「uat」の検索結果

Produces structured asset and liability summaries from financial documents for legal proceedings. Extracts valuations, ownership classifications, and encumbrances, then outputs net-worth overview, categorized schedules, disputed items, and documentation gaps. Use when preparing financial summaries for divorce/dissolution, estate planning, bankruptcy, business valuation, or settlement negotiations. Trigger on: net worth summary, marital estate, balance sheet, asset schedule, liability schedule, community/separate property.

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。

Holistic evaluation framework for language models measuring accuracy, calibration, robustness, and fairness

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 introducing a feature flag system, choosing between release flags / experiment flags / operational flags / kill switches / permission flags, designing percentage rollouts, building kill-switch + circuit-breaker patterns, structuring evaluation contexts (user IDs, plan tier, region), or building flag-cleanup discipline. Triggers: LaunchDarkly / GrowthBook / Unleash / Flagsmith / OpenFeature, percentage ramp, sticky bucketing, kill switch wired to alerting, "we still have flags from 2 years ago", flag debt, OpenFeature provider, evaluation context, default value on provider failure. NOT for A/B test statistical analysis (separate skill), traffic-split routing at the edge, build-time bundler defines, or environment-based config.

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。

Apply recognition-primed decision making to agents operating under time pressure, uncertainty, and ambiguous cues. Use for situation assessment, RPD-style action selection, and decision-support design in operational settings. NOT for batch optimization, static planning with full information, or tasks where exhaustive search is cheap and harmless.

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 and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

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。

Loads, lists, composes, or validates graded evaluation rubrics: PASS/WARN/FAIL grading with weighted criteria and balanced anchor examples for evaluator-style 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。

Use when negotiating a file-based sprint contract between the generator (developer) and evaluator before code is written. Translates a product-level spec into testable acceptance criteria with rubric tie-ins. Triggers on /mk:sprint-contract, "draft a sprint contract", "negotiate scope for sprint", or before any harness-driven sprint kicks 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。

Persists and restores mid-session workflow progress across context resets. Use when resuming workflows, saving state, or handling context compaction. Triggers on: handoff, save state, resume 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。

Use when running an autonomous multi-hour build of a green-field product — orchestrates planner → contract → generator ⇄ evaluator loop with adaptive scaffolding density per model tier. Triggers on /mk:autobuild, "build me a kanban app", "build a retro game maker", "autonomous build", or any green-field product spec. NOT for scoped single-task work (see mk:cook); NOT for initial project scaffolding only (see mk:bootstrap).

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。

Quantitative agent evaluation using 4-metric framework (correctness/step_ratio/tool_call_ratio/latency_ratio) with ideal trajectory annotation and capability-categorical taxonomy. Use when measuring agent efficiency, comparing agent variants, or gating new agents through correctness→efficiency phases. Complements harness-eval (SE benchmarks) and evaluator-optimizer (qualitative rubric).

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。

Parameterized evaluator-optimizer loop for quality-critical output with configurable rubrics

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。

Judge subskill for simmer. Scores a candidate artifact against user-defined criteria on a 1-10 scale and produces ASI (highest-leverage direction) for the next generator round. Supports judge-only, runnable evaluator, and hybrid evaluation modes. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.

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。

Quality control for pooled CRISPR screens covering library representation, Gini index, log-skew, replicate Pearson and Spearman concordance, essentialome precision-recall AUC against CEGv2 (Hart 2017), Cas9 cut-toxicity diagnostics, copy-number amplicon detection (Aguirre 2016 / Munoz 2016), bottleneck propagation through plasmid pool, infection, selection, and endpoint stages, MOI verification, and DepMap-style screen-quality scoring. Use when assessing screen quality before hit calling, deciding whether to repeat or rescue a screen, diagnosing low-confidence hits, choosing between MAGeCK / BAGEL2 / Chronos based on quality grade, picking a normalization strategy from QC signatures, or evaluating whether an in-vivo screen retained adequate library complexity.

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。

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

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。

Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.

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。

Considers adapting the basal insulin rate at hospital admission for patients using insulin pump therapy. Triggered by clinician questions such as "Should we adjust the basal rate upon admission for pump therapy?" or when evaluating pump continuation versus transition to scheduled subcutaneous insulin.

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。

Recommends continuing insulin pump therapy in hospitals with pump expertise; otherwise transitioning to scheduled subcutaneous basal bolus insulin if anticipated length of stay exceeds 1–2 days before pump discontinuation. Consider this when anticipating a hospital stay >2 days, lacking pump expertise, or needing to conserve supplies.

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 guides evaluation of venous thromboembolism (VTE) risk factors in Cushing's syndrome patients to prevent thrombotic complications. Use when assessing a CS patient for thrombotic risk, especially perioperatively; triggers include preoperative assessment, postoperative period (within 4-6 weeks), or presence of CS with additional risk factors such as prior VTE, immobilization, malignancy, or estrogen use.

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。

Recommends discontinuation of GLP-1RA before conception rather than between start of pregnancy and end of first trimester for individuals with type 2 diabetes who are planning pregnancy. Trigger when clinician considers stopping GLP-1RA therapy in a patient with type 2 diabetes who is planning pregnancy or seeking preconception care.

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。

Assesses a patient’s ability to operate an insulin pump and make setting changes, evaluating dexterity, vision, mental health, and cognition for independent or assisted use. Triggered by phrases such as 'Check patient can manipulate pump controls' and 'Evaluate dexterity and vision for pump use'.

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。

Recommends continuing a patient’s personal continuous glucose monitor (CGM) in the hospital with or without algorithm-driven insulin pump (ADIP) therapy rather than discontinuing it for individuals already using CGM outpatient. Use when deciding whether to maintain personal CGM during admission or when a patient requests to keep their device, particularly in those at high risk for hypoglycemia.

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 a structured pre‑prescription evaluation of mental/psychological status, prior diabetes self‑care adherence, willingness/interest in CSII, and availability for follow‑up visits. Triggers include: 'Evaluating pump candidacy', 'Pre‑pump checklist: psych, adherence, motivation, follow-up'.

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 recommends follow-up morning cortisol and/or ACTH stimulation tests or insulin-induced hypoglycemia to assess HPA axis recovery in postoperative Cushing's syndrome patients with at least one intact adrenal gland. Triggers include postoperative remission (morning cortisol <5 µg/dL or UFC <28–56 nmol/d) and the need to evaluate HPA recovery before glucocorticoid discontinuation.

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 recommends regularly evaluating for corticotroph tumor progression using pituitary MRIs and ACTH levels in patients with known Cushing's disease who underwent bilateral adrenalectomy and in patients undergoing this procedure for presumed occult ectopic ACTH secretion. Triggers include postoperative follow‑up after bilateral adrenalectomy, rising ACTH levels, or new pituitary lesion on MRI suggestive of tumor progression.

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。