134 skills · sorted by relevance
Check an educational practice or task for cultural bias, WEIRD assumptions, and cross-cultural validity. Use when adapting resources for diverse contexts or questioning universal claims.
The English summary is being prepared. Showing the original description.
Audit a proposed assessment for construct validity, reliability, and alignment to learning objectives. Use when reviewing or quality-assuring assessments before deployment.
The English summary is being prepared. Showing the original description.
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
The English summary is being prepared. Showing the original description.
Audit a proposed assessment for construct validity, reliability, and alignment to learning objectives. Use when reviewing or quality-assuring assessments before deployment.
The English summary is being prepared. Showing the original description.
Check an educational practice or task for cultural bias, WEIRD assumptions, and cross-cultural validity. Use when adapting resources for diverse contexts or questioning universal claims.
The English summary is being prepared. Showing the original description.
Drafts a defendant's Answer with Invalidity Contentions responding to a U.S. patent infringement complaint. Covers FRCP 8(b) admissions/denials, affirmative defenses, and PLR 3-3 invalidity contentions with claim charts under 35 U.S.C. §§ 101, 102, 103, 112. Use when representing a defendant in the pleadings phase of federal patent litigation who must respond to an infringement suit and assert prior art, anticipation, obviousness, or § 112 defenses.
The English summary is being prepared. Showing the original description.
Simulate quantum dynamics, steady states, and spectra with QuTiP 5. The skill guides solver selection and checks physical assumptions, units, state validity, and numerical convergence so local simulation results can be reviewed with their limitations.
Model what an agent believes, wants, and commits to doing. Connect external facts to goals and plans using structured relationships, with evidence and validity periods that help trace why the agent chose an action.
Build or review tables that match patent claim elements or civil legal requirements to product information and evidence. Each mapping cites a precise source location, while a separate gap list identifies evidence still needed for attorney analysis.
Update the data structure of a deployed Convex app through staged changes. Using @convex-dev/migrations, the skill fills or transforms existing records, checks validity and record counts, and makes new fields required after migration finishes.
Routes between five assessment pathways — formative, rubric/criteria, authentic/performance, peer/self, and diagnostic — with validity and equity checks. Use when a teacher needs help choosing how to assess.
The English summary is being prepared. Showing the original description.
Think and work like an expert Comparative Medicine Researcher. Use when a task calls for Comparative Medicine Researcher judgment. Reasons from species biology, translational validity, and the 3Rs through model-validity frameworks, IACUC protocols, ARRIVE 2.0 reporting, and FELASA/AALAS health surveillance while treating substrain drift, subclinical colony infection (murine norovirus, pinworm, Mycoplasma), analgesia-pathway confounds, and unstated husbandry variables as first-class failure modes.
The English summary is being prepared. Showing the original description.
Query patent legal status information from the Nexscope (Nexscope) database. Triggered when users mention patent legal status, patent validity check, patent status query, patent event history, simple legal status, legal events such as transfer, license, pledge, opposition, litigation, re-examination, patent legal status, patent validity, patent events, transfer/license/pledge, Nexscope, or patent status lookup. Also triggered when users ask whether a patent is active, inactive, pending, expired, granted, withdrawn, or revoked, or want to look up legal status by patent ID or publication number.
The English summary is being prepared. Showing the original description.
Routes between five assessment pathways — formative, rubric/criteria, authentic/performance, peer/self, and diagnostic — with validity and equity checks. Use when a teacher needs help choosing how to assess.
The English summary is being prepared. Showing the original description.
The logic of sentential connectives -- and, or, not, if-then, if-and-only-if -- as a formal system. Covers syntax (well-formed formulas), semantics (truth tables), satisfiability, validity, logical equivalence, normal forms (CNF, DNF), natural-deduction rules, and common translation pitfalls. Use when formalizing arguments with propositional structure, checking validity mechanically, or teaching the foundations of formal reasoning.
The English summary is being prepared. Showing the original description.
Systematic evaluation of arguments for structure, validity, soundness, and charitable interpretation. Covers premise identification, conclusion extraction, argument mapping, steel-manning, and the distinction between validity (form) and soundness (form plus true premises). Use when assessing an argument, reconstructing an opponent's position fairly, or preparing a rebuttal.
The English summary is being prepared. Showing the original description.
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
The English summary is being prepared. Showing the original description.
Audit whether a declared local review evaluation can support fair quality claims. Use only when the user explicitly asks to audit review-eval validity or use the bundled synthetic fixture.
The English summary is being prepared. Showing the original description.
Validates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantification, geometric checks (planarity, vdW overlap, bond/angle distortion), and pose-energy reasonableness. Filters AI-docking outputs (DiffDock, EquiBind, NeuralPLexer) where ~50% of poses fail physical-validity tests. Use when QC-ing docking results, comparing classical vs ML docking outputs, or filtering pose lists before SAR analysis.
The English summary is being prepared. Showing the original description.
研究概要・中間発表予稿の「研究としての筋」を、論理の鎖(L1背景→L2関連研究と限界→L3課題(差分)→L4仮説→L5評価→L6位置づけ)として1リンクずつ採点し、さらに端点間の整合(掲げた構成概念=旗と評価指標=物差しのズレ=construct validity)を照合するスキル。各文の綺麗さ(→articulation-check)でも汎用の弱点(→weakness-analyze)でもなく「リンク間が繋がっているか／旗と物差しが一致しているか」を見る。骨子・位置づけ・仮説・課題設定・研究の一貫性を見てほしい、research framing を見て、と言われたとき。旧名 research-framing-check。
The English summary is being prepared. Showing the original description.
Validates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantification, geometric checks (planarity, vdW overlap, bond/angle distortion), and pose-energy reasonableness. Filters AI-docking outputs (DiffDock, EquiBind, NeuralPLexer) where ~50% of poses fail physical-validity tests. Use when QC-ing docking results, comparing classical vs ML docking outputs, or filtering pose lists before SAR analysis.
The English summary is being prepared. Showing the original description.
Validates docked / generated protein-ligand poses using PoseBusters physical-validity tests, strain energy quantification, geometric checks (planarity, vdW overlap, bond/angle distortion), and pose-energy reasonableness. Filters AI-docking outputs (DiffDock, EquiBind, NeuralPLexer) where ~50% of poses fail physical-validity tests. Use when QC-ing docking results, comparing classical vs ML docking outputs, or filtering pose lists before SAR analysis.
The English summary is being prepared. Showing the original description.
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
The English summary is being prepared. Showing the original description.
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
The English summary is being prepared. Showing the original description.