731 个 · 按相关度排序
Deep learning for drug discovery. 60+ models (GCN, GAT, AttentiveFP, MPNN, ChemBERTa, GROVER), 50+ featurizers, MoleculeNet benchmarks, HPO, transfer learning. Unified load-featurize-split-train-evaluate API. For fingerprints use rdkit-cheminformatics; for featurization-only use molfeat.
中文简介正在准备中。当前显示原文说明。
AiZynthFinder retrosynthetic route planning (CASP) from AstraZeneca Molecular AI. Monte Carlo tree search guided by a template-based neural expansion policy recursively disconnects a target SMILES until precursors are found in a purchasable stock. Covers config.yml (v4 format), aizynthcli batch screening, the AiZynthFinder/AiZynthExpander Python API, one-step disconnections, custom stocks via smiles2stock, scorers, Retro*/breadth-first/DFPN search alternatives, and reading output.json.gz / trees.json. Use for synthesis route planning, synthesizability screening, and building-block/precursor search. For reaction barriers use neb-irc-activation-energy; for 2D reaction scheme drawing use rdkit-chemdraw-cdxml.
中文简介正在准备中。当前显示原文说明。
Molecular featurization hub (100+ featurizers) for ML. SMILES to fingerprints (ECFP, MACCS, MAP4), descriptors (RDKit 2D, Mordred), pretrained embeddings (ChemBERTa, GIN, Graphormer), pharmacophores. Scikit-learn compatible with parallelization/caching. For QSAR, virtual screening, similarity, and molecular DL.
中文简介正在准备中。当前显示原文说明。
Auto-annotate plasmids with features (promoters, terminators, resistance, origins, tags, fluorescent proteins) via BLAST against curated DBs (Addgene, fpbase, SnapGene). FASTA or raw sequence in; annotated GenBank, interactive HTML maps, CSV tables out. Handles circular topology. Use to verify synthetic constructs, prep Addgene submissions, share maps, or batch-annotate cloning libraries.
中文简介正在准备中。当前显示原文说明。
Art direction for FPS, TPS, shooter, battle royale, and extraction-shooter maps and props in Blender with sightline and cover language.
中文简介正在准备中。当前显示原文说明。
When a founder needs demo scripts, discovery call frameworks, objection handling, RFP/RFI responses, competitive feature matrices, POC planning, or closing playbooks. Activate for sales calls, demo prep, talk tracks, bid responses, competitor comparisons, or pre-sales engineering.
中文简介正在准备中。当前显示原文说明。
Audits business spreadsheet models (.xlsx, .xlsm, or Google Sheets exported to .xlsx) for structural integrity errors and explains each fix -- budgets, forecasts, pricing models, commission calculators, FP&A packs, ops trackers, not only banking models. A bundled openpyxl script finds hardcoded numbers inside formulas, typed values pasted over formulas, inconsistent formulas across a row or column,
中文简介正在准备中。当前显示原文说明。
Extract structured data from construction PDFs. Convert specifications, BOMs, schedules, and reports from PDF to Excel/CSV/JSON. Use OCR for scanned documents and pdfplumber for native PDFs.
中文简介正在准备中。当前显示原文说明。
Manage OpenViking collections (OV libraries) from the command line with `ov-cp` — list / create / get / update / usage / get the data-plane API key / delete, plus managing the users and account data spaces of an enterprise-tier library (list / create / register / update / delete), account-scoped users / API keys / usage, and configuring how a library is billed (AgentPlan AFP deduction vs Volcano pay-as-you-go, `--pay-type` / `--seat-id`). Use when the user wants to provision or inspect an OpenViking library, fetch a library's data-plane API key, do the create→get-key cold-start, manage a library's users or accounts / 数据空间, set or switch a library's billing, or otherwise drive the OpenViking control plane (topapi). Authenticates with an Ark AgentPlan ApiKey.
中文简介正在准备中。当前显示原文说明。
Find out why a native Linux program crashed, from its core dump and the binary, with REA, and turn that into a root cause and a bug report. Use when the user has a core file (./core, coredumpctl, a crash artifact from CI or production) or a segfault, abort, SIGFPE, SIGBUS or SIGILL in a C, C++, Rust, Go or other native program, and asks why it died. Works on stripped binaries with no source (functions named from unwind tables, then a walk back from the crashing function to its caller). Read-only - never runs the program.
中文简介正在准备中。当前显示原文说明。
优化实际模型推理链路，将正确性对齐、分段 profiling、显存与数据搬运、TensorRT/ONNX/PyTorch 后端、attention/kernel、FP8/compile、缓存与少步采样、质量回归、GPU 成本和服务验收串成同一实验闭环。当用户要求推理提速、降低显存或 GPU 成本、复现模型效果、定位 GPU 利用率低、优化图像/视频/扩散模型或自托管 LLM 时使用，提供 model inference performance optimization 的脱敏案例。纯 API 调用、提示词或 token 用量优化，以及电脑卡顿，不进入本技能的模型推理实验流程。
中文简介正在准备中。当前显示原文说明。
Create Request for Proposals with requirements specifications, evaluation criteria, scoring rubrics, timelines, and compliance requirements
中文简介正在准备中。当前显示原文说明。
Evaluate, compare, and manage vendor relationships. Trigger with "evaluate this vendor", "compare vendors", "vendor review", "should we renew", "RFP", or when the user is making procurement or vendor decisions.
