skills/abstract-title-contribution-writer/SKILL.md
Draft ML/AI paper titles, abstracts, and contribution lists. Use for title options, abstract structure, contribution bullets, and claim-strength calibration.
npx skillsauth add a-green-hand-jack/ml-research-skills abstract-title-contribution-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 the paper's most compressed sales layer: title, abstract, and contribution list. This skill makes the top-level promise clear, concrete, and evidence-calibrated.
Use this skill for:
Do not use this skill for detailed section drafting. Use paper-introduction-argument-writer for the introduction, paper-writing-assistant for broader prose, paper-writing-memory-manager to record top-level claim wording and dependency impact, and paper-draft-consistency-editor for full-draft consistency.
<installed-skill-dir>/
├── SKILL.md
├── references/
│ ├── abstract-patterns.md
│ └── title-contribution-rules.md
└── templates/
└── abstract-title-plan.md
references/abstract-patterns.md.references/title-contribution-rules.md when writing titles or contribution bullets.templates/abstract-title-plan.md when creating paper/.agent/abstract-title-plan.md.paper/.agent/writing-contract.md, paper/.agent/writing-memory/, paper/.agent/introduction-plan.md, paper/.agent/paper-evidence-board.md, and paper/.agent/provisional-results.md when present.abstract, title, and contribution text from main.tex, paper.tex, sections/abstract.tex, or sections/introduction.tex when revising.Extract:
## Top-Level Writing Snapshot
- Target venue:
- Paper archetype:
- Primary audience:
- Title currently says:
- Abstract currently says:
- Contribution list currently says:
- Primary claim:
- Main evidence:
- Missing/provisional evidence:
- Forbidden claims:
- Desired positioning variants:
If the paper has no stable positioning, route to paper-positioning-planner or paper-writing-contract-planner before finalizing.
Read references/abstract-patterns.md and choose one pattern:
The pattern controls move order, not sentence wording.
Create or update:
paper/.agent/abstract-title-plan.md
If there is no paper/ directory and the current directory is the paper repo, save to:
.agent/abstract-title-plan.md
Use templates/abstract-title-plan.md.
For each abstract sentence or clause, record:
Generate three to six title options across useful positioning styles:
For each title, note what it sells and what risk it creates.
Each contribution bullet should include:
Contribution bullets should be parallel in grammar and non-overlapping in content.
Before finalizing:
paper-writing-memory-manager — record current title, abstract version, contribution bullet list, top-level claim wording, and which downstream sections (intro, contributions, conclusion) now depend on this wordingpaper-evidence-board, paper-introduction-argument-writer, or paper-draft-consistency-editortesting
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.