「uat」の検索結果

Determine technologies needed to build the product, making build/buy/integrate decisions during PRD v0.5 Red Team Review. Handles both greenfield and brownfield contexts. Triggers on requests to select tech stack, evaluate technologies, make build vs. buy decisions, discover existing assets, or when user asks "what technologies?", "select tech stack", "build or buy?", "what do we reuse?", "existing stack", "technical decisions", "what tools do we need?", "evaluate solutions". Consumes FEA- (features), SCR- (screens), RISK- (constraints). Outputs TECH- entries with decisions, rationale, and trade-offs. Feeds v0.6 Architecture 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。

Arize is an AI observability platform, and Phoenix is its open-source tracing and evaluation tool for LLM applications. Use this skill when the user wants to trace OpenAI or LangChain calls, run a local Phoenix server, score RAG answers for faithfulness, debug slow or wrong LLM responses, or send OpenTelemetry traces to Arize for production monitoring.

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。

Run AI agent and LLM evaluations in CI/CD pipelines — automated quality gates that fail the build when AI output quality drops. Use when someone asks to "test my AI agent", "add evals to CI", "catch prompt regressions", "compare models", "evaluate LLM output quality", "set up AI quality gates", or "benchmark my agent before deploying". Covers eval frameworks (Cobalt, Promptfoo, Braintrust), LLM-as-judge scoring, threshold-based assertions, and GitHub Actions 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。

Raising money is a means to an end, not the end itself. Great companies can be built with or without venture capital. But if you're raising, you need to understand the game: when to raise, how much, from whom, and at what terms. This skill covers fundraising timing, process, pitch construction, term sheet negotiation, and investor relationship management. It's not about raising as much as possible - it's about raising strategically. Use when "fundraising, raising money, pitch deck, investors, term sheet, valuation, dilution, series A, seed round, pre-seed, runway, cap table, VC, venture capital, fundraising, investors, venture-capital, pitch-deck, term-sheet, valuation, dilution, seed, series-a, cap-table" mentioned.

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。

Technical decision-making frameworks - trade-off evaluation, reversibility analysis, and second-order thinking for better engineering choicesUse when "should we, which is better, trade-off, decision, choose between, versus, pros and cons, what if we, is it worth, evaluate options, decisions, trade-offs, architecture, adr, reversibility, strategy, planning, risk" mentioned.

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。

Implement comprehensive observability for LLM applications including tracing (Langfuse/Helicone), cost tracking, token optimization, RAG evaluation metrics (RAGAS), hallucination detection, and production monitoring. Essential for debugging, optimizing costs, and ensuring AI output quality. Use when ", llm-monitoring, tracing, langfuse, helicone, cost-tracking, ragas, evaluation, hallucination-detection, prompt-caching" mentioned.

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。

Architecture Decision Framework workflow skill. Use this skill when the user needs Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Influencer Discovery workflow skill. Use this skill when the user needs Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Influencer Discovery workflow skill. Use this skill when the user needs Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

AI Engineering Toolkit workflow skill. Use this skill when the user needs 6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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 third-party vendors for engineering fit. Use when a senior developer needs a structured vendor assessment.

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。

Break out of a locked problem frame by picking one disciplined move — reframe, provocation (Po), random stimulus, SCAMPER, inversion, structured analogy, constraint play, or family traversal — and committing to it before evaluating. Use when stuck, when options feel narrow or obvious, when iterations produce variations of the same idea, or when the user says "widen this", "break out of", "think differently", "I'm stuck", "feels too obvious", "stress-test the framing", "what am I missing", or holds two related examples and asks what lies between or beyond them. Complements challenging (which evaluates) and convening-experts (which synthesizes viewpoints); this skill generates distance, not judgment.

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。

This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design". Use for architecture decision records (ADRs), tech stack evaluation, system design reviews, dependency analysis, and generating architecture diagrams in Mermaid, PlantUML, or ASCII format.

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。

Conduct expert heuristic evaluations using Nielsen's heuristics and domain-specific criteria.