中文简介正在准备中。当前显示原文说明。
Push interfaces past conventional limits with technically ambitious implementations. Whether that's a shader, a 60fps virtual table, spring physics on a dialog, or scroll-driven reveals — make users ask "how did they do that?"
中文简介正在准备中。当前显示原文说明。
A 60 to 75 s hand-drawn ink film of the agent's day with its own user ("a day in my life as <name>'s agent"): one average session from the user's local Claude Code history, beginning to end. The story follows what they actually do (coding, tests, docs, shipping, videos, whatever the history shows), told with their real words (first message, check-ins, corrections, praise, memory titles). It is drawn in two-tone p5.brush strokes that boil at 8 fps and scored for strings composed note-for-note on the film's clock (the typed "claude" is the theme). Trigger on: "day in my life as my agent", "a film about me and my agent", "what is it like to be my agent", "animate your day with me", "make a video of our sessions". Covers harvesting the routine and receipts, the privacy gate, the chapter toolbox, the ink kit, the score, render and QC.
中文简介正在准备中。当前显示原文说明。
Captions living in 3D space around a talking head: a camera flies between the speaker and the words (whip-in, parallax truck, push), caption groups sit at different depths so camera moves pull them apart, hero words hide BEHIND the speaker through an alpha matte, a ring of words wraps round the speaker and turns in front of them, focus racks between depths, and text steps at 15 fps with ghost motion blur. Works in any type style (editorial serif, bold sans) or hand-drawn (p5.brush write-on). Trigger on: "3D text", "3D camera captions", "text around / behind the speaker", "camera moves through the text", "depth captions on my avatar video". Covers prep (portion, padded plate, matte, word clock, font metrics), the shot grammar, depth rules, QC, and limits.
中文简介正在准备中。当前显示原文说明。
Create tailored sales proposals and RFP responses that address prospect needs, articulate solution value, and include pricing, timelines, and social proof. Use when the user requests proposal generation or provides relevant inputs for this workflow.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Molecular Geneticist. Use when a task calls for Molecular Geneticist judgment. Reasons from sequence-as-hypothesis, reference context (genome build, MANE/RefSeq transcript, HGVS), and allele-level molecular consequence through ACMG/AMP-ClinGen criteria, IGV/VEP/SpliceAI/gnomAD/ClinVar review, MIQE-compliant qPCR/ddPCR, and Sanger/NGS validation while treating allele dropout, pseudogene/paralog misalignment, FFPE deamination, contamination and barcode bleed, and transcript/build mismatch as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Machine Learning Engineer. Use when a task calls for Machine Learning Engineer judgment. Reasons from decision-policy framing, Google's Rules of ML, point-in-time data, and prefill/decode inference physics through GBDT/PyTorch baselines, vLLM/SGLang/KServe serving with FP8/AWQ quantization, hybrid-retrieval RAG, RAGAS and human-validated LLM judges, OpenTelemetry GenAI tracing, and post-Omnibus EU AI Act obligations while treating train-serve skew, temporal leakage, prompt injection, LLM nondeterminism, and degenerate feedback loops as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Molecular Pathologist. Use when a task calls for Molecular Pathologist judgment. Reasons from tumor cellularity, assay-specific LOD, and AMP/ASCO/CAP Tier I–IV classification; validates IHC (CAP ≥90% concordance), FISH (HER2/ALK break-apart), and NGS oncology panels under CAP/CLIA MM09 while treating FFPE deamination, HER2-low/ultralow scoring, PD-L1 TPS vs CPS, and ctDNA CHIP as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Dentist-Scientist. Use when a task calls for Dentist-Scientist judgment. Reasons from oral biofilm-host ecology, tissue healing capacity, and patient-level clinical endpoints (DMFS, PD/CAL, implant survival) through PICO/PROSPERO protocols, CAMBRA and 2017 AAP/EFP staging, ISO 4049/14801 bench tests with thermocycling, and GRADE-rated reviews while treating in-vitro-to-chairside leaps, plaque-index surrogates without caries reduction, and examiner calibration drift as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Cheminformatician. Use when a task calls for Cheminformatician judgment. Reasons from Standard InChI identity and RDKit sanitization through ChEMBL pChEMBL harmonization, Morgan/ECFP fingerprints, scaffold splits and applicability domains, while treating tautomer collapse, KNIME-vs-Python canonicalization drift, and random-split QSAR leakage as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Algorithms Researcher. Use when a task calls for Algorithms Researcher judgment. Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS (Williamson–Shmoys), and Instance Space Analysis over DIMACS10/MIPLIB 2017/SuiteSparse while treating amortized-versus-average-case conflation, unproven greedy killed by a 4-node counterexample, Monte Carlo without a false-match probability, DIMACS10 suite overfitting, and 'linear time' hiding word-size tricks over bit-length L as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Produce video with Moonvalley's Marey model family (Marey Realism v1.5) — a filmmaker-oriented, 1080p/24fps generative video model marketed as trained exclusively on licensed data. Use this skill when a task asks for Marey or Moonvalley specifically, when a brief demands brand-safe / legally reviewed AI video for commercial or studio work, or when the request needs Marey's director-style controls (camera trajectory, motion transfer, pose transfer, keyframing, reference conditioning). It covers what "commercially safe" really means versus the actual terms of service, access routes (Moonvalley web / Voyager, the fal API, ComfyUI), pricing, capability limits, prompt and reference strategy, where Marey fits production versus where other models win, iteration, and quality review. Do not use it for audio generation, for photoreal talking-head dialogue, or as a generic "best video model" default.
中文简介正在准备中。当前显示原文说明。