polish_skill

Read an academic-paper PDF or supplied full text and turn it into a faithful, structured Markdown deep-reading note. Use when the user provides a research paper and asks to read, explain, summarize, take notes, extract its problem, method, equations, experiments, results, limitations, or research implications, or fill a paper-note template. Use paper-only analysis by default and verified enrichment when the user requests code, datasets, metadata, or related-paper context. Do not use for rewriting the user's own manuscript or synthesizing multiple papers into a literature review.

Draft, revise, or diagnose an academic journal cover letter (submission letter to the editor) once the manuscript is essentially complete. Use for the submission statement, a non-overclaiming contribution summary, scope-fit argument for the target journal, originality and ethics declarations, suggested or opposed reviewers, and corresponding-author details. Reuse the manuscript's established problem and contributions instead of inventing them; defer final language polishing to paper-polisher.

Recommend target journals for a finished or near-finished manuscript. Use when the user asks where to submit, wants a shortlist, checks fit for a journal, compares SCI/non-SCI, OA/subscription, Chinese/English, fast-review venues, or asks which journals are realistic. Gather indexing, OA/budget, language, deadline, avoid-list, subfield, keywords, abstract/results, article type, and level anchor; estimate paper level; then return about 10 journals each in reach, fast-review reach, safe, and fast-review safe tiers, plus 1-3 field-top reference candidates outside the four tiers when useful. Each journal must include a fit rationale, recent related-paper evidence from that journal, official-site and LetPub URLs, and an adjustment note when borderline. Web search is mandatory: verify the journal site, LetPub page, and recent related papers live, not from memory. Use before paper-cover-letter.

Audit and constrain a paper's experiment section — experiment and ablation design, plus results narration — without leading the design. Use when the user is building or revising experiments, ablations, or results writeup and wants a check that (1) every experiment and ablation maps to a main claim, (2) the set is the minimal one that argues that line under the user's real equipment, data, and time, and (3) results are narrated as claim-tied argument rather than a flat report of numbers. This skill audits the user's plan or draft and proposes only minimal additions needed to close gaps; it does not invent experiments, assume feasibility it cannot verify, fabricate results, or explain away anomalies. It assesses feasibility only against resources the user states. Defer abstract/introduction contribution framing to paper-argument-reconstructor, novelty and claim boundaries to idea-novelty-auditor, and language polishing to paper-polisher.

Audit research ideas, contribution statements, manuscript positioning, and proposed paper storylines for novelty risk before packaging. Use for comparing an idea against classic algorithmic paradigms, direct related work, adjacent fields, dangerous baselines, reviewer attacks, defensible claim boundaries, required experiments, ablation design, and deciding whether an idea can support a short paper, conference paper, or journal paper. Defer audit of an existing experiment section or concrete experiment plan against fixed claims and stated resources to experiment-section-auditor.

Diagnose, restructure, or rewrite academic manuscript arguments into a problem-driven paper storyline. Use for abstracts, introductions, methodology narratives, formula explanations, theory/proof exposition, experiments, results, discussion, conclusions, contribution statements, section outlines, and full-paper diagnosis when the main task is argument design rather than pure language polishing, literature-review construction, novelty-risk auditing, or audit-only experiment-section checking. Defer experiment-set minimality, ablation sufficiency, feasibility-against-resources, and results-narration audits to experiment-section-auditor.

Write, diagnose, revise, or audit literature review, related work, introduction background, research-gap, and reference-selection sections using a problem-driven S-R-L-H-G-M-C-V protocol. Use for claim-first citation selection, literature-route organization, hidden-assumption analysis, direct competitor coverage, structural gap synthesis, review-baseline alignment, contribution mapping, and citation integrity in technical research papers.

Polish, translate, or locally revise Chinese or English TeX academic manuscript text into formal, objective engineering-journal English while preserving equations, labels, references, citations, variables, environments, bibliography keys, numerical data, and technical meaning. Use for sentence-level, paragraph-level, section-level, or full-manuscript language polishing when the main task is faithful expression improvement rather than novelty audit, literature-review construction, or argument redesign.

Draft, plan, or diagnose a point-by-point response to reviewers (response letter / rebuttal) for a journal or conference revision, especially IEEE Transactions and control, robotics, automation, aerospace, and intelligent-systems venues. Use to audit the manuscript's claims, decode each comment's hidden concern, grade severity and required evidence, produce a revision plan before claiming any edit, revise and mark the manuscript, reconcile conflicting reviewers, handle multi-round revisions, and write the response letter with exact locations. Reuses the real revisions the authors made; defers final language polishing to paper-polisher.