research-paper-lifecycle-skills

One consolidated read on how good a paper is right now — top strengths, biggest risks, scores, and what to do next — by running the compliance, integrity, citation, conformance, and mock-review skills and summarizing them in one Paper Health Report. Use when a researcher asks "how good is my paper", "is my paper ready", "what are the strengths and weaknesses of my paper", "give me an overall assessment", "review my whole paper", "what should I improve first", or "what's the state of my paper". Orchestrates preflight-check, verify-citations, check-originality, benchmark-paper, and simulate-reviewers, then summarizes them in plain language with strengths first, a prioritized fix list, and an honest readiness read — never a prediction of acceptance. Trigger words - how good is my paper, paper health, overall assessment, is it ready, strengths and weaknesses, what to improve, paper report, assess my paper.

Drafts or rewrites a Related Work / prior work section positioned against actually-retrieved papers — derives the REQUIRED clusters from the paper's own claimed scope (not just whatever was retrieved), clusters prior work into themes, articulates the delta (what this paper adds) per cluster, enforces a per-cluster citation floor and routes empty expected clusters back to find-papers, follows the target community's placement and citation conventions (numeric ACM/IEEE vs natbib author-year, single- vs double-blind self-citation, where the section sits at NeurIPS/CHI/SIGMOD-style venues), and admits only verified citations. Use when the user says "related work", "prior work", "position my paper against the literature", "how do we differ from X", "reviewers said related work is thin/missing/a laundry list", or asks to add citations to a draft. Works from papers found via find-papers and/or an existing .bib — it never invents references.

Turns a topic into a ranked reading list of the best papers plus a two-column, arXiv-ready literature-review/survey draft grounded in verified citations. Use when a researcher says "write a survey on X", "do a literature review of X", "give me a ranked reading list on X", "what should I read on X first", "draft a survey paper for arXiv", or "two-column related-work survey on X". Searches across DBLP/Crossref/Semantic Scholar/arXiv, ranks candidates by citation impact, venue strength, recency, and citation-graph centrality, clusters them into a taxonomy, verifies every reference, and writes an original-prose survey (intro, taxonomy, per-theme synthesis, open problems) where each claim cites a real, resolved paper. Never fabricates citations, never copies source text — original synthesis only; the author stays the author. Trigger words - survey, literature review, reading list, ranked papers, what to read, arxiv survey, two-column review.

Searches scholarly literature with zero API keys across DBLP, Crossref, Semantic Scholar, and arXiv. Use when the user wants to find papers, search the literature, list a conference's proceedings (e.g. "all SIGSPATIAL 2025 papers"), survey related work on a topic, look up papers by author/venue/year, get DOIs or citation counts, or check recent arXiv preprints. Ships a venue-alias table that solves cross-API venue naming (DBLP "conf/gis" vs Semantic Scholar "SIGSPATIAL/GIS" vs Crossref proceedings titles) plus polite, cached, 429-resilient search scripts. Trigger words - find papers, literature search, related work, proceedings, DBLP, Crossref, Semantic Scholar, arXiv, citation count, DOI lookup, venue search.

Builds a structured literature review — survey of prior work, state of the art, related-work landscape — where every claim cites a verified reference. Use when the user says "literature review", "lit review", "survey the papers on X", "what's the state of the art", "synthesize prior work", or "organize these papers by theme". Composes sibling skills, search via find-papers (key-free DBLP/Crossref/Semantic Scholar/arXiv), full text via fetch-paper (legal open-access only), and citation checking via verify-citations. Tracks a screening corpus, extracts claims with section-level anchors, organizes by theme, and gates the final document with a deterministic checker so no claim ships uncited, unverified, or resting on a fabricated reference.

