'search evaluation' 검색 결과

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Standard Operating Procedures for read-only codebase exploration, symbol search, dependency mapping, code tracing, code review, architecture analysis, technical research, source evaluation, and evidence-based reporting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Marketing analytics and data-driven optimization for B2B SaaS campaigns. Use this skill when analyzing marketing performance, optimizing conversion rates, running A/B tests, conducting customer research, creating marketing dashboards, building attribution models, analyzing funnel metrics, or storytelling with data. Also triggers on: marketing ops, performance analytics, CRO, A/B testing, data storytelling, customer insights, tracking plan, event taxonomy, UTM taxonomy, GA4 audit, consent mode, instrumentation contract, sample size calculation, minimum detectable effect, test duration, not enough traffic to A/B test, statistical significance, Bayesian vs frequentist, sample ratio mismatch, experiment feasibility, martech stack, marketing tech stack audit, tool consolidation, build vs buy, vendor evaluation, shadow IT tools, ESP/CRM/platform migration, switching cost, cutover plan, suppression list migration, data portability, customer interviews, survey design, sampling frame, non-response bias, how many people should I interview, thematic saturation, voice of customer, jobs-to-be-done, buyer persona research, is this finding real, data enrichment, which enrichment provider should we buy, waterfall enrichment, contact data quality, match rate, our list data is bad, email verification, catch-all domain, accept-all, bounce rate from bad data, B2B data decay, how often should we re-verify contacts, ZoomInfo vs Apollo vs Clearbit evaluation, cost per usable record, where did this list come from, GDPR Article 14 notice, purchased list compliance, suppression screening, TAM list building, demand planning, marketing plan, how many leads do we need, what pipeline target should marketing carry, funnel model, top-down vs bottom-up plan, plan of record, annual marketing planning, quarterly planning, pipeline coverage we have to create, sales cycle lag, our leads cannot close this quarter, carry-in pipeline, scenario planning, conservative moderate aggressive forecast, stretch target, reforecast, re-forecast triggers, assumption register, capacity ceiling, addressable audience ceiling, marginal cost per lead, blended CPL is wrong, we missed plan and nobody knows why.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

DSPy로 질문 응답과 문서 검색을 결합한 AI 처리를 만듭니다. 입출력을 정의한 구성 요소를 조합하고 학습 예시와 평가 지표로 프롬프트를 자동 조정합니다.

• 문서 검색을 결합한 질문 응답 만들기
• 학습 예시로 프롬프트 조정하기
• 텍스트에서 구조화된 데이터 추출하기

공통 과제로 대규모 언어 모델의 지식·추론·코드 생성을 평가합니다. 모델 비교표와 학습 단계별 성적 추이를 만들고 평가 결과와 개별 답변을 저장합니다.

• MMLU와 GSM8K로 모델 평가
• 여러 모델의 성적 비교표 작성
• 학습 중 모델의 성적 추적

AI가 외부 서비스를 이용하는 MCP 서버 개발을 지원합니다. API 조사, 도구 설계와 구현, 동작 확인부터 실제 사용을 반영한 평가 문항 작성까지 다룹니다.

• 외부 API를 AI 에이전트에 연결합니다
• TypeScript나 Python으로 MCP를 개발합니다
• 도구 설명, 입력, 오류 문구를 개선합니다

Research existing code, documents, and relevant sources before producing a practical plan for implementation, migration, debugging, or evaluation. The plan explains key decisions, ordered steps, and validation checks, giving users something concrete to review before execution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan implementation steps before changing code
• Design a phased migration with rollback steps
• Break work into separate commits or pull requests

Organize repeated experiments to improve models, prompts, or agent systems against measurable goals. The skill records hypotheses and lessons in a persistent tree, isolates trials, and compares promising candidates using evaluation data kept separate from development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare repeated experiments to improve model training
• Improve an agent system's measured success rate
• Test prompt changes against a fixed evaluator

Analyze time series with aeon, a Python toolkit for data that changes over time. Supports classification, regression, clustering, forecasting, anomaly detection, and pattern search, with guidance on preprocessing, algorithm selection, and evaluation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classify time series and predict continuous outcomes
• Group time series with similar patterns
• Forecast future values

