Results for “sources”

知らない分野にキャッチアップするとき、汎用的な言葉から界隈の用語・中心の人・場（学会・雑誌・個人ブログ・動画・リポジトリ・一覧）を特定し、 引用・リンク・著者を芋づる式にたどって、当たりの原文（論文も個人の記事や動画の字幕も）を要約せずそのまま ~/.local/share/imozuru/<話題>/sources/（リポジトリの作業のための調べものは <repo>/.tmp/docs/research/<話題>/sources/）に落とす。 周ごとに地図（map.md）を育て、要る主張の全部に原文が付くか飽和したら止める。 見張りのモードでは、地図の場（Qiita・Zenn のタグ、note、YouTube、ブログ、arXiv）の新着を RSS で引いて原文の冒頭つきで並べる。 以下で使用:「芋づる式に調べて」「この分野をキャッチアップしたい」「界隈の用語と人から掘って」 「論文とか先行研究を漁って」「既存の技術を真似したいから元ネタを探して」「上手い人のやり方を集めて」「原文で落として」「/imozuru」 「〇〇って研究あるの？原典ほしい」「全然わからないから流れを掘って」「どういう界隈でどう呼ばれてるか知りたい」 「〇〇の新着見て」「今週の〇〇の記事まとめて」「キャッチアップ」「/imozuru watch」 "dig into this field", "find the canonical papers on X", "literature dive", "what's new in X this week"。 以下には使用しない: 答えが1つの事実の確認（年・有無だけ・仕様1つ → そのまま検索）／ 手元の PC の中の資料を探す／読んだ資料の要約や解説を書く。

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

Maintain an OpenClaw memory wiki using original sources and stored notes. Update existing pages, preserve human-written sections, and check for contradictions, missing source information, and unresolved questions after meaningful changes.

• Update wiki pages from original sources
• Find and inspect stored knowledge before citing it
• Check contradictions and missing sources after updates

Investigate a question using official documentation, source code, specifications, and first-party APIs. A background agent records the findings in one Markdown file with sources for each claim, following the repository’s existing conventions for research notes.

• Verify API behavior against official sources
• Save research findings with citations
• Delegate reading while continuing other work

Evaluate prediction markets as information sources for products, agents, dashboards, and business decisions. Record probabilities implied by market prices with sources and timestamps, assess signal quality, and compare other evidence to recommend suitable uses and explain limitations.

• Evaluating prediction-market data for a product
• Comparing market probabilities with internal dashboard metrics
• Assessing probability signals for agent memory or alerts

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

Build web discovery into applications and agent workflows with Firecrawl search. Turn a query into candidate URLs, select useful sources, and decide whether to retrieve page content for further extraction or answers with cited sources.

• Finding web sources for answers with citations
• Discovering companies, competitors, or topics
• Creating a shortlist of pages for deeper research

Research current public information by checking original sources, recording relevant passages, dates, and URLs, and using browser interaction when needed. Cross-check important claims and clearly separate supported facts from inference.

• Checking current information against official sources
• Comparing evidence across multiple web pages
• Researching pages that require browser interaction

Save user-provided or approved decisions, constraints, and facts for an AI team, then retrieve them with their sources. Keep memories separate by team and tenant, and report whether retrieval used a degraded search mode.

• Save team decisions with their sources
• Record approved project constraints and facts
• Recall information the team already knows

Review external links in articles to identify unsupported factual claims and suggest authoritative sources. Check link attributes used for security and for identifying paid, affiliate, or untrusted links, then guide corrections to citations and markup.

• Find factual claims that lack source links
• Add citations to official or research sources
• Review external link security attributes

Review web content for factual claims, figures, and quotations that need reliable sources. Identify missing citations, suggest relevant external links with clear link text, and check the rendered page and HTTP response.

• Checking sources for claims and figures in articles
• Adding links to official information and research
• Reviewing citation link text

Create and update dashboards with charts, metrics, and tables drawn from connected data sources or attached files. Link displayed values to their sources so readers can inspect queries, calculations, and freshness while reviewing business indicators or recurring reports.

