Use when the user asks for D&B Finance Analytics workflows such as customer onboarding, credit decisioning, credit limit validation, portfolio risk management, company reports, ownership trees, folder management, or alerts. Use only the D&B Finance Analytics MCP tools for these workflows.
npx skills add https://github.com/openai/plugins --skill fa-jobs-to-be-done
This skill routes D&B Finance Analytics requests to the partner-supplied workflow
references in fa-skills/references/.
Use the D&B Finance Analytics MCP server only. Do not substitute Morningstar,
Moody's, generic web search, local files, or another MCP server for Finance
Analytics data.
Before making a tool call, confirm the Finance Analytics MCP tools are available.
If they are not visible, tell the user the D&B Finance Analytics connection is not
available and stop rather than fabricating data.
Expected Finance Analytics tools include:
fa_search_toolquery_portfolioget_company_reportget_live_reportaccount_decisioning_toolapplication_decisioning_toolmanage_folderget_company_ownership_treequery_alertsget_portfolio_statusget_portfolio_public_recordsget_companies_and_accounts_countget_dashboard_overviewget_risk_distributionget_dashboard_statusTool names may be exposed with a Codex namespace such as
mcp__finance_analytics_mcp_server__query_portfolio; use the namespaced form when
available.
Load exactly one workflow reference based on the user's intent:
| Intent signals | Load this reference |
| --- | --- |
| onboard, new customer, new account, add to portfolio, can I do business with | fa-skills/references/fa-onboarding-workflow.md |
| credit decisioning, company overview for credit, financial profile, company report | fa-skills/references/fa-credit-decisioning.md |
| approve credit, credit limit, increase credit, validate credit, extend credit | fa-skills/references/fa-credit-validation.md |
| portfolio risk, top risky companies, portfolio overview, risk distribution, risky accounts | fa-skills/references/fa-portfolio-management.md |
| alerts, unread alerts, new alerts, alert severity, alerts for a company | fa-skills/references/fa-alerts-monitoring.md |
If the user's intent is ambiguous, ask one clarifying question before calling tools.
The partner bundle did not include dedicated persona files or an aging-forecast
workflow file. For persona-specific language, load fa-skills/references/fa-plain-language.md.
For aging forecast requests, explain that no aging-forecast workflow was supplied in
this skill bundle and ask whether the user wants to proceed with available portfolio
or report workflows instead.
Before producing user-facing output, load:
fa-skills/references/fa-plain-language.mdUse it for tone, numeric presentation, status summaries, and suppression of internal
tool or entity identifiers.
same parameters.
gap affects the result.
decisions based on available data.
critical decision.
fa-plain-language.md.credit, portfolio, report, ownership, or alert results.
Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.
This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity allocation", or requests organizational design and headcount planning for a startup.
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead.
Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.
Google Workflow: Today's meetings + open tasks as a standup summary.
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.
Initialize the productivity system and open the dashboard. Use when setting up the plugin for the first time, bootstrapping working memory from your existing task list, or decoding the shorthand (nicknames, acronyms, project codenames) you use in your todos.
Take openai/fa-jobs-to-be-done from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.