167 件 ・ 関連度順
概要と使いどころ
Use ColabFold for protein structure prediction workflows: validate FASTA/CSV/A3M inputs, generate MSAs, plan batch predictions, inspect outputs, and troubleshoot optional AlphaFold, MMseqs2, JAX, GPU, and OpenMM dependencies.
日本語の概要は準備中です。原文の説明を表示しています。
Use Chai Lab / Chai-1 for molecular structure prediction, input preparation, MSA/template setup, restraints, glycans, and repo-specific troubleshooting.
日本語の概要は準備中です。原文の説明を表示しています。
Use AlphaFold 3 PyTorch for protein and biomolecular structure-prediction workflows, heterogeneous molecule inputs, PDB/mmCIF/MSA/template preparation, bounded model inference, training configuration, and local CLI or Gradio operation.
日本語の概要は準備中です。原文の説明を表示しています。
Guide alphafold2-pytorch protein sequence, MSA, distogram, angle-logit, coordinate-refinement, recycling, embedding, and structure-utility workflows with version-aware troubleshooting.
日本語の概要は準備中です。原文の説明を表示しています。
Real-world Active Directory environment constraints that silently break attacks when ignored: NTLM disabled (Kerberos fallback), AES-only KDCs (RC4 blocked by GPO), LDAP signing and channel binding requiring LDAPS on 636, Kerberos clock skew (KRB_AP_ERR_SKEW), SPNs that must be FQDNs never short names or IPs (the misleading invalidCredentials), Protected Users / LAPS / gMSA / MachineAccountQuota, LDAP 1000-object paging, and VPN latency. Use this whenever a bind, TGT request, LDAP query, or SMB negotiation fails in a way that looks like bad credentials but is really hardening, or before running any AD tooling against a domain you have not fingerprinted. Standard-tooling knowledge (netexec, impacket, certipy, bloodyAD, kerbrute), no vendor-specific engine.
日本語の概要は準備中です。原文の説明を表示しています。
Think and work like an expert Microbial Physiologist. Use when a task calls for Microbial Physiologist judgment. Reasons from Monod/chemostat (μ = D), YX/S and Pirt maintenance, Crabtree/overflow, 13C-MFA and FBA, and BMSAB taxonomy; treats OD-as-biomass yield error, FBA-as-measured-flux, washout misread, and portable ms across media as first-class failure modes.
日本語の概要は準備中です。原文の説明を表示しています。
Think and work like an expert Medical Parasitologist. Use when a task calls for Medical Parasitologist judgment. Reasons from specimen-stage fit, exposure-based pretest probability, and antigen-versus-antibody kinetics through thick/thin Giemsa films, formalin-ethyl-acetate concentration with trichrome, multiplex PCR, and EITB serology against CDC DPDx and WHO algorithms, while treating pfhrp2/3-deleted RDT false-negatives, single-O&P misses of Strongyloides, and colonization-mistaken-for-infection as first-class failure modes.
日本語の概要は準備中です。原文の説明を表示しています。
Think and work like an expert Manufacturing Engineer. Use when a task calls for Manufacturing Engineer judgment. Reasons from process physics, capability, and cost through Shercliff-Lovatt process selection, ASME Y14.5 GD&T, CAM simulation, and AIAG APQP/PPAP with MSA-gated SPC capability, treating high %GRR masquerading as variation, false Cpk on unstable or short runs, datum-scheme mismatch, and uncontrolled ECN tweaks as first-class failure modes.
日本語の概要は準備中です。原文の説明を表示しています。
Draft or review legal ops documents — NDA, MSA, SaaS agreement review checklist, vendor contract terms. Use when asked to "review this contract", "draft an NDA", "what should I look for in this agreement", or "build our contract review process".
日本語の概要は準備中です。原文の説明を表示しています。
Draft a contract or policy document from a description or template. Use when asked to "draft an NDA", "write an MSA", or "we need a vendor contract".
日本語の概要は準備中です。原文の説明を表示しています。
Active Directory exploitation after domain credentials exist: Kerberos (AS-REP/Kerberoast including cracking the ticket then using the account), delegation, NTLM coercion/relay, lateral movement, ACL abuse, ADCS ESC1-ESC17 and CVE paths, dMSA/BadSuccessor, Kerberos reflection, identity confusion, management-plane, domain trust, and domain persistence. Own the current AD chain through crack-and-use to DA, equivalent domain control, or the targeted host SYSTEM. Do not stop after requesting TGS. Host C2 belongs to /post. Operator chooses next modules.
日本語の概要は準備中です。原文の説明を表示しています。
Active Directory reconnaissance with or without credentials: user/group/computer enumeration, ACL/delegation, ADCS, modern Windows LAPS, BloodHound, Server 2025/dMSA/Ghost SPN candidates, and trust mapping. Recon only — do not exploit Kerberoast-to-DA, DCSync, or change passwords. Operator may select /ad-attack after cards are ready.
日本語の概要は準備中です。原文の説明を表示しています。
Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-source tools in the cloud, references app.tamarind.bio/api or the x-api-key header, or needs to submit batches of sequences for structural or biophysical characterization.
