1,280 件 ・ 関連度順
概要と使いどころ
Rigorous methodology for evaluating ML models on established benchmarks. Covers proper train/val/test splits, baseline verification from original papers, exact metric formula discrepancies, data-leak detection checklist, multi-seed robustness, and honest reporting templates. Use when claiming to beat published baselines, writing methods papers, or auditing existing results.
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。
Assigns honest lipid annotation levels, designs class-based internal-standard quantification, and runs lipid-aware differential and enrichment analysis with lipidr, guarding against in-source-fragment phantoms, sn-position over-claims, and invalid cross-class quantification. Use when naming or canonicalizing lipid species (shorthand separators, Goslin), deciding shotgun vs RP vs HILIC LC-MS, picking internal standards (SPLASH/EquiSPLASH), interpreting MS-DIAL/LipidSearch output, or comparing lipid classes. For general feature detection see metabolomics/xcms-preprocessing and metabolomics/msdial-preprocessing; for non-lipid annotation confidence see metabolomics/metabolite-annotation; for normalization/QC see metabolomics/normalization-qc; for multivariate stats see metabolomics/statistical-analysis.
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。
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.
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。
Extract employee, trip, mileage, per diem, expense lines, VAT, and totals from German travel expense claims.
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。
Extract employee, trip, expense lines, VAT, totals, and approvals from French expense claims.
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。
Self-review, audit, or verify CS/AI/ML paper drafts as a critical peer reviewer. Three-round review (evidence→argument→style) with Verification Status and debt tracking. Use when: reviewing a paper draft before submission, checking evidence compliance of claims, simulating peer reviewer feedback, verifying citation closure and evidence debts, performing cross-section consistency checks. Triggers on: 审修, self review, 自查, verification, revise, 修订, check draft, 审稿, evidence compliance, peer review, 论文审查, draft audit, 验证论文, 检查引用, cross-section review.
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。
Configures JWT Bearer authentication for .NET APIs. Includes token generation, validation, refresh tokens, and user context extraction from claims.
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。
Prepare for a Japanese job interview by working from the documents already submitted: find where an interviewer will dig in (claims the applicant cannot back up, work described in the first person plural, outcomes with no measure, gaps or overlaps in the employment history, must-have requirements the documents never answer), and turn them into questions to prepare evidence for. Use when a user has an interview scheduled and wants to know what will be asked and what to have ready, or wants to prepare reverse questions from earlier company research; do not use to predict whether they will pass, to write answers containing experience they did not report, or to schedule or contact anyone.
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。
Inventory a person's work history as facts before any document is written, listing each period of employment and what they actually did, splitting every experience into situation, their own actions, outcome, and stated role, and recording what each claim rests on (public record, their own records, someone who was there, or memory alone). Use when a user is starting a job search, needs material for a rirekisho, shokumu-keirekisho, or entry sheet, or wants to find which periods of their history they have never written down; do not use to judge their strengths, aptitude, or market value, to name a job they are suited for, or to write finished application copy.
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。
Research a specific company before applying or interviewing by gathering facts from primary and official sources, recording the source and date behind every claim, and keeping anonymous or unverifiable material clearly separated from confirmed fact. Use when a user asks what a company actually does, how it makes money, what its published conditions are, whether a posting matches the company's own disclosures, or what to verify before an interview; do not use to predict hiring outcomes, to repeat review-site content as fact, or to bulk-crawl sites that prohibit automated access.
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 OpenAI Codex CLI as a peer collaboration partner — same standing as Claude, not a one-shot tool. Bring Codex in EARLY (ideation, framing decisions, stuck moments), not only for late peer-review. Hand it strategic context (target, research, draft, reasoning), iterate conversationally over ~3-8 turns, converge before surfacing to the human. Invoke when the user says "check / iterate / ideate with Codex" or "ask Codex" — and proactively when stuck between two reasonable framings, pressure-testing a load-bearing claim or structure, or about to ask the human to pick between options two agents could resolve.
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。
Delimits putative species boundaries from molecular data within the de Queiroz 2007 unified-lineage framework using ASAP (Puillandre 2021 successor to ABGD), mPTP C++ (Kapli 2017 successor to bPTP; bPTP is Python NOT R), GMYC single/multi-threshold (Pons 2006; Fujisawa 2013), multilocus BPP v4 with prior calibration from data (NOT defaults; Yang 2015), SNAPP + BFD* for SNP delimitation, DELINEATE (Sukumaran 2021) speciation-process modeling to address Sukumaran & Knowles 2017 PNAS critique that MSC delimits structure not species, integrative-taxonomy congruence (Padial 2010; Carstens 2013), Dsuite for introgression testing before sister claims (Malinsky 2021), and Meyer & Paulay 2005 barcoding-gap-absence caveat. Use when delineating species from DNA barcoding data, resolving cryptic complexes, choosing among ASAP/mPTP/BPP/DELINEATE, calibrating BPP priors, distinguishing introgression from ILS, or applying the Sukumaran-Knowles oversplitting correction.
