「judge」の検索結果

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

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 the user hands over a dsh plugin repository (or a real migration commit / version corridor) and wants its upgrade experience extracted into one auto-graded Harbor benchmark exam task — produce tasks/<id>/ (fixture + instruction.md + task.toml + judge.mjs + solution) that harbor run can grade 0–1 and that folds into the dsh-plugin-upgrade-skill benchmark suite; also applies to turning existing version cards (references/v*.md) into executable exam tasks. Not for writing upgrade cards; not for running the benchmark.

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。

Owns architecture, engineering delivery, infrastructure, data platform, and internal systems. Use this for build-versus-buy calls, technology selection, architectural direction, engineering capacity and delivery risk, technical debt tradeoffs, platform and tooling decisions, or when a technical choice has business consequences that need stating in business terms. Also use to judge whether a technical plan is sound before it is committed to.

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。

Judges whether material for children under six is developmentally plausible — what is typical at each age, why pre-K is not a thinner kindergarten, and which frameworks apply where Common Core does not. Use this to design or review pre-K material, decide whether a task is reasonable for an age, choose the right framework for a pre-K alignment claim, or push back on material that pushes school-age expectations downward.

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。

Builds and interrogates a project schedule — logic-driven sequencing, dependency types and lags, float and the critical path, resource loading and leveling, schedule risk analysis, and measuring progress against a baseline rather than against optimism. Use this to construct a schedule, audit one you have inherited, find out why a plan keeps slipping, work out what a date change actually costs, or judge whether a reported percentage complete means anything.

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。

The EPMO lead's remit — what the PMO governs, what it must never become, and how it earns standing rather than compliance. Use this to stand up or reform a PMO, decide what it should and should not control, judge whether it is adding value or overhead, or work out why teams route around it.

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。

Owns what gets built and why: product strategy, roadmap, discovery, user experience, and the definition of success for each release. Use this to decide what to build next, to cut scope, to turn a business goal into a product bet, to judge whether a feature is worth its cost, or when engineering and go-to-market disagree about what a release is for. Also use for roadmap sequencing and for killing work that is not earning its place.

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。

Designs and improves referral, affiliate, and word-of-mouth programs — incentive structure, mechanics, timing, and fraud control. Use this to build a referral or affiliate program, diagnose one that is not producing, decide what incentive to offer, or judge whether referral is a realistic channel for a product.

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。

Owns legal, contracts, intellectual property, regulatory compliance, privacy, security governance, enterprise risk, and audit readiness. Use this to review a contract or commitment, assess regulatory or privacy exposure, evaluate an IP or licensing question, judge the risk in a business decision, prepare for an audit or certification, or when a plan may create obligations the business cannot meet. Also use to decide whether a risk should be accepted, mitigated, or refused.

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。

Writes, structures, and evaluates social posts end to end — hooks, body, formatting for how each platform renders, and a quality check before publishing. Use this to draft a post, rewrite one that underperformed, turn a longer piece into social content, sharpen an opening, or judge whether a draft is worth publishing.

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。

Establishes whether the business makes money on each customer or unit — contribution margin, acquisition cost, payback period, lifetime value, and the cohort behavior underneath. Use this to assess whether growth is profitable, evaluate a channel or segment, support a pricing decision, judge how fast the business can afford to grow, or diagnose why revenue growth is not producing profit.

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。

Owns brand, demand generation, content, communications, and how the market understands what the business does. Use this to set marketing strategy, allocate budget across channels, decide positioning and messaging, judge whether a campaign is worth running, diagnose why demand has stalled, or arbitrate between brand-building and short-term acquisition. Also use to decide which marketing work to stop.

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。

The CIO's remit — running the technology the company works on, service quality, IT spend, and the boundary with product engineering. Use this to set IT priorities, decide what IT owns versus engineering, structure IT spend or an IT roadmap, judge whether to build, buy or outsource, or work out why IT is seen as a cost center rather than an enabler.

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。

Establishes what something actually costs — fixed, variable and mixed cost behavior, absorption versus variable costing, job-order, process and activity-based methods, breakeven and operating leverage, and price/volume/mix decomposition. Use this to set a price floor, explain why revenue or margin moved, decide make versus buy, judge whether a product line earns its place, or work out how an allocation basis is distorting a reported margin.

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。

Plans, runs, and optimizes paid acquisition across search, social, and display — account structure, targeting, creative, bidding, budget, and the analysis that says whether to scale or stop. Use this to set up or restructure campaigns, write and iterate ad creative, diagnose rising costs or falling performance, decide budget allocation, or judge whether a channel is working.

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。

Builds large sets of search-targeted pages from a template and a dataset — the location, comparison, integration, and use-case pages that capture long-tail demand at scale. Use this when there is a repeating query pattern with real volume, when a dataset could answer many similar searches, or to judge whether a programmatic approach is viable before building it.

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。

Designs, runs, and reads A/B tests and growth experiments — hypothesis, sample size, duration, and honest interpretation. Use this to plan a test, judge whether a result is real, build an experimentation program, decide what to test next, or diagnose why tests keep producing inconclusive or non-replicating 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。

Quickly judges whether a biomedical paper is worth deep reading by screening for question fit, design quality, sample adequacy, methodological novelty, and reproducibility value.

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 tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent 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。

Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.

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 one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.

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 a task step by step with automated LLM-as-Judge verification at the end of each phase

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。

Comprehensive multi-perspective review using specialized judges with debate and consensus building

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。

Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness must be bulletproof and single-pass or round-by-round review is too slow and too shallow. Invoke for "audit this rigorously", "find ALL the bugs/gaps", "make this rock solid", "converge faster on correctness".

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。