Goal-driven conductor for the whole idea-to-published-paper lifecycle. Takes a research idea plus experiments and a target ("submit to NeurIPS 2026", or "help me pick a venue") and runs a goal->plan->execute->verify->reflect loop. It plans the stages, invokes the right lifecycle skills in order (literature-review, write-abstract, preflight-check, simulate-reviewers, and the rest), checkpoints with the author before each stage, and re-verifies the live CFP via parse-cfp rather than trusting a cached profile. Use when a researcher says "take my idea to a submitted paper", "run the whole pipeline", "orchestrate the paper for venue X", "what's the plan from here", or "what's done and what's next". Copilot, not autonomous author. It stops to ask at every stage gate, never fabricates results or citations, and never submits. Trigger words - orchestrate, pipeline, end to end, whole paper, idea to submission.

Parses a conference Call for Papers (CFP) URL into a machine-checkable requirements card - deadlines with timezone (AoE vs local), per-track page limits including/excluding references, single/double/triple-blind level, exact LaTeX template invocation, LLM/AI-use policy, rebuttal format, and submission system (OpenReview, CMT, EasyChair, HotCRP, PCS) - emitted as a year-versioned venue-profile YAML conforming to venues/schema.yml. Use when the user shares a CFP or author-instructions URL, asks what a venue's submission requirements, deadlines, page limits, or anonymity rules are, or wants a venue profile under venues/conferences/ created or refreshed for a new submission cycle.

Deterministic desk-reject preflight linter for LaTeX paper submissions. Use it when a researcher asks "is my paper ready to submit", or mentions preflight, desk reject, submission check, page limit, anonymization, double-blind, missing checklist, or format/template compliance for a conference (NeurIPS, ICML, CHI, SIGSPATIAL, SIGMOD, ICDE, CVPR, LNCS...). Lints the .tex source against a machine-readable venue profile for documentclass and style-file options, margin/template tampering (geometry, savetrees, spacing hacks), anonymization leaks (author block, acknowledgments, repo links, first-person self-citations, \thanks, pdfauthor), required sections (NeurIPS checklist, ICML impact statement, AI-use acknowledgement, COI, CCS concepts/keywords), abstract length, keywords format, and page-limit risk. Every finding is reported with file:line. Runs bundled stdlib-only Python scripts; advisory only, never submits anything.

Step-by-step camera-ready prep for accepted papers — the error-prone final stage before publication. Use when a researcher says "camera-ready", "final version", or "my paper got accepted, now what", or mentions ACM eRights / rights form / TAPS / ORCID / DOI block, IEEE PDF eXpress / conference ID / eCF copyright form / Xplore, OpenReview final upload, de-anonymization, or extra camera-ready pages. Resolves the venue's rail from a machine-readable profile and walks it end to end across ACM eRights, ORCID, rights/DOI block, TAPS source upload, IEEE PDF eXpress, conference IDs, file naming, eCF exact-title match, registration/no-show, NeurIPS-style [final] recompile, and OpenReview upload. Generates an ordered checklist with deadlines and +page rules, and lints the final .tex for leftover anonymization and missing rights blocks via bundled stdlib-only scripts. Advisory — it prepares, explains, and lints, but never completes a form or submits anything.

Venue-calibrated peer-review simulation. Use when a researcher says "simulate reviewers", "mock review", "review my paper like a NeurIPS reviewer", "what would Reviewer 2 say", "red-team my paper", "find weaknesses before I submit", "peer review my paper", "strengths and weaknesses / pros and cons of my paper", "what to focus on", or wants a rubric score / borderline-reject risk estimate for a conference or journal (NeurIPS, ICML, ICLR, CVPR, KDD, SIGMOD, CHI, VLDB, LNCS, TKDE, TODS...). Builds a reviewer panel calibrated to the venue family and track (harsh NeurIPS main-track skeptics vs lenient demo-track judges), scores novelty/soundness/reproducibility/clarity on the venue's scale, hunts weaknesses grounded in quoted paper text, aggregates scores into a decision-risk band with borderline-reject flags, and outputs a prioritized fix list. Advisory only; improves the paper, never predicts the outcome, re-verifies facts against the live CFP, fabricates no citations or reviewers, and submits nothing.

