Generate format-controlled research reports with evidence tracking, citations, source governance, and multi-pass synthesis. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief. Triggers: "帮我调

Deep Research Create high fidelity research reports with strict format control, evidence mapping, source governance, and multi pass synthesis. Architecture: Lead Agent + Subagents Context discipline: Keep raw search result noise in task workspaces. Pass evidence packets to the lead agent, including locators and short source excerpts. Notes are routing aids, not authorities: the lead agent must open the original source for every load bearing claim, conflicting claim, and exact figure/date/quotation used in the report. Run and asset contract — every invocation Before external retrieval, read [research asset contract.md](references/research asset contract.md). Create or resume a durable project study for single route and multi route research alike . Search its explicit prior study catalog, open relevant earlier originals and record reuse/adapt/reject decisions. Draft the decision questions and provider × actual mode lanes in study.json . Write one exact dispatch context with the user supplied seed URL, named entities, and verified codes or other identifiers needed for the query. Include that string in every lane prompt; [research assets.py](scripts/research assets.py) start rejects an omission. Capture the user's named seed article or document as an original before external dispatch, and follow the [provider handoff](references/provider run contract.md seed source handoff) when a provider cannot read its URL. A model workspace may not see the user's link or local files just because the coordinator does. Then run provider runs.py plan . Keep every user requested mode in the plan; a route that adds no value, is unavailable or lacks paid authorization gets a reasoned deferred event. A report assembled from direct web search and internal subagents still needs a direct source lane and the same archive. New studies use schema 2's [request mode contract](references/provider run contract.md request inventory independent of execution): archive the original request and accepted workflow, interpret the required modes independently of the execution lanes, and map each to matching lanes. An explicit empty mode inventory is valid when none was requested; a missing contract is not. plan rejects an omitted or mismatched mapped route. Review the inventory against the original: fields and hashes cannot prove semantic completeness. Schema 1 archives remain readable with request coverage unknown; do not restart old tasks to fill that gap. Before collecting provider reports, load [report file collection.md](references/report file collection.md). Use available file/download channels instead of the clipboard. Schema 2 submission and historical import require an unchanged actual mode observation receipt; prepared prompts do not. A deferred route stays visible with its reason. An uncertain result or legacy request coverage requires explicit bounded reason at final check/registration; retain that reason without claiming full completion. Catalog search returns current registered details and recorded coverage, not a completed integrity check; follow the [research asset contract](references/research asset contract.md start before external retrieval). During research, retain the unedited provider outputs, every opened original and every provider surfaced source URL with status and provenance. Bind report claims to approved original sources; model reports only locate candidate evidence. Before calling a report complete, run provider runs.py validate , research assets.py check , and register the study for later discovery. An answer with citations but no study/source/claim record does not satisfy this Skill. The local scripts record and check files; they make no provider calls and do not authorize paid work. Before sending a Work/Agent task that may choose its own data plugins, inspect the relevant plugin catalog for per call credits or charges. A signed in account and a request to use a data source do not set an unlimited spend ceiling. If an autonomous task can invoke metered plugins without a per call pause and this task has no explicit spend authorization for them, defer that lane or use a route where the exact calls can be approved first. Even with a budget, a prompt is not a technical charge limit: use a controllable route when the autonomous task cannot enforce it. State authorized limits in the provider prompt for traceability, then read the raw tool log after execution; if a charge occurs despite the boundary, record the observed usage and tell the user. Do not make another paid call to fill a coverage gap. Mode Selection Determine the research mode before starting: Dimension Options Topic Mode Enterprise Research (company/corporation) OR General Research (industry/policy/tech) Depth Mode Standard (multiple decision questions or contested evidence) OR Lightweight (one bounded question with a small evidence surface) Provider Mode An explicit single route or provider × mode plan. Preserve every user requested or project accepted mode as selected or reasonedly deferred; choose additional independent routes when they can materially test the decision Enterprise Research Mode : Question led company research with optional analysis frameworks selected only when they help answer the decision General Research Mode : Standard P0 P7 research pipeline with source governance Depth Selection : Choose from the number and consequence of unresolved questions, not prompt length, task count, or a target word count Provider Selection : Read the user's established workflow when they say “our way” or invoke a named research routine. Extra model reports are useful when they add a distinct evidence route, structured tool access, or a meaningful challenge. Check each provider's