「measure」の検索結果

Evaluate Mycelium's own process effectiveness. Measures cycle velocity, discard trends, confidence calibration, gate effectiveness, regression rate. Run quarterly or every 20 cycles.

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 writing, reviewing, or optimizing CUDA kernels targeting sm_120a (RTX 5090 / Consumer Blackwell, GB202) in the imp inference engine. Triggers on CUDA/PTX kernel code, shared-memory layout, bank conflicts, tensor-core MMA (mxf4nvf4, tf32, 3xTF32/3xFP16), GEMV/GEMM/attention/quantization/GDN-scan kernels, decode tok/s under expected, kernel emitting HMMA instead of mxf4nvf4, occupancy, register pressure, __launch_bounds__, spills, PDL. Pair with `benchmark-cuda` for measurement and `check-degeneration` after hot-path changes.

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 opening, merging, or releasing a PR for imp - branching off main, `gh pr create`, enabling auto-merge, writing the PR body or a CHANGELOG entry, cutting a tagged release (version bump + CHANGELOG + tag + GitHub release). Symptoms - "PR stuck BLOCKED", "my last commit didn't land on main", "which check is required", "how do I cut a release", "auto-merge merged too early", "check-release failed", "STALE.md blocks git pull". Do NOT use for build/test mechanics (building-and-testing) or perf measurement / baseline refresh (benchmark-cuda).

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 economic profit (EVA) models with capital charge calculation, value spread analysis, and long-term value creation measurement. Use when calculating economic profit, analyzing EVA trends, or measuring value creation.

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。

Structures earnout and contingent payment mechanisms with milestone definitions, measurement periods, and payout scenarios. Use when modeling earnouts, designing milestone-based payments, or valuing contingent consideration.

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。

Structures operating partner involvement with portfolio company assignment, initiative tracking, and impact measurement. Use when coordinating operating partners, tracking operational initiatives, or measuring portfolio support impact.

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。

Constructs ROIC decomposition with invested capital measurement, operating return analysis, and value creation vs destruction assessment. Use when analyzing ROIC, building capital return frameworks, or assessing value creation.

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。

Evaluates alternative trading systems with fill rate analysis, information leakage assessment, and venue toxicity measurement. Use when analyzing dark pools, evaluating ATS venues, or assessing execution venue quality.

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。

Measures implementation shortfall with paper portfolio comparison, delay cost attribution, and execution quality assessment. Use when measuring implementation shortfall, analyzing execution quality, or attributing trading costs.

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。

Content strategy, copywriting frameworks (AIDA/PAS/BAB/4Ps/FAB), editorial calendar management, platform-specific content, A/B testing, campaign planning, audience targeting, and content performance measurement.

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。

Detect Claude Code context compaction events in session JSONL logs. Identifies compaction boundaries, measures token delta before/after, reports compaction events with timestamps and token impact.

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。

用户需要从外部可观测信号推断内部隐藏状态时; 当需要"从表象看本质"时; 当直接观测不可行, 必须通过间接指标推断时。 不适用于: 可以直接观测内部的场景、纯数据查询、不需要推断的场景。

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。

Used when the user asks to "create a PowerPoint", "generate PPTX slides", "make a PowerPoint presentation", "build a .pptx deck", "create editable slides", "PptxGenJS", "editable presentation", "corporate deck", "slide deck for sharing", or when the output format is PPTX for any presentation task. Also triggers on "export to PowerPoint", "pitch deck PPTX", "offline presentation", or when the context implies an editable/corporate format. Generates OOXML-compliant .pptx files with PptxGenJS, precise layout, text measurement, and overlap validation.