Diffs a paper draft against a machine-readable venue profile and produces a four-part tailoring plan - contribution reframing for the chosen track (research vs applications/industry vs demo vs short/vision), a page-budget cutting plan, a template/documentclass switch plan (acmart, IEEEtran, NeurIPS-style, llncs), and an anonymization sweep matched to the venue's blind level. Use when the user wants to adapt, retarget, resubmit, or port a paper to a different conference, journal, or track; fit a paper into a page limit ("cut to 10 pages"); switch LaTeX templates ("convert IEEEtran to acmart"); anonymize for double-blind review; or asks "make this fit SIGSPATIAL/NeurIPS/ICDE/KDD", "which track should this go to", or "retarget my rejected paper".

Verifies every citation in a BibTeX .bib file against Crossref, DBLP, Semantic Scholar, and arXiv to catch hallucinated, fabricated, or incorrect references before reviewers do. Use when the user says verify citations, check references, validate bibliography, check my .bib, fake or hallucinated citations, retracted paper, or DOI check — and before any draft, rebuttal, or camera-ready leaves the machine. Flags unresolvable entries (likely fabrications), author/year/venue mismatches, duplicates, and retractions, and points to the canonical record for each fix. Every skill that writes or edits citations must route new references through this gate.

Drafts peer-review rebuttals and author responses in the three real venue formats - (a) strict one-page LaTeX rebuttal PDFs (CVPR-style), (b) OpenReview threaded per-review replies under 10,000-character budgets (NeurIPS/ICML/ICLR), and (c) revise-and-resubmit packages with a change-log response document (CHI, SIGMOD/ICDE revision rounds, journals). Anchors every response to paper sections, tables, figures, and line numbers; enforces character/page budgets and point-by-point coverage with bundled checker scripts; ships a one-page rebuttal LaTeX template. Use when the user says "write my rebuttal", "respond to reviewers", "author response", "reviews came back", "reviewer 2 says", "revise and resubmit", "response letter", "rebuttal deadline", or needs to fit a response into an OpenReview character limit or a one-page PDF. Drafts files on disk only; never posts, uploads, or submits.

Scores a draft against the measurable patterns of recent award-winning and top-cited papers at a target venue, producing a shareable venue-fit scorecard. Use when a researcher asks "score my paper", "how does my paper compare to best papers at SIGSPATIAL/NeurIPS/...", "is my paper good enough for this venue", "benchmark my draft against award winners", "rate my paper out of 10", or wants a readiness scorecard before submitting. Builds an exemplar corpus via study-exemplars, extracts comparable structural and rhetorical features from the draft, and reports a per-dimension scorecard plus an overall venue-fit index — explicitly a conformance measure (does the draft match the form of strong work at this venue), never a prediction of acceptance, award, or scientific quality. Trigger words - score my paper, rate my paper, benchmark, scorecard, compare to best papers, award winners, venue fit, am I ready to submit.

Studies exemplar papers from a target venue and produces an original style-and-structure brief — fetches best-paper awardees and top-cited papers on demand (DBLP, Semantic Scholar, Unpaywall, arXiv, open-access ACM DL) and analyzes section architecture, contribution framing, evaluation patterns, and figure/table conventions. Use when the user wants to study best papers or award-winning papers at a venue, find the most-cited papers and how they are structured, learn how successful papers at a conference are written ("what do winning SIGSPATIAL papers look like", "analyze NeurIPS best papers before I draft"), or model a draft on a venue's strongest work. Copyright-safe by design - papers are fetched from legal open-access sources and processed transiently, never bundled, stored, or committed; the output is metadata plus original analysis. Trigger words - exemplar, best paper, award-winning, most cited, top cited, model paper, venue style, paper structure.