availability, privacy boundary and paid authorization; do not silently reduce a requested mode set to a direct source report. Never run every available route by default or hardcode a vendor roster. Source Governance (V6) Source Accessibility Classification Classify every source by accessibility: Accessibility Definition Examples Usage Rule public Available to any external researcher without authentication Public websites, news articles, WHOIS (without privacy), academic papers ✅ Always allowed semi public Requires registration or limited access LinkedIn profiles, Crunchbase basic, industry reports (free tier) ✅ Allowed with disclosure exclusive user provided User's paid subscriptions, private APIs, proprietary databases Crunchbase Pro, PitchBook, private data feeds, internal databases ✅ ALLOWED for third party research authorized first party User authorized records about the user's own organization, transactions, or work Contracts, invoices, CRM records, meeting transcripts ✅ May establish internal business facts; label provenance First party boundary: User authorized records may establish what the organization did, agreed, paid, delivered, or observed. They do not count as independent external validation of market standing, customer sentiment, regulatory compliance, or third party claims. Never relabel an internal record as an external finding. ✅ EXCLUSIVE INFORMATION ADVANTAGE : You SHOULD: Use user's Crunchbase Pro to research competitors Use user's proprietary databases for market research Use user's private APIs for investment analysis Leverage any exclusive source user provides for third party research Source Type Labels Every source MUST also be tagged with: Label Definition Examples official Primary source, official documentation Company SEC filings, government reports, official blog academic Peer reviewed research Journal articles, conference papers, dissertations secondary industry Professional analysis Industry reports, analyst coverage, trade publications journalism News reporting Reputable media outlets, investigative journalism community User generated content Forums, reviews, social media, Q&A sites other Uncategorized or mixed Aggregators, unverified sources Coverage diagnostics: Track source counts, domains, source type mix, and concentration to reveal thin coverage. Never pass or fail research from these totals alone. Gate on whether each decision question and load bearing claim has fit for purpose evidence, whether counter evidence was sought, and whether remaining unknowns are explicit. AS OF Date Policy Set AS OF date explicitly at P0. For all time sensitive claims: Include source publication date with every citation Downgrade confidence if source is older than relevant horizon Define a freshness horizon per claim class and flag material outside it; a universal age cutoff is only a diagnostic P0: Environment & Policy Setup Check capabilities before starting: Check Requirement Impact if Missing Required evidence channel available Required Narrow scope or stop with the affected questions marked unknown Original source retrieval available Required for load bearing claims Do not promote summaries/snippets to final evidence Subagent dispatch Preferred Degrade to sequential Filesystem writable Required for completion In memory notes may support partial investigation; report the archival gap and leave the study incomplete Set policy variables: AS OF : Today's date (YYYY MM DD) mandatory for timed topics MODE : Standard (default) or Lightweight, justified by the question map SOURCE TYPE POLICY : Enforce official/academic/secondary/journalism/community/other labels COUNTER REVIEW PLAN : What evidence would overturn each provisional conclusion Before setting provider mode, run the [research asset](references/research asset contract.md) catalog search. An earlier model summary is a lead; reopen its source and check freshness before reuse. Report: [P0 complete] Subagent: {yes/no}. Mode: {standard/lightweight}. AS OF: {YYYY MM DD}. When researching a specific company, use the specialized workflow to route evidence by question. Treat the six dimensions as a coverage map, not a mandatory report outline. Enterprise Workflow Overview P1: Research Task Board When continuing an existing question, first restore its supported conclusions, resolved questions, corrections, remaining unknowns and reopening conditions under [incremental follow up](references/research asset contract.md incremental follow up). Passing one previous report to an executor does not by itself establish that this state was carried forward. For every study, use the portable [provider run contract](references/provider run contract.md): one question map, exact prompts, and a distinct lane id per provider × actual mode, including a direct original source route when used. Run [provider runs.py](scripts/provider runs.py) plan before dispatch. When two or more provider/mode lanes are selected, load [parallel provider ops.md](references/parallel provider ops.md) before fan out and coordinate the available provider, browser/app, retrieval and verification Skills with independent agents. Assign one owner per control surface and serialize that owner's UI actions. Do not implement provider calls inside this Skill or assume a fixed vendor roster. Submit long asynchronous jobs early and collect each original result under its own lane; resume active tasks by their existing origin instead of starting duplicate paid work. Resolve and read each lane's current executor Skill before actual dispatch, following its authorization rules; the local planner makes no provider calls. A provider's report is an input to P3, not an independently verified source. Do not infer that normal chat used native Deep Research from model name or report length; verify the actual UI or API route. Synthesize by underlying original source and decision value, never by a vote of model

deep-research