CatMaster

Proposal-first scientific writing pipeline. Three modes (compose/revise/hybrid) with four-layer QA pipeline. Enforces evidence-before-prose, argument-before-sections, and contracts-before-paragraphs.

Use this skill for managed MLFF molecular dynamics, restart-safe trajectory continuation, ensemble selection, and trajectory-health analysis when mlff_md is available.

Use only after a DPDispatcher-backed managed execution tool returns a failure with receipt/context fields, an ambiguous transport error, or evidence of a possible orphan job. Do not use for a pending synchronous call or ordinary success.

Use this skill before remote_submission or remote_submission_batch to build and verify canonical stage directories for registered DPDispatcher tasks, including deterministic MLFF SP/relax, MD, and NEB input layouts.

Use this skill for managed MLFF NEB optimization after a complete locally interpolated fixed-image path has been validated.

Use this skill for MLFF single-point screening, ranking, and geometry relaxation when choosing among enabled MACE, FairChem UMA, MatterSim, or ORB-v3 backends.

Use this skill for dispatching prepared VASP jobs with remote_submission or remote_submission_batch, choosing valid stage layouts, and collecting clean failure evidence.

Use this skill for the execution stage of NEB and dimer workflows, especially the detailed run protocol for plain-NEB to CI-NEB refinement or NEB/frequency/dimer refinement.

Use this skill for NEB and dimer preparation work: validate endpoint pairs, choose image counts, build image trees, prepare VASP NEB roots, and prepare dimer-ready inputs or raw mode guesses.

Use this skill for candidate ranking and relabel-loop bookkeeping when the task is to select the next structures for expensive reference calculations from a structure pool or curated dataset.

Use this skill for remote MACE fine-tuning/training plus held-out evaluation using the validated reference-script conventions, especially the `mace-mh-1 + omat_pbe` replay-style path with explicit E0 and replay controls.

Use this skill for MLFF single-point screening or pre-relaxation of molecules, conformers, and clusters before xTB or ORCA validation.

Use this skill for slab construction, vacuum and layer choices, surface supercell setup, and atom-fixing strategy in heterogeneous catalysis workflows.

Use this skill for turning one relaxed bulk reference into a controlled slab/termination screening set, including slab generation, freezing policy, optional lateral expansion, and standardized VASP ranking runs.

Render an existing Markdown note, report, or summary directly to a stable PDF without rewriting it as LaTeX; use when the requested source is Markdown and the deliverable is PDF.

Use this skill for VASP MD execution and post-analysis when the goal is trajectory-based MSD/RDF/diffusion evidence rather than a generic VASP run log.

Use this skill for broad or focused literature discovery, evidence selection, full-text grounding, deduplication, and final bibliography generation with CatMaster's active LitReview tools.

Use this skill to acquire legitimate open-access or institution-authorized paper full text through CatMaster's controlled agent-browser session, then ingest it into the local evidence corpus.

Use this skill when a task needs visual inspection of atomic structures, adsorption geometries, slab-site context, or image-based sanity checks before or alongside numerical analysis.

Use this skill for adsorption-candidate generation, execution, and first-pass ranking when screening one adsorbate across one slab family with reproducible site provenance and thermochemistry-ready metadata.

Use this skill for adsorption-site enumeration and adsorbate placement workflows, including candidate screening setup and batch structure generation.

Use this skill for materials discovery and bulk structure selection before slab construction, including database query strategy, candidate filtering, and export readiness.

Use this skill for source-grounded CP2K AIMD preparation, restart staging, generic execution handoff through cp2k_execute, and run-health inspection.

Use this skill to continue CP2K AIMD from existing result directories without losing restart context or overwriting previous outputs.

Use this skill for generic CP2K run-health analysis after cp2k_execute, without replacing property-specific parsers.

Use this skill for LAMMPS NVE/NVT/NPT/annealing preparation, execution, restart output, and generic MD health analysis.

Use this skill for LAMMPS force-field minimization stages and generic minimization log inspection.

Use this skill for source-grounded LAMMPS force-field validation and preparation of minimization, MD, and restart stages.

Use this skill to continue LAMMPS stages from restart files while preserving prior stage context.

Use this skill for generic CP2K/LAMMPS trajectory and run-health checks and for deciding when task-specific trajectory parsing is required.

Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default. Use this skill whenever the user asks to input text and automatically get references, add citations to a paragraph/manuscript, find Nature-series or CNS support for statements, create text-to-reference correspondence, "分段引用", "自动给出引用", "Nature系列引用", "CNS及子刊", "支撑文献", "补引用", "找引用", or export EndNote/RIS/ENW/Zotero RDF. Also trigger on general academic-writing citation needs even without the word "Nature", such as adding references while writing a paper, finding sources/literature for a claim, building a reference list, citation/referencing for academic writing, and Chinese phrasings like 学术写作引用、写论文加引用、写paper找文献、加参考文献、配文献、引用文献、文献支撑.

Complete automated literature discovery pipeline: multi-source search → six-dimension scoring → fine reading → formatted delivery → archival. Combines a configurable engine with daily cron-driven application layer. Works with Feishu, Telegram, or any messaging platform.

Build full-paper Chinese-English side-by-side, figure/table-aware, source-grounded Markdown readers for journal or conference papers from PDF, DOI, arXiv, publisher HTML, or pasted text. Use whenever the user asks to translate or read a paper, make 中英文对照/原文对照/全文翻译解读, extract figures or tables into the right positions, preserve figure/table placement near relevant prose, or keep exact source anchors for every block. This skill must not degrade into a summary-only output unless the user explicitly asks for a summary. Also trigger on general paper-reading and translation requests even without the word "Nature", such as reading/translating an academic paper, literature reading, understanding a paper, and Chinese phrasings like 读论文、精读论文、论文翻译、文献翻译、文献阅读、学术阅读、帮我读这篇文章、翻译这篇paper.

对学术文献逐条执行多源交叉验证，逐字段对比作者、标题、年份、卷期、页码， 标记卷年/DOI年冲突、作者顺序异常、页码偏差等问题，输出结构化验证报告。 可批量处理整篇论文/开题报告的参考文献列表，也可单条校验，支持与 Zotero 同步修正。

Use this skill for generating adsorbates and reaction intermediates, standardizing molecular inputs, and preparing structures for adsorption placement.

Use this skill for post-relax bulk electronic-structure workflows when the goal is a clean DOS or band-path-ready calculation sequence with explicit KPOINTS provenance and result summaries.

Use this skill for bulk-reference preparation and analysis when a workflow needs a relaxed bulk baseline, symmetry-inequivalent site ledger, and optional band/DOS follow-up from one consistent starting structure.

Use this skill for source-grounded CP2K conventional DFT preparation in materials workflows: single-point, fixed-cell geometry optimization, cell optimization, frequency, and DOS-style stages.

Use this skill for CP2K DOS/PDOS, band-style, and population-analysis follow-up planning where parsing is task-specific and should usually be scripted.

Use this skill for source-grounded CP2K NEB and dimer path-refinement preparation through the single cp2k_prepare tool.