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。

Audits any developer documentation site across 33 checks in 7 categories and produces a scored report (out of 100) with Pass / Warn / Fail status per check. Use this skill whenever a user provides a docs URL and asks to audit it, review it, score it, check its quality, or evaluate it for AI discoverability, SEO, structure, content, or completeness. Also trigger when the user says "run a docs audit", "audit these docs", "check this documentation", "how good are the docs for X", or pastes a docs URL with any evaluative intent. Always use this skill — do not attempt a freeform docs review without following this structured workflow.

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。

Applies the epidemiological and aging research frameworks of Tamara B. Harris (epidemiologist, National Institutes of Health). Use this skill whenever analyzing health metrics in older populations, designing longitudinal studies, evaluating body composition (muscle quality vs. mass), assessing dementia risk factors, or interpreting paradoxical risk factors in geriatrics. Trigger this skill when the user asks about aging, longevity, functional decline, socioeconomic health disparities, or when evaluating clinical trial data where reverse causation or subgroup stratification might skew 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。

This skill channels the reasoning of Walter C. Willett, nutrition epidemiologist at Harvard University. Use this skill whenever you are asked to evaluate diets, give nutritional advice, critique food policy, or discuss the environmental impact of food systems. Trigger this skill for topics like macronutrient quality (fats vs. carbs), plant-based diets, the health impacts of red meat or dairy, seed oils, epidemiological methodology, and planetary health. Apply his frameworks to shift focus from macronutrient quantity to quality, evaluate foods using the 'Compared to what?' rule, and prioritize public health over personalized nutrition fads.

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。

Applies the reasoning of Mary Wollstonecraft (18th-century English philosopher and author of A Vindication of the Rights of Woman) to evaluate situations involving power dynamics, education, independence, gender roles, and systemic inequality. Use this skill whenever Claude encounters career trade-offs involving financial dependence, analyzing structural oppression, questioning societal norms, or balancing reason against emotion. It helps dismantle arbitrary hierarchies, prioritize rational capability over superficial elegance, and frame personal struggles as political realities.

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。

This skill applies the first-principles engineering and capital allocation frameworks of Elon Musk (CEO of Tesla and SpaceX, founder of X.com / PayPal). Reach for this skill whenever the user is facing complex manufacturing bottlenecks, evaluating existential risks, debating free speech vs. censorship, dealing with bureaucratic overregulation, or trying to accelerate ambitious technical timelines. It is highly effective for situations involving hardware production, AI symbiosis, radical innovation, and aggressive execution. Use this skill proactively when discussing multi-planetary expansion, government efficiency, or scaling prototypes to mass production, even if the user doesn't explicitly name him.

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。

Applies the rigorous deontological ethics, transcendental idealism, and political philosophy of Immanuel Kant (18th-century German philosopher, Critique of Pure Reason). Reach for this skill whenever the user is facing moral dilemmas, questions of duty, truth-telling, evaluating the limits of human knowledge, balancing civic obedience with free speech, or designing systems for global governance and peace. Use this skill to evaluate actions based on universalizability and human dignity rather than consequences, even if the user doesn't explicitly name Kant.

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。

Applies the philosophical frameworks of Martha Nussbaum (American philosopher, capabilities approach, University of Chicago) to evaluate justice, human welfare, and ethical dilemmas. Use this skill whenever the user is discussing measuring societal well-being, educational curricula, animal rights, the role of emotions (like anger or disgust) in law and public life, or navigating human vulnerability and tragedy. Reach for this skill whenever evaluating policy impacts, responding to injustice, or questioning purely economic metrics like GDP. It shifts the focus to what people are actually able to do and be.

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 agent and skill behavior or routing.

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。

Manages Neo4j Aura Agents via the v2beta1 REST API — create, list, get, update, delete, and invoke Aura agents backed by an AuraDB instance. Use when configuring Aura Agent tools (CypherTemplate, SimilaritySearch, Text2Cypher), setting system prompts, deploying agents to REST or MCP endpoints, invoking agents with natural language queries, or generating evaluation datasets (max 50 questions) for the Aura Agent evaluation feature. Covers OAuth2 auth, organization/project scoping, tool parameter schemas, and InvokeAgentResponse format. Does NOT cover AuraDB instance provisioning — use neo4j-aura-provisioning-skill. Does NOT cover vector index creation — use neo4j-vector-index-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。