Research

Find, verify, and synthesize scientific literature with traceable citations.

使用独立 CLI 执行连续、长程的既有模块研究，通过当前代码取证、Git 提交线索反查和用户补充问题三条轨道，把代码、测试、配置和文档中的当前行为沉淀为经过最终审查的专家级模块认知资产。支持完成后重新追加问题并刷新认知。适用于深入理解模块职责、运行路径、数据与状态、外部契约、失败恢复、并发一致性、配置、安全、可观测性…

Search and retrieve academic papers from arXiv using their free REST API.

Investigate scientific evidence with a lightweight literature workflow, or run bounded experiments with task-specific evaluation and reproducible checkpoints.

深度研究工具。接收用户的研究主题，分析请求、生成研究提示词， 用户确认后执行多源网络搜索（覆盖中英文主流平台和社交媒体）， 最终产出带引用链接的结构化 Markdown 研究报告并保存。 当用户说"深度研究"、"帮我研究一下"、"deep research"、"调研一下"、"调研"时触发。

here.now lets agents publish websites and store private files in cloud Drives.

Research BytePlus products, APIs, SDKs, setup, quotas, regions, pricing, and troubleshooting using the bundled official documentation index, then verify…

Four-phase SDLC loop for any codebase: intent (90% clear: explore, reproduce, research, ask the requester), plan (parallel scouts, one PLAN.md), build…

Investigate codebases with SCAN, READ, and DEEP reading modes.

Compress research findings into actionable artifacts with tiered reduction.

Phase 1 spec research: refines spec, fills gaps via user Q&A, surveys algorithm candidates with trade-offs.

Portable multi-source research with cross-source validation and an offline evidence ledger.

Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper…

Fetch a BibTeX citation from a DOI and optionally add it to a bibliography.

Progressive disclosure for what AI agents produce.

Manage a GitHub-Issues-backed backlog and a Projects-v2 work graph via five verbs.

Delegate bounded research, analysis, codebase scouting, or audits to GPT-6.1 Sol through Codex CLI in Fast mode.

Run customer interviews that produce usable language instead of agreement, and turn the transcripts into a sharper ICP.

Perform CWE-grounded security code reviews and precise weakness mapping using a locally derived MITRE CWE corpus, relationship graphs, mapping notes…

Interactive diary writing assistant that guides users through journal entries using interview-style questions.

Use when writing a Wikipedia-style article or comprehensive research-backed document on a technical topic.

Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers…

Question-driven workflow for empirical research, from source inventory through paper review.

Enforce and audit FAIR data principles (Findable, Accessible, Interoperable, Reusable) across scientific datasets, bioinformatics workflows, metadata…