Results for “search evaluation”

Develop a broad research interest into evaluated project options. Specialized agents generate ideas, assess feasibility and competition, and draft abstracts and conclusions, helping researchers decide what to pursue, postpone, or drop and which assumption to test first.

• Turn a broad research interest into project ideas
• Compare the novelty and feasibility of research proposals
• Check competing work before choosing a direction

Diagnose slow MSBuild startup by measuring project evaluation, the work done before compilation. Inspect logs for costly file searches, imported configuration, and repeated evaluations, then identify targeted changes supported by timing evidence.

• Investigating delays before compilation starts
• Checking file searches across large directories
• Analyzing deep import chains

Research industrial AI topics such as predictive maintenance and anomaly detection. Compare papers by methods and publication venues, distinguish preprints from reviewed work, identify conflicting findings and research gaps, or build an evidence-based survey draft.

• Researching recent predictive maintenance literature
• Comparing industrial anomaly detection methods and evaluations
• Identifying research gaps in manufacturing AI

Find scientific papers in PubMed by turning a research question into targeted search terms and synonyms. Collect titles, authors, abstracts, and identifiers into a structured paper list ready for relevance evaluation.

• Finding an initial paper set for a research question
• Searching for methods, compounds, or diseases
• Filtering papers by date, journal, or author

Helps design semantic search and RAG, where an AI answers using retrieved documents. Covers embeddings, numerical representations of content, plus document splitting, search indexes, keyword search combinations, and evaluation of retrieval quality.

• Design document retrieval for AI answers
• Compare embedding models and document splitting strategies
• Combine semantic search with keyword search

Plan and carry out research by refining questions, improving searches, evaluating sources, and checking claims across independent references. Turn findings into cited reports that explain the evidence, conflicting views, confidence levels, and remaining gaps.

• Comparing options using multiple sources
• Checking source reliability and conflicting claims
• Writing research reports with citations

Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports

Guide role-specific work in LoopX auto-research, from defining research conditions and proposing hypotheses to experiments, evaluation, and adoption or retirement decisions. Keep evidence, failed attempts, task handoffs, and stopping conditions tied to each worker’s assigned role.

• Define research objectives, metrics, and editable scope
• Record hypotheses and unsuccessful research directions
• Run a selected experiment and capture evidence

Plan philosophy and interdisciplinary papers by comparing preprint platforms, searching literature, identifying unanswered questions, and assessing originality. Receive a detailed outline with section word counts, key citations, and improvements based on a reviewer-style assessment.

• Planning a philosophy or interdisciplinary paper
• Choosing a suitable preprint platform
• Finding research gaps and assessing originality

Audit a specific web page using Google Search Console data and its live HTML. Assess content quality, search intent, readability, metadata, structured data, and internal links, then produce a scored SEO report with suggested fixes.

• Reviewing the SEO of a specific blog post
• Checking content and technical issues on a landing page
• Planning page improvements using search performance data

Use when a decision needs deep multi-source technical research with cited evidence — technology evaluation, ecosystem comparison, standards/spec fact-finding, "how do others solve X". Triggers on "research X", "deep dive on X", "evaluate X vs Y", "find best practices for X". NOT for library/API doc lookup (see mk:docs-finder); NOT for one-shot URL fetch (see mk:web-to-markdown); NOT for internal codebase discovery (see mk:scout); NOT for project-only Q&A (see mk:ask-me); NOT for comparing solution designs (see mk:brainstorming); NOT for root-cause debugging (see mk:investigate); NOT for wiki ingestion of sources (see mk:wiki-research).

The English summary is being prepared. Showing the original description.

Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation. Capabilities: technology evaluation, architecture analysis, best practices research, trade-off assessment, solution design. Actions: research, analyze, evaluate, compare, recommend technical solutions. Keywords: research, technology evaluation, best practices, architecture analysis, trade-offs, scalability, security, maintainability, YAGNI, KISS, DRY, technical analysis, solution design, competitive analysis, feasibility study. Use when: researching technologies, evaluating architectures, analyzing best practices, comparing solutions, assessing technical trade-offs, planning scalable/secure systems.

The English summary is being prepared. Showing the original description.

Research a topic across multiple web sources, break it into focused questions, and read key pages in depth. Produce a report with source links, confidence levels, practical findings, and clear distinctions between facts and estimates.

• Investigating competitors and market trends
• Comparing technologies before choosing one
• Researching market size and growth forecasts

Prepare and review research funding proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Maps application requirements to draft sections, identifies gaps, and helps refine research aims, budgets, impact statements, and responses to reviewers.

• Map funding-call requirements to proposal sections
• Review research aims against evaluation criteria
• Align budgets and timelines with the research plan

Develop and prioritize early research ideas through independent brainstorming, structured discussion, evidence checks, and critical review. Keep assumptions, uncertainty, dissent, and scoring reasons visible, then record the human decision and appropriate next steps.

• Exploring candidate directions for a new research topic
• Organizing ideas before a research team discussion
• Comparing proposals using explicit evaluation criteria

Prepare and check research documents for clinical decision-support evaluation, including evidence profiles, cohort tables, survival plans, and model assessments. Work with aggregate or synthetic inputs, record sources and review status, and keep outputs outside patient care.

• Preparing research model evaluation documents
• Checking evidence profiles and source links
• Reviewing survival analysis plans

Turn a research proposal into an experiment plan tied to specific paper claims. Define comparisons, evaluation measures, tests that remove individual components, run order, and compute estimates, with a written plan and tracker for execution.

• Turning a research proposal into concrete experiments
• Designing comparisons and component-removal tests
• Prioritizing runs within a compute budget

Turn research code and experimental results into ML and AI paper drafts. The skill guides paper structure, related work searches, citation verification, and conference formatting with LaTeX, a document preparation system used for academic papers.

• Drafting a paper from research code and results
• Finding and organizing related research
• Verifying citations and retrieving BibTeX entries

Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and request-level candidate testing; do not modify search scenes, app config, dictionaries, recommend scenes, or primary recall parameters.

The English summary is being prepared. Showing the original description.

Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.

The English summary is being prepared. Showing the original description.

Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: "research X for me", "do web research on", "look up sources for", "find citations for", "gather evidence on", "what does the web say about X". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), local file search, LLM-as-judge evaluation, or paywalled/auth-gated scraping. Produces a written plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.

The English summary is being prepared. Showing the original description.

Build TypeScript code for Azure AI Foundry projects using its SDK, a library for accessing project services. Create and run agents, inspect connections and deployed models, and manage datasets and search indexes.

• Creating and running agents in TypeScript
• Adding file search or external tools to agents
• Inspecting project connections and deployed models

Run repeated change-and-evaluation cycles for one predefined improvement mission within an explicit runtime limit. Save each evaluation as JSON and each decision in readable Markdown logs, with support for periodic reruns through Claude Code native cron.

• Repeating improvements under a fixed evaluation method
• Keeping evaluation results and decision logs
• Running experiments within a time limit

Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports