Agent skill

Finta Reference Architecture

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Reference architecture for fundraising operations with Finta CRM.

MITAuto-check passedBusiness, Finance & HR

Install Finta Reference Architecture

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill finta-reference-architecture -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace finta-reference-architecture --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/finta-reference-architecture .claude/skills/finta-reference-architecture && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
finta-reference-architecture
GitHub stars
2.8k
Token cost
~1.8k tokens
SKILL.md length
455 words
Files
1
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Reference architecture for fundraising operations with Finta CRM.

  • Works in 5 steps: Treat Finta as the authoritative system… → Put exports, notifications, and CRM… → Limit event payloads to identifiers and… → …
  • With phrases like finta architecture
  • SKILL.md covers Overview, Prerequisites, Instructions and Architecture Diagram, plus 10 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Finta Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Reference architecture for fundraising operations with Finta CRM. Trigger with phrases like "finta architecture", "finta fundraising stack".

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Designed for Claude Code

It sits in Business, Finance & HR, covering Fundraising and pitch decks and CRM management. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • With phrases like finta architecture
  • Finta fundraising stack

Example prompts

  • “finta architecture”
  • “finta fundraising stack”
  • “/finta-reference-architecture”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Grep

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Treat Finta as the authoritative system only where the business has explicitly assigned that role; resolve conflicts through a review…
  2. Put exports, notifications, and CRM updates behind a durable queue with idempotency keys, bounded retries, and a dead-letter review path.
  3. Limit event payloads to identifiers and required fields; retrieve sensitive records only inside the authorized worker and redact…
  4. Separate document-room access from operational dashboards, and enforce a permission check at the point where a document is retrieved.
  5. Promote changes through staging with fictitious investor data, observe a small canary, and retain a tested disable/rollback path for each…

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • trustfinta.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Finta Reference Architecture loads about 1.8k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 455 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 455 words, ~1,790 tokens.

Download SKILL.mdSave it as .claude/skills/finta-reference-architecture/SKILL.md (or your agent's skills folder).
name
finta-reference-architecture
description
Reference architecture for fundraising operations with Finta CRM. Trigger with phrases like "finta architecture", "finta fundraising stack".
allowed-tools
Read, Grep
compatibility
Designed for Claude Code
version
1.7.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, fundraising-crm, investor-management, finta

Finta Reference Architecture

Overview

Production architecture for fundraising operations integrating with Finta's CRM platform. Designed for startup founders and fund managers who need investor pipeline visibility, automated round management, and document room analytics. Key design drivers: deal velocity tracking, investor communication audit trail, capital collection automation via Stripe, and CRM integration with external systems like HubSpot or Salesforce for LP relationship management.

Prerequisites

  • A documented data-flow inventory naming each source, destination, owner, retention period, and approved fields.
  • Separate development, staging, and production credentials with least-privilege access.
  • An incident and rollback owner for every sync or document-sharing integration.

Instructions

  1. Treat Finta as the authoritative system only where the business has explicitly assigned that role; resolve conflicts through a review queue instead of automatic overwrites.
  2. Put exports, notifications, and CRM updates behind a durable queue with idempotency keys, bounded retries, and a dead-letter review path.
  3. Limit event payloads to identifiers and required fields; retrieve sensitive records only inside the authorized worker and redact diagnostics.
  4. Separate document-room access from operational dashboards, and enforce a permission check at the point where a document is retrieved.
  5. Promote changes through staging with fictitious investor data, observe a small canary, and retain a tested disable/rollback path for each integration.

Architecture Diagram

Founder Dashboard ──→ Pipeline Service ──→ Cache (Redis) ──→ Finta API
                           ↓                                  /investors
                      Queue (Bull) ──→ Email Sync Worker      /rounds
                           ↓                                  /deal-rooms
                      Doc Room Service ──→ Finta Deal Rooms   /documents
                           ↓
                      Zapier Webhooks ──→ Slack / Sheets / CRM

