Results for “heuristic-estimation”

Conduct expert heuristic evaluations of digital interfaces using Nielsen's 10 usability heuristics and domain-specific criteria.

Evaluate and improve interface usability using heuristic analysis based on Nielsen's 10 heuristics, Krug's laws, and severity ratings.

贺涵（都市剧虚构）认知与表达框架（压缩蒸馏）：导师型男主、职场金句、情感争议 触发：我的前半生 等。虚构；忌情感操控教程

A* pathfinding skill for heuristics and optimization.

Evaluates the correlation between automatic text generation scores and human quality ratings, including robustness to domain and quality drift, using metrics like Kendall's Tau and Pearson correlation.

Guides statistical hypothesis testing with assumption checks, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting for research data.

Run a heuristic evaluation of interactive UIs against Nielsen's 10 usability heuristics and interaction add-ons, scoring the rendered artifact and producing a prioritized fix list.

贺炜（体育解说）认知与表达框架（压缩蒸馏）：文学比喻嵌入赛况、克制激情、终场金句… 触发：足球诗人解说 等。非煽动球迷对立

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

Evaluates the robustness and alignment with human judgment of reference-based and reference-free evaluation metrics for machine translation and summarization, particularly under adversarial conditions.

Honestly evaluate AI work quality using a two-axis scoring system with mandatory devil's advocate reasoning and cross-session anti-inflation detection.

Design, prioritize, and evaluate product experiments with clear hypotheses and defensible decisions, including A/B testing, sample size estimation, and statistical interpretation.

Every metric encodes an opinion about which mistake hurts.

heath-no-fluff

Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benign over-refusal or measure refusal/KL trade-offs, not for training.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Multi-phase dialectical stress-test for HIGH-STAKES decisions only (architecture choices, irreversible product calls, strategic bets). Heavy-cost skill — do NOT use for routine questions, brainstorming, or simple tradeoffs. User must explicitly invoke or describe a decision they call "high-stakes", "irreversible", or "needs stress-testing". Triggers: "stress test this decision", "dialectic on", "challenge this thesis", "should I really".

Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "UX review", "users are confused", "heuristic evaluation", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "usability testing". Also trigger when reviewing a design for usability issues, improving form completion rates, or evaluating information architecture and navigation. Covers Nielsens 10 heuristics, severity ratings, and information architecture. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.

Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery planning.

Computes the HARE Score, an entity- and relation-centric metric for evaluating machine-generated histopathology reports against ground truth, using GatorTronS+SapBERT embeddings and relation F1.

Design and implement evaluation harnesses for models, agents, and code. Use when creating benchmarks, designing eval metrics, or comparing system outputs.

Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking

Evaluates an AI judge system's pairwise ranking accuracy on generated commit messages against a heuristic ground truth from five automatic text metrics, using the MCMD dataset.

Analyzes evaluation results by requiring a stated hypothesis before examining data, then compares expectations to actual result files to prevent post-hoc rationalization.

Use when you need to characterize score distributions of a profile HMM on random sequences, such as calibration checks, benchmarking, or filter-behavior experiments.

Ranks any list of impediments and their countermeasures using a value-stream scoring model (ROI, Cost to Implement, Ease of Deployment, Risk Factor) and a fixed prioritization formula.

韩寒（作家车手）认知与表达框架（压缩蒸馏）：反套路叙事、冷幽默、公共发言锋利… 触发：三重门赛车 等。不伪造赛事实；尊重他人

日本語の生産性コーチングモード。明示的な依頼、反復失敗、受け身、検証不足、品質不満のときに、構造化トラブルシューティングと証拠ベースの完了確認を促す。

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

選択肢(A/B/C)の深掘り比較→淘汰→推奨で判断負担を下げ判断の質を上げるスキル。5段階（L1固定3点/L1.5案拡張Diverge・自動/L2評価軸マトリクス/L3複数LLM弁証論/L4過去判断照合）。 「比較して」「深掘りして」「メリデメ教えて」「お勧めは？」「徹底的に」「過去の判断と照合」「前にどう決めたっけ」「/sentaku」等で発火。teian(浅)の深掘り要求を受け取り、brainstorming(深:設計全体)と棲み分け。

Design and evaluate paid-ad experiments with hypotheses, randomization, sample-size calculations, guardrails, and decision rules for A/B and split tests.

Quantifies how sensitive a language model benchmark's reliability and ranking stability are to specific design choices, such as the selection of scenarios, subscenarios, examples, and few-shot prompts. Use when the user has predictions and gold and needs to compute DIoR.

当寻求个人行动或项目在更宏大系统中的意义，或需要将日常工作与长远价值连接时

葛优（演员）认知与表达框架（压缩蒸馏）：蔫坏冷面、话少留白、小人物体面与大谎 触发：甲方乙方、活着 等。虚构创作谈

Use when positioning a manuscript against the existing economics literature, building the antecedents map for the introduction, deciding what to cite, or verifying that every reference in the bibliography is real, correctly attributed, and cited to the published version. Apply at topic selection for the novelty scan and again before drafting the introduction.