skills/paper-introduction-argument-writer/SKILL.md
Plan and draft ML/AI introductions as venue-aware argument chains. Use for hook, gap, insight, method, result, contribution flow, and paragraph roles.
npx skillsauth add a-green-hand-jack/ml-research-skills paper-introduction-argument-writerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write introductions as disciplined arguments. This skill turns a paper's positioning, venue, claims, and evidence into a paragraph-by-paragraph introduction plan or draft.
Use this skill for:
Do not use this skill for full-paper review. Use paper-reviewer-simulator for adversarial critique. Use paper-writing-assistant for broad prose drafting. Use paper-writing-memory-manager to record introduction paragraph roles, claim dependencies, and stale downstream locations. Use related-work-positioning-writer for the full related-work section. Use paper-writing-contract-planner first when the paper archetype or claim contract is not settled.
<installed-skill-dir>/
├── SKILL.md
├── references/
│ ├── argument-patterns.md
│ └── paragraph-moves.md
└── templates/
└── introduction-plan.md
references/argument-patterns.md.references/paragraph-moves.md when drafting, revising, or diagnosing paragraph-level flow.templates/introduction-plan.md when creating paper/.agent/introduction-plan.md.paper/.agent/writing-contract.md, paper/.agent/writing-memory/, paper/.agent/paper-evidence-board.md, paper/.agent/related-work-plan.md, and paper/.agent/provisional-results.md when present.main.tex, paper.tex, sections/introduction.tex, sections/intro.tex, sections/abstract.tex, and sections/related_work.tex when revising an existing paper.Extract:
## Introduction Snapshot
- Target venue:
- Paper archetype:
- Intended audience:
- Primary claim:
- Secondary claims:
- Core problem:
- Dominant contribution type: insight / performance / capability / unresolved
- Closest prior limitation:
- Key insight:
- Proposed object:
- Main evidence:
- Missing/provisional evidence:
- Related-work boundary needed in intro:
- Forbidden claims:
Prefer existing project artifacts over memory. If no claim IDs exist, assign local CLM-TMP-* IDs and suggest syncing them to paper-evidence-board.
Read references/argument-patterns.md and choose one pattern:
If the paper has multiple plausible archetypes, choose the one that matches the paper's main sell and mark the secondary archetype as a constraint.
Create or update:
paper/.agent/introduction-plan.md
If there is no paper/ directory and the current directory is the paper repo, save to:
.agent/introduction-plan.md
Use templates/introduction-plan.md. Every paragraph should specify:
When drafting, write paragraph-by-paragraph prose that follows the plan. When revising, preserve correct citations, labels, macros, math, and verified numbers.
For each paragraph:
Contribution bullets should answer:
Avoid contribution bullets that only restate section titles.
Avoid contribution bullets that hide many small engineering tweaks behind a broad novelty claim; route to paper-positioning-planner if the core contribution cannot be expressed compactly.
Before finalizing:
abstract-title-contribution-writer when neededpaper-writing-memory-managertesting
Bootstrap project-local ml-research-skills. Use from global installs when creating a new ML research project, enabling this collection in an existing ML research repo, or deciding whether to install the full bundle locally. Route to project-init for new projects; do not handle paper or experiment work directly.
development
Route project operations tasks — git, memory, bootstrap, remote, workspace, code review, timeline, ops — to the correct skill. Use when the task involves commits, pushes, worktrees, project memory, enabling project-local skills, SSH/server coordination, sidecar runners, or audits. Do not solve the ops task directly.
testing
Route ML/AI paper writing tasks to the correct skill — contract planning, prose drafting, section writing, consistency editing, review simulation, rebuttal, submission, or citation work. Use when the task involves writing, revising, reviewing, or submitting a paper instead of guessing between paper-writing-assistant, paper-writing-contract-planner, paper-reviewer-simulator, auto-paper-improvement-loop, or citation skills. Do not draft prose directly.
data-ai
Project-local router for ML research skill selection. Use inside an initialized ML research project, or while maintaining this skill repo, when the user describes an ML research/paper/experiment/discovery/ops/release workflow and may not know the skill; route to a domain router or high-signal leaf. Do not use for generic non-ML projects.