Writes, rewrites, and lints venue-aware paper abstracts and prepares abstract-registration packages. Enforces venue length norms (e.g. LNCS 150-250 words), generates the correct keywords block (ACM CCS Concepts, IEEE Index Terms, LNCS \keywords, or none for NeurIPS-style), structures the abstract as motivation-gap-approach-results-impact, and builds the abstract-registration card (title, abstract, authors, topics, conflicts/COI, deadline countdown) for venues with a separate abstract deadline. Use when the user asks to write, revise, shorten, lengthen, or polish an abstract; asks about abstract word limits, CCS concepts, index terms, or keywords; or needs to register an abstract / meet an abstract-registration deadline (NeurIPS, ICML, KDD, CVPR, CHI, SIGSPATIAL) before the full-paper deadline.

Creates a new venue-profile YAML for venues/conferences/ from a conference CFP URL, validates it against venues/schema.yml, and preps the contribution PR. Use when the user wants to add a venue, contribute or refresh a venue profile, encode a conference's submission requirements (deadlines, page limits, blind level, template invocation, rebuttal format, submission system) as machine-readable YAML, copy a profile forward to a new year, or validate a profile before opening a pull request. Covers scaffolding the file, extracting facts from the live CFP, the DBLP/Semantic Scholar/Crossref alias table, the mandatory verified provenance block, schema validation, and PR-readiness checks.

Helps a paper hit its target length: recommends exactly what to compress when it is over the page limit, or what to add with substance when it is too short. Use when a researcher says "I'm over the page limit", "compress my paper", "what should I cut", "trim two pages", "my paper is too long", "help me fit NeurIPS's limit", "my paper is too short", "I have space left, what should I add", or "where is all my length going". Runs a section-by-section length analysis, then gives a prioritized, value-aware plan: which low-value sections to condense or move to an appendix, while protecting contributions, results, and citations, or which thin sections to develop. Never deletes evidence to fit and never pads to fill. Trigger words: page limit, compress, trim, cut down, too long, too short, over the limit, fit the limit, what to cut, what to add.

Renders the paper-workspace (outputs + lifecycle progress) into a single self-contained HTML dashboard the author can open in a browser, and refreshes it on request. Use when a researcher says "show me an HTML view", "give me a dashboard", "can I see my progress in a browser", "visualize what's been done", "make an HTML report", or "update the dashboard". Offered as an option whenever a visual overview would help (it is opt-in, not generated unprompted), and re-run after each significant change so the page stays current. The output is one local dashboard.html with inline CSS — no network, no external assets, light/dark aware — listing every generated artifact by stage with clickable links and a recent-activity timeline. Trigger words - html, dashboard, browser view, visualize progress, html report, update the html.

Bridges an Overleaf project to the local skills so a paper kept on Overleaf can be checked, polished, and reviewed, then synced back. Use when a researcher says "my paper is on Overleaf", "sync my Overleaf project", "pull my paper from Overleaf", "run preflight on my Overleaf paper", "edit my Overleaf project locally", or "push my changes back to Overleaf". Walks the three real paths — Overleaf Git integration (clone as a local repo), GitHub synchronization, or download-as-ZIP for free accounts — gets the .tex into a local working copy the other skills operate on, and guides syncing changes back. Treats the Overleaf access token as a secret, never auto-pushes without confirmation, and re-verifies the current Overleaf method live since premium availability and steps change. Trigger words - overleaf, my paper is on overleaf, sync overleaf, pull from overleaf, push to overleaf, edit overleaf locally.

Prepares a reproducibility artifact (code/data) for submission and badging. Use when a researcher says "artifact evaluation", "artifact appendix", "reproducibility", "badge", "Artifacts Available/Evaluated/Functional/Reusable", "Results Reproduced/Replicated", "ACM badging", "USENIX/OSDI/SOSP AE", "SIGMOD ARI", "NeurIPS code/checklist", "ACL repro checklist", "Zenodo DOI", "Software Heritage", "anonymize my code/repo", or "package my code". Builds the artifact README + appendix, the dependency/run instructions, an anonymized repo for double-blind, and archival-DOI (Zenodo version vs concept) / Software Heritage SWHID guidance; resolves the ACM badge taxonomy and the Reproduced/Replicated era swap; and lints the artifact directory against the ML Code Completeness checklist with bundled stdlib-only scripts. Outputs an artifact-readiness checklist + packaging plan. Re-verifies the venue current artifact rules live. Advisory only; never submits.

