「train」の検索結果

Fine-tune large language models — data curation, SFT, parameter-efficient methods (LoRA), evaluation, and avoiding common training failures. Use when a base model needs task-specific behavior or domain knowledge.

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。

Distill large models into smaller ones — teacher-student training, data generation, loss design, and quality validation. Use when you need big-model behavior at small-model cost.

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。

Relational schema design — normalization, keys, constraints, and evolution — use when modeling data or reviewing a schema.

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 annotation pipelines that produce reliable training labels — guidelines, agreement measurement, and quality control.

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。

Train safer, more steerable AI by having the model critique and revise itself against an explicit written constitution.

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。

Structured ideation for technical problems: divergent generation, constraint framing, and convergent selection. Use when stuck on a design, naming, architecture, or feature approach and need fresh options.

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。

Scale Ray workloads and serve models on Anyscale — managed Ray clusters for training and inference.

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。

Writing abstracts that get papers read — structured content, the 5-sentence core, and journal-specific constraints.

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。

Analyze vehicle routing and fleet optimization systems for route planning algorithms, multi-stop sequencing, time window constraints, and last-mile delivery performance.

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 factory production scheduling systems for finite capacity planning, Drum-Buffer-Rope (DBR) Theory of Constraints implementation, dispatching rules (EDD, SPT, critical ratio), sequence-dependent changeover optimization, MRP 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。

Audit litigation analytics and case outcome prediction systems -- ML outcome models (logistic regression, gradient boosting, neural nets with temporal train/test splits), settlement range modeling (Monte Carlo simulation, comparable case matching, BATNA analysis).

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。

Analyze demand forecasting systems — time-series decomposition (ARIMA, Prophet, ETS), seasonal and event-driven demand modeling, booking curve and pickup analysis, cancellation prediction, forecast accuracy metrics (MAPE, bias), and model retraining pipelines.

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。

Analyze fraud detection systems including rule engines, ML scoring models, real-time transaction monitoring, alert triage workflows, false positive management, SAR/CTR regulatory reporting, adversarial robustness testing, and adaptive retraining pipelines for payment fraud, account takeover, identity theft, and AML compliance.

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。

Analyze compliance operations for regulatory change tracking, control mapping, policy management, audit readiness, and training compliance. Triggers: 'audit compliance program', 'assess GRC platform', 'review regulatory change management', 'check control framework'.

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。

Generate a pre-launch readiness checklist for feature releases. Use this skill when: - A feature is nearing completion and you need a launch readiness checklist - You want to ensure all pre-launch items are covered (docs, training, support, rollback) - You are planning a phased rollout and need a structured go-to-market plan

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。

Scope a milestone to a fixed time window with variable scope. Use when the user says "scope this milestone", "what fits in the sprint", "cut scope for the release", "define the MVP for this milestone", "we need to ship by [date] what do we cut", "shape the work to fit the cycle", or needs to make hard scope decisions under a time constraint - even if they don't explicitly say "milestone scoping". Based on "Shape Up" by Ryan Singer (appetite, shaping, betting table) and "The Art of Project Management" by Scott Berkun (milestones as forcing functions, scope as a variable).

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。

Write an executive summary using the Pyramid Principle SCQA structure. Use when a consultant says "write an executive summary", "I need a one-pager for the exec", "how do I open this report", "write me the intro for this deck", "draft the cover memo", "I need to frame the findings", "executive doesn't have time to read the full report", "help me write the storyline", or "write the situation-complication-answer". Also trigger when someone has findings or recommendations and needs to communicate them top-down to a time-constrained audience.

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 a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover, music, sound effects, and other hard constraints. Use when a user wants to turn an idea, story, feeling, or rough/over-specified prompt into a strong text-to-video prompt (Seedance, Sora, Kling, Veo, Runway, etc.), or asks to "rewrite", "improve", "clean up", or "vibe-ify" a video prompt. Do NOT use for long narrative films that need precise word-for-word dialogue sync, industrial shot lists meant to be executed verbatim, or functional/UI demos and step-by-step tutorials.

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 a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.

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。

**WORKFLOW SKILL** — Create custom VS Code Copilot agents (.agent.md). USE FOR: new agents, tool restrictions, handoffs, orchestration patterns, discipline constraints. DO NOT USE FOR: general coding, VS Code extension 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。

Diagnose and draft or explicitly apply paid-ad optimizations using evidence, financial constraints, experiments, and capability-gated adapters. Use for campaign optimization, budget reallocation, bid changes, pausing or archiving ads, requests to delete campaigns, search-term or negative-keyword actions, creative rotation, or improving CPA and ROAS.

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。

Plan and review paid-media budgets, bidding, pacing, marginal return, forecasts, CPA, ROAS, MER, LTV:CAC, constraints, and allocation across supported platforms. Use for ad budget allocation, media budget, bidding strategy, scaling, spend pacing, budget forecast, ROAS target, or investment tradeoffs.

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 a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.

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。

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

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。