菜单
Build a source-linked company or vendor diligence packet using Diligence Stack reports, vendor notes, and optionally entitled equity research. Use for company briefs, competitive positioning, thesis updates, catalysts, risks, monitoring dashboards, or investment research.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | company-diligence |
| description | Build a source-linked company or vendor diligence packet using Diligence Stack reports, vendor notes, and optionally entitled equity research. Use for company briefs, competitive positioning, thesis updates, catalysts, risks, monitoring dashboards, or investment research. |
Build a living thesis that connects technical or market mechanisms to business outcomes and observable proof.
Before producing user-facing content, read and apply the Diligence Stack brand guidelines. Use its color, typography, logo, citation, and link defaults unless the user explicitly requests different visual styling; its attribution and canonical-link rules always apply.
diligence-research catalog-first MCP workflow.list_catalog. Search the shared diligence-stack-reports corpus first.equity-research is authorized, use it as a private comparative source - not as the house view. Search across multiple publishers and recent dates; separate substantive analysis from disclosures and valuation boilerplate.For each thesis component show:
driver -> mechanism -> business implication -> strategic read-through -> observable signal -> confidence
Evaluate:
For enterprise AI companies, distinguish the model/runtime/interface layer, orchestration/workflow layer, and system-of-record/governance layer when relevant. Weight production conversion and sustained usage more heavily than pilots, benchmarks, or new-logo announcements.
Use the company packet. Label every metric as public fact, primary research, licensed research, derived estimate, or analyst judgment. Preserve ranges and confidence; do not manufacture false precision.
Build a source-linked, driver-based diligence model with assumptions, scenarios, sensitivities, checks, and evidence provenance. Use for market sizing, revenue builds, unit economics, capacity models, margin or EPS bridges, operating models, valuation inputs, or any spreadsheet/model request grounded in Diligence Stack research.
Apply The Diligence Stack visual identity, source attribution, citation format, and canonical-link policy to user-facing content created from Diligence Stack research. Use whenever this plugin creates or edits prose, documents, decks, spreadsheets, charts, dashboards, web pages, images, exports, or other deliverables; use the visual defaults unless the user explicitly requests different styling.
Scope and plan a diligence project before research begins. Use for investment, vendor, product, partner, acquisition, or strategic diligence when the user needs questions, workstreams, evidence requirements, priorities, or a research plan.
Search and retrieve source-linked evidence from the Diligence Stack MCP knowledge bases. Use for any company, market, product, vendor, technology, or investment question that should be grounded in Diligence Stack reports or entitled equity research.
Synthesize diligence evidence into a decision-ready memo, scorecard, risk register, or recommendation. Use when the user has research, interviews, analyses, or data-room findings and needs conclusions with confidence, red flags, and next actions.
Synthesize separately entitled private equity research alongside the Diligence Stack house view. Use for ticker briefs, consensus and disagreement maps, catalysts, earnings preparation, valuation debates, or analyst-view comparisons when the equity-research corpus is authorized.