Clean research code for public release while preserving reported results. Uses release_audit.py to separate safe mechanical cleanup from ask-first behavior risks and identity leaks. Use for release-ready repos, dead experiment branches, config extraction, documented entrypoints, and double-blind code cleanup.

Diagnoses and fixes a paper's argument architecture and narrative flow, independent of any venue. Checks whether the story is built in the right order, whether each section does its job, whether the intro promises what the body delivers, and whether the contribution -> evidence -> conclusion arc holds — then produces a restructuring plan (move / merge / split / cut sections) the author approves BEFORE anything is rewritten. Use when a researcher says "the structure is off", "it doesn't flow", "reviewers said it's hard to follow / disorganized / the story is unclear", "my intro over-promises", "related work is in the wrong place", "this section doesn't belong here", "reorganize my paper", "fix the narrative", or "the contributions don't match the results". Distinct from tailor-to-venue (venue/track fit, page limits, templates) and polish-prose (sentence-level wording). Bundles outline_extract.py to print the section tree + each section's opening sentence so the architecture is reviewable at a glance.

Make research code runnable and repeatable for artifact review by auditing README, dependencies, seeds, entrypoints, data instructions, result commands, and smoke tests with repro_check.py. Use for smoke tests, seed pinning, environment capture, reproducibility checks, or works-on-my-machine cleanup.

Audit load-bearing paper claims against evidence in results, tables, figures, experiments, or citations. Use for claim audits, overclaiming checks, first or state-of-the-art claims, significant-result wording, prose-table number mismatches, and camera-ready or rebuttal evidence checks.

Check whether reported paper metrics are consistent with outputs from the local code artifact. Use for result reproduction checks, artifact evaluation, reproducibility checklists, code-versus-paper audits, table or claim metric comparisons, and badge-readiness review.

Checks a draft for plagiarism, self-plagiarism, text recycling, and uncited near-quotes using several detection methods, and reports overlapping passages so the author can fix them before reviewers or an integrity check do. Use when a researcher says "check for plagiarism", "plagiarism check", "did I copy too much", "self-plagiarism", "text recycling", "am I reusing too much of my own paper", "check originality", "is this too close to the source", or "did I paraphrase closely enough". Compares the draft against sources the user provides (their own prior papers, co-author drafts, suspected sources, or papers fetched on demand), detects internal duplication, and surfaces distinctive phrases to search externally. Honest about scope - it is not iThenticate/Turnitin and has no private publisher corpus; it catches overlap against given sources and publicly findable phrases. Trigger words - plagiarism, self-plagiarism, text recycling, originality, copied, overlap, too close to source, duplicate text.

Interactively elicits and stores the author's paper positioning so every other skill in this repo behaves context-awarely. Use when a researcher says "set up my paper profile", "ask me about my paper", "what verticals", "configure for my paper", "remember my positioning/style", or is starting a new paper and wants the toolkit tuned before drafting. Asks with sensible options about vertical/emphasis, contribution type, audience and venue tier, risk appetite, and writing preferences, then writes .paper-memory/profile.yml in the paper working directory. Explains how downstream skills consume it for benchmark-paper weighting, simulate-reviewers persona calibration, polish-prose/match-style register, and tailor-to-venue framing. Bundles a stdlib script profile_io.py that reads/writes/validates the file and emits a blank template. Local-only, never uploaded; advisory copilot, never submits.

