873 件 ・ 関連度順
概要と使いどころ
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
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 a polite-but-firm payment-reminder / collections email sequence for overdue invoices. Use when asked to write a collections email, a payment reminder, a dunning sequence, or to chase an overdue invoice. Produces a staged sequence — gentle pre-due nudge through escalating overdue reminders to a final notice — that stays professional, keeps the relationship intact, and makes paying easy. 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。
Model, simulate, and optimize Serializer/Deserializer (SerDes) systems — serial and parallel links — using MATLAB SerDes Toolbox. Design NRZ and PAM-N links (PAM3 through PAM16) — explore equalization architectures (FFE, CTLE, DFE), sweep or optimize parameters with genetic algorithms, and characterize channels from loss models, S-parameter files, or crosstalk scenarios. Process captured waveforms through equalization chains, build eye diagrams, and decompose jitter. Deliver IBIS-AMI models for Tx, Rx, Redriver, or Retimer by exporting to Simulink and compiling .ami/.ibs/.dll/.so files. Covers the full arc from initial design exploration and parameter optimization to compliance testing and compiled model validation, including custom datapath blocks for nonstandard equalization.
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 a generated Scenario image needs a quality check or a brand-brief compliance verdict before it ships: pass/warn/fail scoring, on-brand review against a configured brief, QA gating a batch, pricing or refreshing a stored verdict, or iterating a generation until it clears the gate. Keywords: quality gate, quality check, QA, verdict, brief compliance, on-brand, brand brief, pass fail, score, review, asset_quality_gate_run.
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。
Approval cascade definition and tracking for multi-stakeholder document workflows. Internal review sequences, client approval workflows, regulatory review, overdue chasing with escalation logic, version control coordination, and cross-jurisdiction document dependencies. Use when defining who reviews a document and in what order, tracking where a document is stuck in the approval chain, chasing an overdue reviewer, preventing reviewers working on superseded drafts, or mapping dependencies between documents across jurisdictions. Trigger on: 'who needs to approve this', 'document approval', 'review sequence', 'stuck in review', 'overdue approval', 'who has the document', 'version control', 'wrong version', 'document dependency', 'NL SPA waiting on German opinion', 'approval cascade', 'review chain', 'document circulation', 'chasing the partner', 'client approval process', 'where is the document'.
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。
Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe paper".
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。
Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".
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 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".
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。
Kontextspezifische Marketinghypothesen entwickeln, vorprüfen und als messbare Experimente priorisieren. Nutze diesen Skill, wenn Ideen für Kanäle, Kampagnen, Angebote oder Wachstum gesucht werden, wenn eine Ideenliste auf Risiko und Machbarkeit geprüft werden soll, oder wenn aus Vorschlägen Experimentsteckbriefe mit Metrik, Laufzeit, Budget und Stopkriterium werden sollen. Sortiert vor der Bewertung aus, was rechtlich, plattformseitig oder finanziell nicht tragbar ist, und trennt Evidenz von Vermutung. Führt keine Kampagne aus und schaltet keine Anzeigen.
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。
E-Mail-Entwürfe auf die Merkmale prüfen, mit denen Spamfilter Werbepost erkennen, und empfangene Nachrichten auswerten, die im Junk gelandet sind. Nutze diesen Skill, wenn eine Mail vor dem Versand geprüft werden soll, wenn jemand wissen will, warum eine Nachricht im Spam- oder Junk-Ordner gelandet ist, oder wenn Betreff, Text, HTML und Kopfzeilen einer Mail auf Aufbau- und Inhaltsfehler durchgesehen werden. Prüft unter anderem Linktext gegen Linkziel, defekte Abmeldewege nach RFC 8058, erfundene Thread-Bezüge, sichtbare Seriendruckreste, versteckte Zählpixel, Domainstreuung sowie unbelegte Zahlen und Superlative. Sagt keine Zustellung voraus und ist kein Werkzeug, um Filter zu umgehen. Für die Frage, ob eine Kaltakquise-Mail überhaupt versendet werden darf, ist cold-email zuständig.
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。
Evaluate or operate DuckLake on MotherDuck when open table formats, bucket ownership, or file maintenance matter.
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。
Roll out governed MotherDuck analytics to internal teams, choosing trusted datasets, access boundaries, and owners.
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。
Design or implement MotherDuck analytical schemas and transformation models, including grain, types, and materialization.
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 the MotherDuck CLI for terminal queries, authentication, and file-based Dive or Flight workflows.
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。
Look up or repair DuckDB SQL syntax and verify MotherDuck-specific command and feature support.
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。
Read or maintain MotherDuck Guides for business definitions, join rules, and reusable warehouse conventions.
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。
Design or improve a MotherDuck Dive’s layout, responsive behavior, themes, filters, and visual accessibility.
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。
Create, edit, publish, share, or embed MotherDuck Dives using their React and SQL runtime.
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。
Set up or troubleshoot MotherDuck connections, authentication, client runtimes, and read scaling.
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。
Administer MotherDuck service accounts, tokens, Ducklings, and Dive embed sessions through the control-plane REST API.
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, execute, or optimize analytical DuckDB SQL against MotherDuck data.
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。
Create, consume, or manage MotherDuck data shares, including audience grants, table filters, and refresh policy.
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。
Build a MotherDuck dashboard as a Dive, choosing the analytical story, metrics, and section queries.
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。
Assess MotherDuck security, permissions, isolation, residency, and compliance requirements against documented controls.
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。