Research
Research, evidence gathering, literature, reports, investigation, and synthesis
Browse research skills
Showing 1,873–1,896 of 22,633 skills
当用户明确要求"写/改 NSFC 立项依据""立项依据写作/重构"时使用。基于最小信息表输出价值与必要性、现状不足、科学问题/假说与项目切入点,并保持模板结构不被破坏。适用于 NSFC 及各类科研基金申请书的立项依据写作场景。
Retrieve disease-associated targets from Open Targets using disease EFO IDs to identify therapeutic targets.
Search scientific literature and research papers using FlowSearch to find relevant academic articles and publications.
Search PubMed database for scientific articles and publications to retrieve biomedical literature.
Cross-company language sweep via Quartr full-text search — date the adoption curve of a term/phrase across the global transcript+filing corpus, identify which companies (and which speaker roles) use it and when they started, and cross-reference against vault theses and graph adjacency to flag terms propagating through supply chains the book owns. Use when user says "sweep", "who is talking about X", "language scan", "adoption curve for X", or "is X inflecting".
Surface new insights, potential trades, and research opportunities from existing vault content. Use when user says "surface", "what am I missing", "find opportunities", or "what should I research next".
Adversarial thesis testing — act as a short seller to find the weakest points in a thesis. Use when user says "stress test", "devil's advocate", "challenge this thesis", or "break [TICKER]".
Change conviction level or status on a single thesis. Use when user says "change conviction", "downgrade", "upgrade", "move to monitoring", "close [TICKER]", or "set [TICKER] to [level]".
Propagate a hypothetical macro scenario through the entire portfolio. Use when user says "what if", "scenario", "what happens to my portfolio if", or describes a macro event to model.
Generate a backward-looking retrospective of vault activity (addressed callouts + Log entries) over a time window (1w / 1m / 1q), overlay with newsflow + earnings transcripts + price action, and rank trade ideas by the gap between official narrative and market reaction. Output is an immutable Research note. Use when user says "retro", "retrospective", "what did I do this week/month/quarter", "review activity against market", or "recommend trades from recent research".
Run health checks on the vault for inconsistencies, stale data, orphaned notes, and missing connections. Use periodically or when user says "lint", "health check", or "audit".
Ingest content into the vault as structured research notes. Accepts a URL, a local file path, `--from-brief [date]` (pick stories from an n8n Daily Intel news brief), or no arguments (batch-processes _Inbox/). Use when user shares a URL, says "clip this", "ingest", "ingest from the brief", or "process inbox".
Weekly sweep of ALL transcript-bearing spoken events (earnings calls, conference firesides, CMDs, investor days, AGMs, investor updates) for every active thesis, via the Quartr watchlist. Produces a triage digest in Daily Intel/ flagging thesis-touching mentions and recommending deep reads. Use when user says "event sweep", "what did my companies say this week", "conference sweep", or on the weekly schedule. Also `--setup` (build/rebuild the Quartr watchlist from active theses) and `[N]` (win...
Audit whether a thesis's stated conviction matches its evidence, and whether any Conviction Trigger has silently fired without being actioned. Use when user says "conviction audit", "is my conviction right on [TICKER]", "did a trigger fire", or "should I re-rate [TICKER]".
Generate a concise 1-page investment brief from a thesis — the elevator pitch version. Use when user says "brief", "summarise thesis", "pitch me [TICKER]", "one-pager", or "investment memo".
Extract a thesis's load-bearing assumptions and scan for internal contradictions — the falsifiable claims the bull case requires, what would falsify each, and where the thesis's own Risks / Bear Case / research already argue against it. Use when user says "assumptions", "what must be true", "load-bearing assumptions", or "does [TICKER] contradict itself".
Surface new insights, potential trades, and research opportunities from existing vault content. Use when user says "surface", "what am I missing", "find opportunities", or "what should I research next".
Adversarial thesis testing — act as a short seller to find the weakest points in a thesis. Use when user says "stress test", "devil's advocate", "challenge this thesis", or "break [TICKER]".
Change conviction level or status on a single thesis. Use when user says "change conviction", "downgrade", "upgrade", "move to monitoring", "close [TICKER]", or "set [TICKER] to [level]".
Propagate a hypothetical macro scenario through the entire portfolio. Use when user says "what if", "scenario", "what happens to my portfolio if", or describes a macro event to model.
Generate a backward-looking retrospective of vault activity (addressed callouts + Log entries) over a time window (1w / 1m / 1q), overlay with newsflow + earnings transcripts + price action, and rank trade ideas by the gap between official narrative and market reaction. Output is an immutable Research note. Use when user says "retro", "retrospective", "what did I do this week/month/quarter", "review activity against market", or "recommend trades from recent research".
Run health checks on the vault for inconsistencies, stale data, orphaned notes, and missing connections. Use periodically or when user says "lint", "health check", or "audit".
Ingest content into the vault as structured research notes. Accepts a URL, a local file path, `--from-brief [date]` (pick stories from an n8n Daily Intel news brief), or no arguments (batch-processes _Inbox/). Use when user shares a URL, says "clip this", "ingest", "ingest from the brief", or "process inbox".
Targeted deep research to fill a specific gap in an existing thesis. Use when user says "deepen", "flesh out", "expand on", "fill in", or specifies a thesis section to improve. Also supports --sync-metrics mode — detects stale financial metrics across every in-scope analytical section of a thesis (not just Key Metrics or Summary) and coherently updates every sentence that depends on them, using a Key-Metrics-table / FMP / web-search waterfall. Use when user says "sync metrics", "update the nu...