Service Layer

typescript
class FundraiseService {
  constructor(private finta: FintaClient, private cache: CacheLayer) {}

  async getPipelineSnapshot(roundId: string): Promise<PipelineSnapshot> {
    const investors = await this.cache.getOrFetch(`round:${roundId}:investors`,
      () => this.finta.getInvestorsByRound(roundId));
    return { total: investors.length, byStage: this.groupByStage(investors),
             committed: investors.filter(i => i.stage === 'committed').reduce((s, i) => s + i.amount, 0) };
  }

  async moveInvestor(investorId: string, toStage: string): Promise<void> {
    await this.finta.updateInvestor(investorId, { stage: toStage });
    await this.cache.invalidate(`investor:${investorId}`);
    await this.queue.add('stage-change', { investorId, toStage, timestamp: Date.now() });
  }
}

Caching Strategy

typescript
const CACHE_CONFIG = {
  rounds:     { ttl: 600, prefix: 'round' },     // 10 min — round terms rarely change mid-raise
  investors:  { ttl: 120, prefix: 'investor' },   // 2 min — stage changes need freshness
  documents:  { ttl: 300, prefix: 'doc' },         // 5 min — doc list stable between uploads
  dealRooms:  { ttl: 60,  prefix: 'room' },        // 1 min — view analytics need near-real-time
  metrics:    { ttl: 30,  prefix: 'metric' },      // 30s — commitment totals are time-sensitive
};
// Stage-change webhooks flush investor cache immediately for dashboard accuracy

Event Pipeline

typescript
class FundraiseEventPipeline {
  private queue = new Bull('finta-events', { redis: process.env.REDIS_URL });

  async onStageChange(event: StageChangeEvent): Promise<void> {
    await this.queue.add('notify', event, { attempts: 3, backoff: { type: 'exponential', delay: 2000 } });
  }

  async processNotification(event: StageChangeEvent): Promise<void> {
    if (event.toStage === 'committed') await this.notifySlack(`${event.investorName} committed $${event.amount}`);
    if (event.toStage === 'passed') await this.logPassReason(event);
    await this.syncToCRM(event);  // Push stage change to HubSpot/Salesforce
  }
}

Data Model

typescript
interface Round     { id: string; name: string; targetAmount: number; instrument: 'SAFE' | 'convertible-note' | 'priced'; status: 'active' | 'closed'; }
interface Investor  { id: string; name: string; email: string; firm: string; roundId: string; stage: 'contacted' | 'meeting' | 'dd' | 'term-sheet' | 'committed' | 'passed'; amount: number; }
interface DealRoom  { id: string; roundId: string; investorIds: string[]; documents: Document[]; viewAnalytics: ViewEvent[]; }
interface Document  { id: string; name: string; type: 'pitch-deck' | 'financials' | 'cap-table' | 'legal'; uploadedAt: string; viewCount: number; }

Scaling Considerations

  • Partition investor pipelines by round to keep active-raise queries fast and isolated
  • Buffer email sync operations — Gmail/Outlook API rate limits are aggressive for bulk tracking
  • Batch Zapier webhook deliveries to avoid per-event overhead during rapid stage updates
  • Cache commitment totals at round level; invalidate on any investor stage change
  • Use read-through cache for deal room analytics — investors check rooms sporadically but in bursts
Show full SKILL.md (173 more words)Show less

Error Handling

ComponentFailure ModeRecovery
Investor syncFinta API rate limitQueue with exponential backoff, per-round circuit breaker
Deal room uploadS3/storage timeoutRetry with resumable upload, notify founder on failure
Email trackingGmail OAuth token expiredAuto-refresh token, fallback to manual logging alert
Stripe collectionPayment declinedRetry schedule (1d, 3d, 7d), escalate to founder dashboard
CRM syncHubSpot conflictLast-write-wins with Finta as source of truth, log discrepancies

Output

Maintain an architecture decision record showing each data boundary, the source of truth for each entity, the queue and retry policy, privileged-access owners, and the rollback switch for every external integration. Operational telemetry should be aggregated and redacted.

Examples

For a stage-change test, publish a synthetic event with an opaque investor identifier. The worker records an idempotency key, sends one redacted CRM update, and writes a success receipt. Replaying the same event must result in no second update; a destination failure goes to the review queue after the retry limit.

