact / employ a 
multiple case study approach / survey N organizations].

**Paragraph 5 — Contribution Statement** The make-or-break paragraph for reviewers.

Template (3-contribution pattern):

This study makes three contributions to [field/literature stream]. First, we 
[specific contribution 1 — what new knowledge]. While prior work has [what they did], 
we [what you do differently]. Second, we [contribution 2 — theoretical or methodological]. 
This extends [theory/framework] by [specific extension]. Third, we derive [contribution 3 — 
practical]. For practitioners, our findings provide [actionable insight: guidelines / 
framework / decision criteria / implementation roadmap].

**Paragraph 6 — Roadmap** Keep it short.

Template:

The remainder of this paper is structured as follows. Section 2 reviews [theoretical 
foun