Build Python AI applications on Microsoft Foundry with azure-ai-projects. Provides examples for creating agents, connecting tools, managing conversations and project resources, and running evaluations through Foundry and OpenAI-compatible clients.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an agent that searches uploaded documents
• Implement conversation threads and response handling
• List model deployments and project connections

Find autonomous AI agents, frameworks, and tools through AgentFolio. Compare their capabilities, intended users, integrations, and deployment options to shortlist existing products or gather examples and ideas before designing an agent of your own.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding existing agents before building your own
• Shortlisting agent vendors for evaluation
• Researching competitors and market gaps

Evaluate investment factors across multiple securities using statistical measures and grouped backtests. Compare how well each factor predicts future returns, examine its consistency over time, and combine useful factors with equal or performance-based weights.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing whether an investment factor predicts returns
• Comparing factor strength across industries and markets
• Checking how predictive power changes with holding periods

Plan free calculators, generators, and checkers for marketing. Compare ideas by search demand, competition, and effort, then define the user flow, lead capture, landing page, launch activities, and measurement plan to assess results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare free tool ideas before committing development time
• Design useful results and an email capture flow
• Plan a tool landing page and launch activities

Design loops that improve an agent’s own prompts, workflows, or execution code from failure records. Define bounded edits, preserve candidate histories, and accept changes through independent tests that check improvements and regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing agent self-improvement from failure records
• Defining acceptance checks for self-modifying workflows
• Diagnosing score gaming and stalled improvement

Check experimental results before making research claims. A fresh reviewer examines reference data, score calculations, result files, and evaluation scope, then produces an evidence-based report showing which claims are supported and which need qualification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking results before writing a paper
• Verifying reference data and score calculations
• Matching reported numbers to result files

Monitor model training through WandB metrics to detect invalid numbers, worsening loss, and declining evaluation results. Ambiguous trends receive a Codex review, while stopped runs retain key metrics and the reason for stopping.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check loss and evaluation trends during model training
• Detect NaN values and diverging loss
• Review flat or noisy training metrics

Turn a research experiment plan into training and evaluation code, run a small setup check, and launch GPU experiments. Collect initial metrics and update progress records so the results are ready for further review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing experiments from a written plan
• Checking a small run before full GPU experiments
• Collecting baseline and main-method results

Manage machine learning experiments with MLflow by recording settings, metrics, files, and trained models. Covers experiment comparison, model version management, reproducible project configurations, and deployment workflows across local and cloud environments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording experiment settings and evaluation results
• Comparing model performance across experiments
• Managing model versions for production use

Combine specialized language models without retraining using mergekit. The skill explains how to choose merging methods, configure each model’s contribution, compare resulting variants, and prepare a merged model for evaluation and deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combine math, coding, and conversation capabilities
• Compare model variants with different merge weights
• Choose a method for merging several models

Plan systems conference papers with section page budgets, paragraph outlines, and writing patterns. Organize design choices, experimental evidence, and related work into a clear argument, then review the draft with submission checklists.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning sections and page budgets for a systems paper
• Explaining design choices and alternatives
• Organizing evaluation experiments and results

Guides fine-tuning and evaluation of OpenVLA-OFT robot models that turn images and language into actions. Covers LIBERO simulation, ALOHA deployment, LoRA adaptation that updates a small set of parameters, and troubleshooting action scaling or configuration mismatches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluate pretrained models in LIBERO
• Fine-tune robot action models with LoRA
• Deploy server-client inference for ALOHA

Explore training workflows that reduce harmful model responses using a written set of principles. The skill covers self-critique, revised training examples, and RLAIF, reinforcement learning from AI feedback, with implementation examples and hardware guidance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing principles for model safety training
• Creating training examples through self-critique and revision
• Planning reinforcement learning with AI-rated responses

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Review and improve SKILL.md files using nine evaluation criteria and test prompts. Independent agents compare original and revised versions, while user checkpoints, version history, and result cards help track which changes are retained or rolled back.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess skill quality without editing files
• Improve instructions in a specific SKILL.md
• Prioritize weaker skills for revision