「math」の検索結果

从官方或内置模板创建、编译和校验数学建模 LaTeX 论文项目，并可配合 DOCX 工具把完整 LaTeX 论文转换为 Word。

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。

Convert PDF documents to Markdown using marker_single. Use when Claude needs to extract text content from PDFs while preserving LaTeX formulas, equations, and document structure. Ideal for academic papers and technical documents containing mathematical notation.

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。

Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). Use proactively when debugging a training pipeline that shows no improvement, loss anomalies, reward stagnation, NaN gradients, or other unexpected behavior during reinforcement learning fine-tuning. Work through all pipeline stages — reward, advantages, log-probs, loss, generation/decoding — before concluding the diagnosis is complete; stopping after one or two fixes is a common failure mode. Covers log-probability math, advantage estimation, numerical stability, reward processing, and generation/decoding pipeline issues.

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。

AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching `acopf-math-model.md` and MATPOWER branch fields. Use when computing branch flows in either direction, aggregating bus injections for nodal balance, checking MVA (rateA) limits, computing branch loading %, or debugging sign/units issues in AC power flow.

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。

Reference for the GRPO (Group Relative Policy Optimization) algorithm. Use when implementing, debugging, or verifying a GRPO training pipeline — covers the mathematical formulation (group-relative advantages, clipped surrogate loss, KL penalty), the training loop (generate → score → advantage → loss), log-probability computation, advantage estimation, and relationship to PPO/REINFORCE.

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。

Telegram Bot skill for sending and editing Telegram messages via Bot API. Use when Bub needs to: (1) Send a message to a Telegram user/group/channel, (2) Reply to a specific Telegram message with reply_to_message_id, (3) Edit an existing Telegram message, or (4) Push proactive Telegram notifications. Prefer rich formatted messages (headings, lists, tables, blockquotes, math, collapsible details, captioned media) over plain markdown whenever the content is more than one short paragraph.

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。

Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness must be bulletproof and single-pass or round-by-round review is too slow and too shallow. Invoke for "audit this rigorously", "find ALL the bugs/gaps", "make this rock solid", "converge faster on correctness".

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。

Write game shaders from cross-engine fundamentals — the vertex→fragment pipeline, coordinate spaces, UV math, and common 2D/3D effects (tint, UV scroll, dissolve, outline, fresnel rim, vignette) in GLSL with HLSL equivalents. Use when the user mentions shaders, fragment/pixel shader, vertex shader, UV, GLSL, HLSL, or effects like dissolve, outline, or rim light.

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。

Compress tool outputs, logs, and JSON before they enter the context window — structural compression via a deterministic stdlib script (schema + samples + stats instead of 300 raw rows), no API, no summarization loss. Use when asked shrink this tool output, my context is full of JSON, compress these logs before analysis, or stop wasting tokens on raw data. Produces the crushed artifact with its token math shown, the crush-or-keep decision rules, and the fetch-the-original escape hatch.

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。

Decode a brand deal or UGC contract before signing — usage rights, exclusivity windows, whitelisting, payment terms, and kill clauses ranked 🔴🟡🟢 by what they can cost a creator, plus the counter-ask email. Use when a creator says 'is this brand deal fair', 'what does perpetual usage mean', 'they sent me a contract', or 'should I sign this collab agreement'. Produces a clause-by-clause decode, a money-math check on the rate, and a ready-to-send negotiation email. Not legal advice.

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。

Audit a landing page or funnel step and produce a prioritised CRO test plan. Use when asked to improve conversion rate, audit a landing/signup/checkout page, reduce funnel drop-off, or plan A/B tests for a page. Produces a CRO plan — a heuristic conversion audit, the diagnosed friction, prioritised test hypotheses (ICE), test designs with sample-size math, and the measurement guardrails.

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。

Never get auto-renewed into another year again — the contract inventory with the dates that matter (notice deadlines, not renewal dates), the calendar system with decision-time buffers, and the renewal-decision ritual that renegotiates instead of rubber-stamping. Use when asked track our contracts and renewals, we got auto-renewed again, when do we have to decide on this vendor, or set up renewal management. Produces the inventory with notice-deadline math, the alert system, the renewal-decision checklist, and the negotiation-window playbook.

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。

Decode a car lease offer — the money factor converted to APR, the cap-cost math, mileage and disposition traps, and what to negotiate. Use when asked to decode my car lease, is this lease deal good, what's a money factor, or review this lease before I sign. Produces the real-numbers decode (money factor → APR, total lease cost), the trap list with dollar exposure, and the negotiation points dealers expect to concede.

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。

Decide when to buy a big-ticket item to get the best price — the sales cycles, model-refresh timing, and 'buy now vs wait' math for the specific thing you want. Use when asked when's the best time to buy [item], should I wait for a sale, is now a good time to buy, or when do [products] go on sale. Produces the typical discount calendar for that category, whether a new model/version is due (and if the current one will drop), a buy-now-vs-wait recommendation for your timeline, and price-tracking tactics — flagging that timing is a guide, not a guarantee.

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。

Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO asks what the AI tools returned, when renewing AI contracts, when consolidating overlapping AI subscriptions, or to build the measurement plan before the next spend. Produces an ROI audit with per-tool verdicts (keep/consolidate/cut), the honest-measurement method behind each number, and a baseline plan for whatever can't be scored yet. To forecast ROI before an investment use roi-estimator; this skill measures what already happened.