• Track KPIs and progress toward targets
• Visualize CSV, TSV, or JSON data
• Build recurring reports from connected data

Design multi-agent workflows for research, reviews, and migrations. Organize work across different evidence sources, add independent checks, and combine findings while preserving source references, unresolved questions, and limits on what was examined.

• Plan research across multiple evidence sources
• Review implementation and tests from different angles
• Compare candidate solutions with independent judges

Research a question from five search angles, gather sources, and test their claims through multiple verification judgments. The workflow combines overlapping findings and produces a cited report with conclusions ranked by confidence.

• Investigating a topic from several perspectives
• Checking claims across multiple web sources
• Preparing a research report with citations

Research recent discussions about a topic across social platforms, communities, and the web. Collect posts and engagement from the last 30 days, summarize supported findings with source links, and diagnose unavailable or broken research sources.

• Reviewing reactions to a product or announcement
• Comparing recent user opinions about tools
• Finding topics gaining attention in a field

Compare job requirements with your current skills and experience to identify learning priorities. Get a report with ranked gaps, study resources found through web searches, estimated learning time, and a recommended study sequence.

• Identify skill gaps across tracked jobs
• Build a learning plan for one job posting
• Choose study resources and a learning sequence

Build and operate bioinformatics workflows on Latch using Python, Nextflow, or Snakemake. Configure computing resources and input forms, move data, connect Registry records, and register, debug, launch, and monitor analysis runs.

• Create and register Python analysis workflows
• Package Nextflow or Snakemake pipelines for Latch
• Connect Latch Data and Registry records

Organize research sources in self-hosted Open Notebook, then search them, ask questions with citations, create notes, transform text, or generate podcasts with multiple speakers. Supports REST API automation and configuration of local or cloud AI providers.

• Collect PDFs and web sources in a research notebook
• Ask questions about selected sources with citations
• Apply custom summaries and text transformations

Search academic literature across sources, verify references, and convert citation files. Build PubMed queries using MeSH, its subject vocabulary, or audit citations to distinguish independent citations and document who cited a paper and how.

• Search academic literature across multiple sources
• Verify references extracted from a document
• Build a MeSH-based PubMed search strategy

Manage AWS infrastructure as TypeScript code with SST v4 and Pulumi. Guides resource creation, connections between services, infrastructure tests, deployment checks, troubleshooting, and resource migrations while accounting for existing project conventions.

• Adding AWS resources to an SST v4 application
• Connecting resources and reviewing access permissions
• Adding infrastructure tests and reviewing deployment changes

Find the right GitNexus tools and workflows for exploring code relationships. This reference explains available commands, graph queries, and resources, including how to check which branch an answer describes and whether its index is current.

• Find a GitNexus tool for a specific task
• Learn how to query code relationships
• Check index freshness and branch information

Prepare the narrative, sources, and design requirements for an editable PowerPoint deck. Clarify the audience and intended decision, track evidence for factual claims, and record visual choices before slide creation begins.

• Clarifying a presentation's audience and intended decision
• Choosing a narrative framework
• Organizing sources for metrics and claims

Create courses grounded in verified external facts, including recent developments, market data, product details, and scientific findings. It researches sources, records which evidence supports each claim, and carries those findings and uncertainties into page plans and content.

• Creating a course about recent events or industry developments
• Building lessons around verified market or policy data
• Teaching product details or scientific findings with sources

Turn company documents, public filings, and other sources into structured Excel workbooks for investment review. Organize financial statements and operating metrics, document sources and adjustments, and check that calculations and statements reconcile.

• Preparing financial data for M&A due diligence
• Building materials for investment committee review
• Standardizing reporting across portfolio companies

Organize Power Automate flows by business impact and responsible team using FlowStudio’s cached records. Find resources without active owners, audit connections to other services, review compliance metadata, and configure notifications for failures or missing runs.

• Review flows for missing governance information
• Find resources owned by departing employees
• Audit connectors and premium license needs