skills/related-work-positioning-writer/SKILL.md
Draft ML/AI related work as novelty-boundary writing. Use for closest-work grouping, citation roles, paragraph plans, boundary statements, and safe novelty wording.
npx skillsauth add a-green-hand-jack/ml-research-skills related-work-positioning-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 related work as a novelty-boundary argument, not as a citation list. This skill turns literature maps, citation coverage audits, positioning decisions, and paper claims into a related-work plan and, when requested, related-work prose.
Use this skill for:
paper/.agent/related-work-plan.mdfirst, novel, unlike prior work, and orthogonal claimsDo not use this skill to discover all missing citations from scratch. Use literature-review-sprint for field mapping and citation-coverage-audit for submission-time missing citation checks. Use citation-audit for BibTeX and citation correctness. Use paper-writing-memory-manager to record novelty-boundary dependencies and intro/abstract claim impact. Use paper-writing-assistant for general paper prose outside related work.
<installed-skill-dir>/
├── SKILL.md
├── references/
│ ├── boundary-patterns.md
│ └── paragraph-recipes.md
└── templates/
└── related-work-plan.md
references/boundary-patterns.md, references/paragraph-recipes.md, and templates/related-work-plan.md.paper/.agent/writing-contract.md when present.paper/.agent/writing-memory/, paper/.agent/paper-evidence-board.md, root memory/claim-board.md, and root memory/risk-board.md when present.literature-review-sprint, citation-coverage-audit, paper-positioning-planner, and paper-writing-contract-planner when available.Find:
paper/, current directory, or user-provided pathsections/related.tex, introduction, contribution bullets, and abstractpaper/.agent/writing-contract.mdpaper/.agent/related-work-plan.mdpaper/.agent/paper-evidence-board.mdIf the literature map is thin and the user asks for a final related-work section, recommend literature-review-sprint or citation-coverage-audit first.
Use:
plan: create or update related-work-plan.mddraft: write related-work prose from a planrevise: edit an existing related-work section for boundary clarityaudit: report novelty-boundary and grouping issuesDefault to plan when no related-work plan exists and revise when a related-work section exists.
Read references/boundary-patterns.md.
Classify cited and candidate work into buckets:
For each bucket, state:
Read references/paragraph-recipes.md.
For each related-work paragraph:
- Paragraph role:
- Papers included:
- Synthesis sentence:
- Boundary sentence:
- Claim protected:
- Citation keys needed:
- Forbidden wording:
Place the closest-work paragraph early unless venue norms strongly favor a different order.
Use templates/related-work-plan.md.
Save to:
paper/.agent/related-work-plan.md
If the current directory is the paper repo, save to:
.agent/related-work-plan.md
The plan should be useful to paper-writing-assistant and paper-draft-consistency-editor.
Record changed novelty boundaries and affected intro/title/abstract locations through paper-writing-memory-manager.
When drafting:
When editing LaTeX:
Report:
Route:
citation-coverage-audit: missing or recent citationscitation-audit: BibTeX/key correctnesspaper-writing-contract-planner: novelty boundary changes the paper contractpaper-draft-consistency-editor: related work conflicts with title/abstract/introfirst, novel, unlike prior work, or orthogonal claim remainstesting
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.