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。
Performs subgroup and heterogeneous treatment effect (HTE) analyses for clinical trials. Covers Mantel-Haenszel pooling, Breslow-Day, interaction tests in regression, RERI for additive interaction, modern data-adaptive HTE methods (STEPP, SIDES, causal forests, X/R-learners), Bayesian shrinkage (Dixon-Simon, MAP, EXNEX), graphical multiplicity (Bretz-Maurer), and credibility frameworks (Sun BMJ, EMA 2019). Use when analyzing treatment effects across patient subgroups for regulatory submissions or precision-medicine claims.
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。
Detect and adjust for horizontal pleiotropy in two-sample Mendelian randomization by distinguishing uncorrelated (UHP) from correlated (CHP) pleiotropy and choosing among Egger, MR-PRESSO, MR-RAPS, CAUSE, LHC-MR, LCV, MR-Clust, MR-Mix, and contamination-mixture methods. Use when validating an MR causal claim, running the STROBE-MR sensitivity battery, suspecting a shared heritable confounder, working under weak-instrument or polygenic-exposure regimes, or reconciling discordant estimates across robust methods.
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 configuring Spring Boot as an OAuth2 resource server, validating JWTs from an external auth provider (Keycloak, Auth0, Okta, Cognito), extracting claims, or implementing scope-based authorization.
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。
Extract a thesis's load-bearing assumptions and scan for internal contradictions — the falsifiable claims the bull case requires, what would falsify each, and where the thesis's own Risks / Bear Case / research already argue against it. Use when user says "assumptions", "what must be true", "load-bearing assumptions", or "does [TICKER] contradict itself".
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。
Execute an explicitly authorized exploratory charter and record notes, findings, evidence, and follow-up without claiming false coverage.
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 about to claim work is complete, fixed, or passing, and when a finished feature needs adversarial verification before integration
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。
Pick a product archetype from a curated catalog before any UI gets built — the single biggest lever for not looking vibecoded. Routes the request to one of B2B-productivity, enterprise-trust, premium-consumer, playful-consumer, editorial, brutalist-distinctive, dev-tool, or marketing-landing, and returns a complete design philosophy: typography pair, color logic, motion curve, density, icon stance, reference sites, and a "feels like X" claim. Load when the user asks to pick an aesthetic, choose a design direction, decide what a UI should feel like, classify a product visually, says "what should this look like", "make this feel like [Linear/Stripe/Apple/Duolingo/...]", "give me a design direction", "what's the right aesthetic for this", or when frontend-design routes here during archetype selection. Sub-skill of frontend-design.
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。
Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causally, make a ship/iterate/kill decision against the pre-declared rule, and append to cumulative learnings. Forces honest readouts — strips significance claims from underpowered or peek-violating tests; never lets directional results masquerade as causal wins. Load when results exist, or when the user says "read out this experiment", "analyse the test", "did the test win", "interpret the results", "what did we learn", "ship or kill", or when the experimentation orchestrator routes here.
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。
Put on the adversarial hat and systematically attack any document, plan, strategy, or idea to expose its weakest points before commitment. Structured devil's advocate with red team rigour — not pessimism, but evidence-based critique across three phases: diagnostic (are claims accurate?), creative (is the problem artificially constrained?), challenge (are solutions robust?). Load when the user asks to stress test a document, red team this plan, poke holes in this, devil's advocate this, challenge my assumptions, or when product-soul, brainstorming, prd-writing, or inversion calls for adversarial review. Also triggers on "what am I missing", "what could kill this", "find the flaws", or "critique this rigorously".
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。
Monitor a pull request through review and CI until it's green: verify every bot claim against the code, fix what's real, push back on what's wrong, rerun flaky checks. Use when the user asks to babysit, monitor, watch, or shepherd a PR, says "get this PR green" or "handle the review comments". Accepts an optional PR number/URL; defaults to the current branch's open PR.
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。
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
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。
Delimits putative species boundaries from molecular data within the de Queiroz 2007 unified-lineage framework using ASAP (Puillandre 2021 successor to ABGD), mPTP C++ (Kapli 2017 successor to bPTP; bPTP is Python NOT R), GMYC single/multi-threshold (Pons 2006; Fujisawa 2013), multilocus BPP v4 with prior calibration from data (NOT defaults; Yang 2015), SNAPP + BFD* for SNP delimitation, DELINEATE (Sukumaran 2021) speciation-process modeling to address Sukumaran & Knowles 2017 PNAS critique that MSC delimits structure not species, integrative-taxonomy congruence (Padial 2010; Carstens 2013), Dsuite for introgression testing before sister claims (Malinsky 2021), and Meyer & Paulay 2005 barcoding-gap-absence caveat. Use when delineating species from DNA barcoding data, resolving cryptic complexes, choosing among ASAP/mPTP/BPP/DELINEATE, calibrating BPP priors, distinguishing introgression from ILS, or applying the Sukumaran-Knowles oversplitting correction.
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。