Resources

Next Steps

See finta-deploy-integration.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/.curated/finta-reference-architecture of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287

Compare with similar skills

Finta Reference Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Finta Reference Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Finta Reference Architecture this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.8kAutomated safety check: PassMIT
Apify Buying Signal Detectionapify/awesome-skills266—~5.1kAutomated safety check: NotesApache-2.0
Investor Outreachaffaan-m/ECC276k6 repos~664Automated safety check: PassMIT
Investor Call Prepgooseworks-ai/goose-skills1.2k1 repos~3.8kAutomated safety check: PassMIT
Dossierborghei/Claude-Skills891—~2kAutomated safety check: PassMIT
Know Your CustomerJoelLewis/finance_skills206—~3.6kAutomated safety check: PassMIT

Similar skills

  • Apify Buying Signal Detection

    apify/awesome-skills

    Official

    Set up a recurring buying-signal detection pipeline that finds companies showing buying intent across three signal types — job postings (hiring for the persona), fundraising events (recent raises)…

    266 GitHub stars~5.1k tokensUpdated 17 days ago
    Business, Finance & HRAuto-check: notes
  • Investor Outreach

    affaan-m/ECC

    Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising.

    276k GitHub starsUsed in 6 repos~664 tokens
    Business, Finance & HRAuto-check passed
  • Investor Call Prep

    gooseworks-ai/goose-skills

    Prepare for investor calls by pulling upcoming meetings from Google Calendar, deeply researching each investor and their firm (website scraping, portfolio analysis, thesis extraction), checking for…

    1.2k GitHub starsUsed in 1 repo~3.8k tokens
    Business, Finance & HRAuto-check passed
  • Dossier

    borghei/Claude-Skills

    Structured intelligence dossiers on companies, people, markets, or domains, with source triangulation and fact/inference discipline.

    891 GitHub stars~2k tokensUpdated 3 days ago
    Business, Finance & HRAuto-check passed
  • Know Your Customer

    JoelLewis/finance_skills

    Guide customer onboarding identification, due diligence, and profile maintenance under FINRA Rule 2090, the CIP rules, and the FinCEN CDD Rule.

    206 GitHub stars~3.6k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Vc Outreach

    pedronauck/skills

    Build investor lists, warm intros and cold emails; prepare meetings, manage a raise pipeline, and run diligence through close.

    634 GitHub stars~480 tokensUpdated 26 days ago
    Business, Finance & HRAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Questions about Finta Reference Architecture

What does Finta Reference Architecture do?

Reference architecture for fundraising operations with Finta CRM. Finta Reference Architecture is an agent skill from jeremylongshore/tons-of-skills-marketplace. Reference architecture for fundraising operations with Finta CRM.

When should I use Finta Reference Architecture?

Finta Reference Architecture fits situations like: with phrases like finta architecture; finta fundraising stack.

How do I install Finta Reference Architecture in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill finta-reference-architecture -a claude-code`. Or copy the skill folder (skills/.curated/finta-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/finta-reference-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Finta Reference Architecture in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill finta-reference-architecture -a codex`. Or copy the skill folder (skills/.curated/finta-reference-architecture in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/finta-reference-architecture in your project. Codex loads it when a task matches its description.

Can I use Finta Reference Architecture in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill finta-reference-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/finta-reference-architecture, .gemini/skills/finta-reference-architecture, .github/skills/finta-reference-architecture and .opencode/skills/finta-reference-architecture in your project.

What does Finta Reference Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Finta Reference Architecture is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Grep. Compatibility (from SKILL.md): Designed for Claude Code.

Does Finta Reference Architecture access the network?

SKILL.md names 1 domain. As links in the text: trustfinta.com. This is read from the text; nothing was executed.

Is Finta Reference Architecture safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Finta Reference Architecture use?

Finta Reference Architecture is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Finta Reference Architecture use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Finta Reference Architecture?

Skills that share tags, products or a category with Finta Reference Architecture: Apify Buying Signal Detection (apify/awesome-skills, 266 stars), Investor Outreach (affaan-m/ECC, 276k stars), Investor Call Prep (gooseworks-ai/goose-skills, 1.2k stars) and Dossier (borghei/Claude-Skills, 891 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Finta Reference Architecture?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.