调研与学习技能

Generate a compact pool of discussion-worthy research directions from the signal table, writing `output/trace/IDEA_DIRECTION_POOL.md`.

中文简介正在准备中。当前显示原文说明。

Review and record one pending human checkpoint in a research Workspace; use when a HUMAN Unit is blocked on an `Approve C*` decision, and never treat silence or artifact existence as approval.

中文简介正在准备中。当前显示原文说明。

Write the survey's front matter files (Abstract, Introduction, Related Work, Discussion, Conclusion) in paper voice, with high citation density and a single evidence-policy paragraph.

中文简介正在准备中。当前显示原文说明。

Use when a tutorial module plan exists but each module still needs a verifiable teaching loop.

中文简介正在准备中。当前显示原文说明。

Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.

中文简介正在准备中。当前显示原文说明。

PRODUCES a citation-budget plan/report (`output/CITATION_BUDGET_REPORT.md`); does NOT edit the draft. Allocates an in-scope per-H3 budget (NO NEW FACTS) so drafts stop failing the global unique-citation gate; citation-injector applies it.

中文简介正在准备中。当前显示原文说明。

Build per-chapter (H2) writing briefs (NO PROSE) so the final survey reads like a paper (chapter leads + cross-H3 coherence) without inflating the ToC.

中文简介正在准备中。当前显示原文说明。

Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.

中文简介正在准备中。当前显示原文说明。

Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.

中文简介正在准备中。当前显示原文说明。

Use when an approved tutorial spec exists and the run needs a deterministic prerequisite graph before module planning.

中文简介正在准备中。当前显示原文说明。

Use when a broad paper candidate pool needs deterministic deduplication and a stable core set.

中文简介正在准备中。当前显示原文说明。

Generate and verify BibTeX entries from paper notes, writing `citations/ref.bib` and `citations/verified.jsonl`.

中文简介正在准备中。当前显示原文说明。

Multi-route literature expansion + metadata normalization for evidence-first surveys.

中文简介正在准备中。当前显示原文说明。

Rewrite limitation passages so the paper keeps limitations without falling into count-based slot phrases (e.g., \"Two limitations…\") across many H3s.

中文简介正在准备中。当前显示原文说明。

Bind addressable evidence IDs from `papers/evidence_bank.jsonl` to each subsection (H3), producing `outline/evidence_bindings.jsonl`.

中文简介正在准备中。当前显示原文说明。

Synthesize the shortlist into a discussion-ready research idea brainstorm memo, writing `output/REPORT.md`, `output/APPENDIX.md`, and `output/REPORT.json`.

中文简介正在准备中。当前显示原文说明。

Global consistency review for survey drafts: terminology, cross-section coherence, and scope/citation hygiene.

中文简介正在准备中。当前显示原文说明。

Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.

中文简介正在准备中。当前显示原文说明。

APPLIES/consumes a `citation-diversifier` budget report (`output/CITATION_BUDGET_REPORT.md`) to inject *in-scope* citations into an existing draft (NO NEW FACTS), so the run passes the global unique-citation gate without citation dumps.

中文简介正在准备中。当前显示原文说明。

Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.

中文简介正在准备中。当前显示原文说明。

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

中文简介正在准备中。当前显示原文说明。

对照高可信度一手来源调查问题，并将发现以 Markdown 文件落库。当用户希望研究某个主题、收集文档或 API 事实、或把阅读跑腿交给后台 agent 时使用。

中文简介正在准备中。当前显示原文说明。

Use Exa MCP for current web, code/docs, company, people, and page-fetch research. Prefer current hosted tool schemas and note deprecated tools.

中文简介正在准备中。当前显示原文说明。

Autonomous iteration loop: modify, verify, keep/discard against any metric

中文简介正在准备中。当前显示原文说明。