com um clique
paper-spine-research
// Researches target requirements, downloads reference materials, learns strong examples, and prepares motivation options.
// Researches target requirements, downloads reference materials, learns strong examples, and prepares motivation options.
Audits PaperSpine outputs for missing artifacts, shallow revisions, logic transfer, unsupported claims, and translation coverage.
Builds a paper or report from materials using the shared PaperSpine research, motivation, and rationale workflow.
Collects PaperSpine workflow options and writes config for flash/pro, scene, language, and inputs.
Handles LaTeX project assembly, figure placement, citations, labels, and compile-safe cleanup.
Rewrites an existing manuscript from confirmed motivation, research, paragraph-level rationale, and evidence.
Orchestrates the PaperSpine suite for motivation-driven paper/report rewriting or building from materials.
| name | paper-spine-research |
| description | Researches target requirements, downloads reference materials, learns strong examples, and prepares motivation options. |
Use this skill before motivation confirmation and before any scene-specific writing. No target-scene research means no venue-specific writing advice.
Read paper_rewriting_output/paper_spine_config.json when available. The
important fields are scene, tier, target_name, official_urls,
materials_dir, draft_path, and output_language.
Create and use this folder before writing:
paper_rewriting_output/reference_materials/
source_index.md
official_requirements/
target_examples/
field_sota/
templates/
figures_images/
extracted_notes/
Store downloaded or extracted materials here, including target journal papers, conference papers, competition reference papers, official rules/guidelines, LaTeX or Word templates, reference figures/images, and extracted notes. Do not mix these external examples with user evidence. External examples teach writing logic only.
source_index.md must record every reference item:
| Source ID | Type | Title/Name | Origin/URL/Path | Why Included | Local File/Note | Used For |
|---|
flash: collect 3 target-scene examples and 3 recent high-quality field/SOTA
examples.pro: collect 6 target-scene examples and 6 recent high-quality field/SOTA
examples.Users may override counts explicitly, but do not invent that override.
journal: read references/scenario-journal.md.conference: read references/scenario-conference.md.report_review: read references/scenario-report-review.md.competition: read references/scenario-competition.md.For current official requirements, use current web sources when available: author guidelines, CFPs, rubrics, school or department pages, competition rules, templates, and official announcements.
Do not finalize the motivation before learning SOTA and target-scene examples. If the user provides a motivation early, treat it as a hypothesis.
Create sota_gap_map.md:
| Candidate Contribution | What SOTA/Examples Already Do | User Evidence | Real Gap | Claim Strength | Risk of Overclaim |
|---|
Then create motivation_options_after_research.md:
| Option | One-Sentence Motivation | Core Innovation | Why It Is Not Overbroad | Required Evidence | Best-Fit Paper Arc |
|---|
Rules:
confirmed_motivation.md with:
Create:
paper_rewriting_output/reference_materials/source_index.mdpaper_rewriting_output/research_dossier.mdpaper_rewriting_output/exemplar_learning_dossier.mdpaper_rewriting_output/style_profile.mdpaper_rewriting_output/sota_gap_map.mdpaper_rewriting_output/motivation_options_after_research.mdpaper_rewriting_output/confirmed_motivation.md only after user confirmationThe dossier must separate official requirements, target-scene examples, field SOTA examples, reusable rhetorical moves, and constraints that affect the user's manuscript. Do not borrow claims, data, or results from examples into the user's paper.