other / skill

Claude for Financial Services

Reference agents, skills and data connectors for investment banking, equity research, private equity and wealth management work in Claude.

At a glance

Purpose
Reference agents, skills and data connectors for investment banking, equity research, private equity and wealth management work in Claude.
Runs in
Chat app with skills, Local agent with shell, Web service
Operating systems
Not stated
Needs
Runtime: Not stated; Needs internet: Yes; Needs accounts or API keys beyond your agent: Not stated
Files and data
Reads files: Yes; Writes files: Yes; Sends data to other services: Yes
Tool type
Skill
Delivery
From GitHub
Version
Latest on the main branch
Access
Code on GitHub
Compatibility
According to the README: Claude Cowork plugins, Claude Code plugins installed with claude plugin commands, and the Claude Managed Agents API. The README also describes tooling that provisions the Claude Microsoft 365 add-in for Excel, PowerPoint, Word and Outlook against Vertex AI, Bedrock or an internal LLM gateway. The README describes the data connectors as MCP servers.
External costs
The repository is Apache-2.0 licensed and states no pricing. The README says MCP access may require a subscription or API key from the data provider. Your coding agent or model provider may charge for usage.
Permissions
The agents and skills act through Claude with the access you give it. The README says MCP access may require a subscription or API key from the provider. The README says connectors are MCP servers that link Claude to data providers and document stores. The README says Managed Agents deployment uses your Anthropic API key, uploads skills, creates leaf-worker subagents and posts the orchestrator to /v1/agents. The README says the Microsoft 365 tooling guides an IT admin through generating an add-in manifest, granting Azure admin consent and writing per-user routing configuration through Microsoft Graph. The README also describes editing .mcp.json, skill files and agent prompts to customize the deployment.
Usage terms
Apache License 2.0, as stated in the repository. See its LICENSE file for the exact terms.

Code on GitHub

anthropics/financial-services

Apache-2.0

Python39,554 stars5,590 forksLast pushed 21 Sept 2026 UTC

Public GitHub data fetched · 0 days old

Skill folders in this repository (112)

Folders that contain a SKILL.md file, from GitHub's file list on .

And 12 more in the repository.

View on GitHub ↗

What it does

Claude for Financial Services is a set of reference agents, skills and data connectors for financial-services workflows. According to the README, the same source can be installed as a Claude Cowork plugin or deployed through the Claude Managed Agents API behind your own workflow engine.

The README lists named agents such as Pitch Agent, Market Researcher, Earnings Reviewer, Model Builder, GL Reconciler, Month-End Closer and KYC Screener. It also lists vertical plugins for financial analysis, investment banking, equity research, private equity, fund admin and operations, and partner-built plugins for LSEG and S&P Global. Slash commands include /comps, /dcf, /earnings and /ic-memo. The README says everything is markdown and JSON with no build step.

The README says these agents draft analyst work product for review by a qualified professional. It says they do not make investment recommendations, execute transactions, bind risk, post to a ledger or approve onboarding, and that every output is staged for human sign-off. It also says nothing in the repository is investment, legal, tax or accounting advice.

Who it is for

Teams in investment banking, equity research, private equity, wealth management and fund admin who use Claude Cowork, Claude Code or the Claude Managed Agents API.

Example tasks

The README describes these tasks:
Pitch Agent: comps, precedents and LBO to a branded pitch deck
Earnings Reviewer: earnings call and filings to a model update and note draft
GL Reconciler: find breaks, trace root cause and route for sign-off
/comps: comparable company analysis with trading multiples
KYC Screener: parse onboarding documents, run the rules engine and flag gaps

Getting started

According to the README, in Cowork open Settings, Plugins, Add plugin, then paste the repository address or upload a zip of a folder under plugins. In Claude Code, run claude plugin marketplace add anthropics/financial-services and then install what you want, starting with claude plugin install financial-analysis@claude-for-financial-services. For Managed Agents, set ANTHROPIC_API_KEY and run scripts/deploy-managed-agent.sh gl-reconciler. The README has the exact commands.

Limitations

According to the README, the agents run in Claude Cowork, Claude Code or through the Claude Managed Agents API. The README labels subagent delegation (callable_agents) Research Preview. The README says MCP access may require a subscription or API key from the provider, and the Managed Agents deployment example uses ANTHROPIC_API_KEY. The README says the Microsoft 365 install tooling is a Claude Code plugin, not a Cowork plugin. The README describes the agents as starting points to tune to your firm and says their analyst work product requires review by a qualified professional. The README says the repository does not constitute investment, legal, tax or accounting advice, and assigns responsibility for checking outputs and complying with applicable laws and regulations to the user. The repository can change at any time; check its README before you install.

Data practices

The README lists MCP connectors to outside data providers, with their addresses, and says access may require a subscription or API key from the provider. It says the Microsoft 365 tooling provisions the add-in against your own cloud, Vertex AI, Bedrock or an internal LLM gateway, instead of Anthropic's API. It points to per-agent READMEs for security notes. It gives no general statement on storage or telemetry. What is sent where depends on the connectors you enable, your Claude product and your model provider.

Community experience

Not rated yet

Sign in to share your experience.

Comments 0

No comments yet.

Sign in to comment

Report a listing concern