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。

Diagnoses and fixes Claude behavioral issues in system prompts and Projects using tested countermeasure templates. Use when "Claude is too verbose," "keeps hedging," "agrees with everything," "claims it did something it didn't," "won't use a tool," "fix Claude's output," "tune Claude's behavior," "Claude ignores my preferences," "adds unsolicited disclaimers," "uses too many lists." Covers ten tendencies: agreeableness (output-content + persistent-preference), hedging, verbosity, list overuse, fabricated precision, over-exploration, tool miscalibration (over- and under-triggering), LaTeX defaulting, editorial drift, self-referential fabrication. Also use when auditing a system prompt for behavioral calibration or recalibrating a pre-4.7 prompt, and when users describe recurring output problems without naming a tendency. Do NOT use for scoring a prompt's overall quality — use rootnode-prompt-validation if available.

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。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Web runtime package: uses memory in this order: connector-backed, project-pack, none. Never assumes subprocess access or unrestricted local files. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles.

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。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and learning.

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 new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

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 needs to design, run, or audit product or GTM analytics — metric hierarchies and north stars, funnels, cohort retention, churn, pipeline velocity, forecasting, lead scoring, NRR, A/B tests, or analytical SQL — or uploads a dataset to analyze. Triggers on questions like "why did activation drop", "is this metric meaningful", "review my dashboard", or "what should I measure". For writing the spec that defines a feature's success metrics, use product-spec.

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 and execute A/B tests for ML models in production using traffic splitting, statistical significance testing, and canary/shadow deployment strategies. Measure performance differences and make data-driven decisions about model rollout. Use when validating a new model version before full rollout, comparing candidate models trained with different algorithms, measuring business metric impact of model changes, or when regulatory requirements mandate gradual rollout.

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。

Restore legibility to an auto-generated graph diagram that has outgrown its canvas - rendering at single-digit percent scale with sub-pixel labels. Covers the levers that measurably reduce layout units (source-level label wrapping, invisible chain links so unconnected nodes stop spreading into one row, per-cluster splitting, layout direction picked by rendering both and measuring) and the rejected ones (raising the render font is a no-op because layout engines measure in text units; a topology heuristic for direction regressed 13 of 38 diagrams). Use when a generated Mermaid/Graphviz/DOT diagram is too small to read; not for hand-authoring a small diagram.

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 systematic data labeling workflows using Label Studio or similar tools. Implement quality controls, measure inter-annotator agreement, manage labeler teams, and integrate labeled data into ML training pipelines. Use when starting a supervised ML project that requires labeled training data, when model performance is limited by insufficient labeled examples, when labeling text, images, audio, or video, or when implementing active learning to prioritize the most valuable examples.

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。

Grade a trading card using PSA, BGS, or CGC standards. Covers observation-first assessment (adapted from meditate's unbiased observation), centering measurement, surface analysis, edge and corner evaluation, and final grade assignment with confidence interval. Supports Pokemon, MTG, Flesh and Blood, and Kayou cards. Use when evaluating a card before professional grading submission, pre-screening a collection for high-grade candidates, settling condition disputes between buyers and sellers, or estimating the grade-dependent value spread for a card.

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 and compare levitation mechanisms for a given application through a structured trade study. Covers magnetic (passive diamagnetic, active feedback, superconducting), acoustic (standing wave, phased array), aerodynamic (hovercraft, air bearings, Coanda effect), and electrostatic (Coulomb suspension, ion traps) mechanisms. Use when selecting the most appropriate levitation approach for transport, sample handling, display, bearings, or precision measurement applications.

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。

Add an external probabilistic classifier to a decision path without letting it take the path over. Covers finding the externally-graded rows you are already logging, measuring the confidence separation between the overrides it got right and the ones it got wrong, choosing an operating point your data licenses, failing open at the call site, and proving the whole arrangement offline with no API key. Applies to any service returning a score you can order — TypeSafe AI's System One models (Jev) are the worked example. Most of the method transfers to a local model or a second heuristic, with the parts that do not called out where they arise. Use when a rule-based path is wrong often enough to hurt, when someone proposes replacing a heuristic with a model, when a confidence threshold needs a defensible value, or when an oracle already in production has never been graded.

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。