The reflection agent. Use it right after another skill produces an artifact such as a rewrite from polish-prose, a rebuttal, an abstract, a preflight fix, or a tailored draft to critique that output against the stated goal, the paper's .paper-memory/profile.yml, the relevant rubric, and past .paper-memory/lessons.md, then decide whether it actually improved. Trigger words include reflect, self-critique, did this get better, did my edit help, regression check, review my own output, iterate, refine, second pass, sanity-check the rewrite, and "is the new version actually better". Runs a bounded self-refine / Reflexion loop, guards against regressions, and appends durable, deduplicated, dated lessons to .paper-memory/lessons.md via a stdlib script so the toolkit gets sharper each paper. Reflection adds cost; it only pays off when there is a measurable target.

Aligns a draft to a target writing voice — the author's own previous papers, a target venue's published style, or both — so it reads as consistent, native to the venue, and unmistakably the author's. Use when a researcher says "make this match my other papers", "use my usual writing style", "make it sound like my group's work", "match the style of this venue", "align terminology with my prior work", or "make my co-authored draft read consistently". Extracts a measurable style signature (terminology, sentence rhythm, hedging, connective habits, structure) from a corpus the author supplies, diffs the draft against it, and drives a section-by-section alignment that never changes a technical claim, number, or citation. Only the author's own papers and open-access venue exemplars are used; nothing copyrighted is bundled. Trigger words - match my style, my writing voice, sound like my papers, venue style, consistent terminology, align voice, my group's style.

De-AI-ifies and tightens academic prose without changing any technical claim. Use when a researcher says "this sounds like ChatGPT / AI-written", "humanize my paper", "remove the AI words", "too many delves and leverages", "polish my writing", "tighten the prose", "fix my hedging", "too many Moreover/Furthermore", "make my contributions active", or "keep my terminology consistent". Runs deterministic stdlib linters — prose_lint.py (leftover chatbot artifacts, LLM-tell vocabulary, connective stacking, em-dash density, double hedges, overclaiming boosters, passive contribution statements) and terminology_check.py (dataset/data set/data-set variants, acronym discipline, -ise/-ize mixing, glossary enforcement) — then drives a section-by-section edit pass using rewrite catalogs and the venue family's register norms. Numbers, results, claims, and citations are never altered; the venue's AI-use disclosure policy is surfaced and respected, never dodged.

Runs a two-pass paper reflection loop with a Researcher pass and a Writer pass. Use when the user asks to reflect on a paper, improve a draft, run a research-agent and writer-agent review, critique the paper before submission, find both technical and writing issues, or produce a revision plan. The Researcher pass checks claims, citations, evidence, venue fit, missing related work, and reviewer risk; the Writer pass checks framing, structure, abstract, related work, prose, tables/figures, and response clarity. Outputs a merged action plan with evidence, priority, owner, and next skill to run.

Deep anonymization sweep for double-blind paper submissions, plus clean de-anonymization for camera-ready. Use when a researcher says "anonymize my paper", "double-blind check", "blind this submission", "remove author names", "did I leak my identity" — or, after acceptance, "de-anonymize" / "restore authors for camera-ready". Sweeps the whole leak surface, \author/\affiliation/\email/\orcid/\thanks, acknowledgments and grant numbers, hyperref pdfauthor and compiled-PDF metadata, first-person self-citations (rewritten to third person), GitHub/dataset/homepage links vs anonymized mirrors, LaTeX comments, .bib annotations, home-directory paths, and supplementary material (.git dirs, notebooks, LICENSE/AUTHORS files). Bundles a stdlib-only scanner (scan_anonymization.py, check ids shared with preflight-check) and a reversible-edit workflow (toggle + manifest) so every change is cleanly undone at camera-ready. Advisory only; never submits anything.

Fetches a legal open-access copy of a paper from its DOI or arXiv ID — resolves through Unpaywall, arXiv PDF/HTML, and the open-access ACM Digital Library. Use when the user wants to fetch, download, read, or get the PDF or full text of a specific paper. Single polite fetch, transient processing only: it never stores paper text in the repo, never bypasses paywalls, and never uses shadow libraries. For finding papers by topic or venue, use find-papers first; this skill starts from an identifier.