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。

Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are eroding seat counts, when asked to migrate to usage- or outcome-based pricing, to price an agent/API tier, or to defend revenue as customers automate their own usage. Produces a pricing migration plan: the new value metric, fences, agent-tier design, cannibalisation math, and a phased migration for existing customers. For general pricing and packaging strategy use pricing-strategy.

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。

Help users distinguish between deceptive tarpit ideas and high-potential opportunities by applying rigorous frameworks for market timing, business math, and user demand.

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 optimizing the performance of an existing native scalar expression in the datafusion-comet-spark-expr crate (native/spark-expr/) — casts, string/JSON/array/math kernels that run per-row or per-batch. Covers benchmarking, keeping output bit-identical, and the no-regression gate. Not for adding new expressions (use implement-comet-expression) or wiring upstream functions (use wire-datafusion-function).

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。

Find, show, open, or identify shipped MathWorks example models that demonstrate a concept, block, or application domain, and return the command to open them.

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。

Runs JACKS (Joint Analysis of CRISPR/Cas9 Knockout Screens; Allen et al 2019 Genome Research) which models per-sgRNA log-fold-change as the product of a treatment-dependent gene-essentiality term and a treatment-independent guide-efficacy term. Covers the Bayesian decomposition math, the hierarchical efficacy prior shared across screens performed with the same library, when JACKS outperforms MAGeCK (multi-screen joint analysis, libraries with broad efficacy variance) and when it does not (single screen, novel libraries with no prior efficacy), library-reuse efficacy transfer, downstream essentiality interpretation, and the 2.5x sample-size reduction enabled by efficacy-aware testing. Use when running multiple screens with the same library, when guide-level noise is suspected to dominate per-gene signal, when reusing published essentiality reference screens for efficacy priors, or when comparing screens performed across cell lines that share library but differ biologically.

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。

Designs and analyzes in vivo CRISPR screens in animal tumor models, organoids, and immune-cell adoptive transfers. Covers bottleneck math (250x cells/sgRNA requires ~25M cells implanted; impossible for most syngeneic models, forcing focused libraries), focused library design (Manguso 2017 Nature 547:413 immune screen; Chen 2015 tumor screens), CRISPR-StAR intrinsic-control screening (Uijttewaal 2025 Nat Biotechnol 43:1848), clonal-dynamics-limited detection, tumor-explant DNA recovery, syngeneic vs xenograft vs PDX considerations, and the relationship to downstream MAGeCK / drugZ analysis. Use when designing in vivo CRISPR screens for tumor / immune / metastasis biology, choosing focused vs genome-wide for animal models, addressing bottleneck-induced clonal collapse, picking the syngeneic / xenograft / PDX model, integrating in vivo with in vitro results, or applying CRISPR-StAR for animal experiments.

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。

Quantifies CRISPR editing outcomes with CRISPResso2 (Clement 2019 Nat Biotechnol) across Cas9-nuclease (indels, HDR), CBE and ABE base editors (target conversion + bystander), and prime editor (pegRNA-templated) modes. Covers single-amplicon (CRISPResso), multi-sample batch (CRISPRessoBatch), pooled-amplicon (CRISPRessoPooled), WGS off-target (CRISPRessoWGS), and sample-comparison (CRISPRessoCompare) workflows; quantification-window math that controls what is called edited; substitution-vs-indel diagnostic to distinguish BE from Cas9 contamination; MMEJ deletion pattern interpretation; allele-frequency tables; and failure modes from amplicon misalignment or contamination. Use when quantifying editing from amplicon sequencing, choosing CRISPResso mode by design, distinguishing intended edits from bystanders and indel byproducts, debugging low-alignment runs, or generating publication-grade editing reports.

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。

Analyzes CRISPR drug-modifier (chemogenomic) screens with drugZ (Colic et al. 2019 Genome Med), a bidirectional Z-score method that identifies synthetic-lethal sensitizing genes and resistance-conferring suppressor genes from vehicle vs drug comparisons. Covers vehicle-anchored design (not Day-0), the bidirectional Z math giving greater sensitivity to small-effect hits than MAGeCK / STARS / edgeR / RIGER on drug screens, per-gene sumZ and normZ, synth (sensitizer) vs supp (suppressor) FDR, multi-dose handling, integration with control sgRNAs, and comparison with MAGeCK MLE with dose covariate. Use when running a drug-modifier CRISPR screen, identifying sensitizing or resistance genes for a drug candidate, choosing drugZ vs MAGeCK MLE for chemogenomic analysis, troubleshooting low-effect drug screens where MAGeCK lacks sensitivity, or designing a drug-screen layout (vehicle vs drug arms).

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。

Analyzes base-editing screens for variant function. Covers library design (Hanna 2021 ClinVar-scale CBE screen benchmarked on BRCA1/2, Cuella-Martin 2021 DDR saturation), CBE vs ABE chemistry choice (BE3/BE4 vs ABE7.10/ABE8.20/ABE8e), editing-window math (positions 4-8 from PAM-distal end; 4-7 for ABE7.10), bystander-edit quantification and the variant-call ambiguity it creates, sgRNA-efficiency filtering before hit calling, indel byproduct interpretation, the substitution-vs-indel diagnostic, variant annotation against ClinVar / COSMIC, and the Broad be-validation-pipeline. Use when designing a BE variant screen, choosing CBE vs ABE for a specific edit, interpreting bystander-confounded hits, distinguishing functional signal from indel artifact, integrating CRISPResso2 output with screen scoring, or deciding BE vs PE for SNV installation.

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。