日本語の概要は準備中です。原文の説明を表示しています。
Cofold protein-ligand, protein-protein, and nucleic-acid complexes with Boltz-2, and predict binding affinity with its trained affinity head. Use this skill to build Boltz input YAML, run structure prediction with MSAs, pocket constraints, templates, and modified residues, screen compound libraries by cofolding, and interpret confidence scores (pLDDT, pTM, ipTM, PDE) and affinity output (binder probability and log10 IC50). Also trigger on Boltz, Boltz-1, Boltz-2, cofolding, boltz predict, affinity_pred_value, affinity_probability_binary, ipTM, or open-weights AlphaFold3 alternatives.
日本語の概要は準備中です。原文の説明を表示しています。
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.
日本語の概要は準備中です。原文の説明を表示しています。
量化专家经验调优库：按「L1 通用专家调优意见 → L2 结构化专家调优意见 → L3 模型专属专家调优意见」三级递进， 输出量化精度调优的完整手段（离群值抑制 / 量化方法·粒度·对称性选型 / 校准集调整 / 敏感层回退 / 模型专属策略）， 每条结论附专家原因分析与专家意见可信度等级。 本 Skill 是专家经验库，负责说明可选离群值抑制算法并询问用户选择哪些算法，以及回答「怎么调、哪些层需要回退及为什么」；不运行离群值抑制 processor，不修改 YAML、不执行量化、不做 EP 检查 / 服务化 / 任务评测。
日本語の概要は準備中です。原文の説明を表示しています。
对 DiT（扩散/多模态生成）模型执行 W8A8 动态（data-free）或 W8A8 MXFP8（data-free）量化。覆盖 HunyuanVideo、Wan2.2-T2V/I2V/TI2V、FLUX.1-dev（已迁移）、SD3、Sana、HunyuanDiT、CogViewX 等。YAML apiversion 固定 multimodal_sd_modelslim_v1，统一 MultimodalPipelineInterface 重构路径（不再保留 LegacyMultimodalPipelineInterface）。模板与字段以 msmodelslim/model/hunyuan_video/model_adapter.py（唯一已迁移到重构路径且 lab_practice YAML 已 validated 的 DiT）为参考；其它 DiT 需按各自推理仓的 `parse_args` 调整字段集合。data-free 指不引入外部激活校准数据，spec.dataset（校准集短名，短名如 wan2_2_t2v；enable_dump: false 时不参与 dump）仍必填；精度调优通过下游经验库 L2 §7 + 直接调 `quantization-expert-experience-tuning-rules/scripts/apply_rollback.py`（整层回退）扩展 exclude 列表，闭环由 `quantization-accuracy-tuning-orchestrator` 调度。
日本語の概要は準備中です。原文の説明を表示しています。
End-to-end automated model quantization and accuracy tuning workflow. Use when user asks for automated model quantization and accuracy tuning, e.g. "自动量化", "量化调优", "一键量化", "精度调优", etc. 当用户给出多卡（≥2 卡）卡号时，量化阶段通过 EP 并行适配（msmodelslim-ep-parallel-adaptation）保证多卡 EP 并行，调优主流程仍在本 Skill。
日本語の概要は準備中です。原文の説明を表示しています。
Use when 量化调优闭环中需要生成或修改一轮调优所需的 Practice YAML，包括敏感层分析、策略决策、写出 YAML 文件和校验。
日本語の概要は準備中です。原文の説明を表示しています。
在 W8A8 动态量化后，用 MindIE-SD 冒烟测试 DiT 量化权重是否可加载（可选 skill）。与 `quant-tuning-evaluate`（DiT 扩展节）的区别：本 skill 仅做"能跑通 + 权重可用"的轻量验证（4~16 条 prompt，几分钟出结果），不算分；后者产出视频集交 `quant-tuning-score-dit`（AISBench-VBench 16 维度）评分，是调优回路一环。不引入 vLLM-Ascend、不做精度指标评估（FID/CLIP-score 等）。
日本語の概要は準備中です。原文の説明を表示しています。
执行模型量化。通过 msmodelslim quant 依据 Practice YAML 对模型进行量化。
日本語の概要は準備中です。原文の説明を表示しています。
Aggregate DiT inference outputs into per-dimension VBench metrics via AISBench. Run after the quant-tuning-evaluate DiT workflow produces a directory of mp4s and the user supplies a VBench-1.0-mini JSON + pre-populated cache dir. Single mode (Standard).
日本語の概要は準備中です。原文の説明を表示しています。
重采样：把已有多轮对话数据的每条 assistant 回答丢弃，用 verifier 模型/vLLM 服务逐轮重生成，产出可直接进训练的预分词样本（每行含 input_ids/loss_mask）。依赖支持 return_token_ids 的 OpenAI 兼容 chat 服务（服务需由用户提前就绪，本技能不负责拉起服务）。触发：用某模型对某个数据集做重采样/重生成（如“对这个数据集用这个模型做重采样”）、把对话回答用模型重写、生成预分词样本/on-policy/MTP 训练数据。
日本語の概要は準備中です。原文の説明を表示しています。
Compares two Prof datasets (GPU vs NPU / NPU vs NPU) by auto-installing and calling msprof-analyze compare, then parses the result xlsx into HTML report and Chinese xlsx. Invoke when user provides two prof dirs to compare, or has a compare result xlsx to analyze/translate.
日本語の概要は準備中です。原文の説明を表示しています。