Creates and checks conference research posters and short poster-session pitches. Use when the user asks to make a poster, prepare a research poster, adapt a paper into a poster, fit a poster to A0/A1/36x48in, check a beamerposter or tikzposter file, reuse paper figures, or write a 2-minute or 5-minute poster pitch. Bundled scripts resolve poster dimensions, inventory reusable figures, lint print-day problems, and time spoken pitches.

Builds a conference talk deck (Beamer or Marp markdown) from a paper draft - problem-first narrative, one claim per slide, figures reused straight from the paper's LaTeX source, sized to the real slot (12-20 minute full talk vs 5-minute lightning). Use when the user asks to make slides, build a presentation or talk deck for an accepted paper, turn a paper into a talk, prepare a conference presentation, fit a talk into N minutes, or check and trim an existing deck that is too long or too text-heavy. Inventories the paper's figures by in-text reference count, computes a minutes-and-slides budget per section, drafts the deck, and deterministically lints pacing, overfull slides, missing or unrenderable figures, and generic non-claim titles. Venue profiles give context only; the slot length must come from the venue's presenter instructions or acceptance email.

Builds a backwards submission timeline from a conference deadline - days remaining (AoE-aware), abstract-registration offsets, author-list freeze, OpenReview/CMT/EasyChair/HotCRP/PCS account lead times and per-system steps, supplementary-material and code size limits, reciprocal-reviewing duties, and a dual-submission audit. Use when the user wants to plan a submission, asks how long until a deadline, mentions abstract registration, submission checklist, deadline countdown, "what do I need before the NeurIPS/ICML/CHI deadline", or asks what happens after submitting (rebuttal window, notification, camera-ready). Phase-aware - produces pre-submission, under-review, and camera-ready plans from venues/ profiles and flags overdue steps.

Polishes LaTeX tables and figures to publication quality. Use when a researcher mentions table formatting, booktabs, figure layout, subfigures, captions, colorblind-safe colors or palettes, cref/cleveref consistency, overfull hbox, column widths, or asks to make tables and figures look professional or camera-ready for a venue (ACM, IEEE, NeurIPS, LNCS, CHI). Converts hline-and-vertical-rule tables to booktabs, sizes columns within the page budget, lays out subfigures with subcaption, applies caption conventions per venue family (table captions above, figure captions below, ACM Description alt-text), fixes ref/cref inconsistencies, and recommends colorblind-safe palettes (Okabe-Ito, Paul Tol) using bundled stdlib-Python linters and palette generators. Edits presentation only — never alters data values, units, or results.

Simulated-audience Q&A rehearsal for conference talks, thesis defenses, job talks, and poster sessions. Use when a researcher says "rehearse Q&A", "practice questions", "mock Q&A", "grill me on my paper", "what will the audience ask", "hostile questions", "defense practice", "viva prep", "anticipate questions for my talk", or "questions I hope nobody asks". Sizes a drill to the real Q&A slot, fires hostile and curious questions one at a time in audience personas (hostile skeptic, methods stickler, statistician, adjacent-field expert, big-picture senior, confused newcomer, industry practitioner, self-promoter, rambler) calibrated to the venue family, mines the paper for dreaded weak-point questions, coaches concise answer-first responses, and grades transcripts deterministically for timing, hedging, filler, and buried answers. Coaches honest answers only — never spin — and never invents prior-work citations in drill questions.

Builds a ranked venue shortlist for a research paper. Use when the user asks where to submit, which conference or journal to target, venue selection, track selection, or mentions CORE rank, h5-index, acceptance rate, CCF class, or submission deadlines. Maps the paper's topic and contribution type (method, system, dataset, demo, vision, industrial, survey) to venue-track pairs scored on topic fit, track fit, prestige signals, and deadline proximity computed from the machine-readable venues/ profiles — with mandatory re-verification of deadlines and page limits against each live CFP before the user relies on them.