Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Syndication

ASecurity

Builds a plan to spread a financing across multiple providers, defining roles, allocations, underwriting basis, and flex. Use when a financing is too large or risky for one provider.

8 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-finance-skills --skill syndication --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Syndication?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Syndication
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-syndication/badge)](https://www.skillsdirectory.com/skills/andreworia-syndication)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: syndication
description: Builds a plan to spread a financing across multiple providers, defining roles, allocations, underwriting basis, and flex. Use when a financing is too large or risky for one provider.
---

# Syndication Agent

## When to use
Use this agent when a financing is too large or too risky for a single provider to hold and it must be spread across several. The trigger is a deal where the lead cannot or will not retain the full amount and you need a plan for who leads, who participates, and how the paper is allocated and de-risked.

## What it does
It produces a syndication plan with roles and allocations: the lead and participant structure, allocation sizing, the underwriting basis, flex terms, and the timeline to close.

## Method
This agent runs a structured syndication strategy.

1. Define the syndication need. State the total facility size, the lead's target final hold, and the amount that must be placed with others.
   - Establish the driver: sheer size, single-name risk concentration, or a desire to diversify relationships.

2. Set roles. Designate the lead or arranger, any co-leads, and the participant tier.
   - Define responsibilities: the lead runs the process, sets terms, and holds the pen; participants take allocation on those terms with limited input.
   - Decide title economics up front; co-leads expect a larger fee share and league-table credit in exchange for a bigger commitment.

3. Choose the underwriting basis. Decide between a firm underwrite, where the lead commits the full amount and then sells down, and a best-efforts basis, where the lead commits only its own hold and markets the rest.
   - Trade-off: a firm underwrite earns a higher fee and gives the borrower certainty but leaves the lead holding unsold paper if the market softens; best-efforts is lower risk and lower fee.

4. Size allocations. Build the allocation stack: lead final hold, co-lead holds, and participant tickets.
   - Ensure the stack sums to the facility, no single participant creates undue concentration, and there is room to scale back if the book is oversubscribed.

5. Set flex terms. For an underwrite, define pricing flex, structure flex, and any market-flex provisions that let the lead adjust terms to clear the market.
   - State the flex caps explicitly; uncapped flex transfers all market risk to the borrower and is rarely accepted.

6. Build the timeline. Sequence launch, the commitment or syndication period, allocation and scaling, and close and funding.
   - Identify go/no-go checkpoints, typically at the end of the commitment period when the book is assessed.

7. Plan risk management. Address the sell-down plan, a market backstop if demand is soft, and contingency if the book is undersubscribed.
   - What good looks like: the lead knows its worst-case hold and has priced the flex to reach clearing terms without breaching it.

8. Summarize. Present the plan with roles, allocations, basis, flex, and timeline in one view.

## Inputs
- Total facility size and instrument type
- The lead's target final hold and maximum acceptable hold
- Underwriting appetite (firm versus best-efforts)
- Candidate participants and their likely appetite
- Timeline constraints and the funding date
- Market conditions and recent comparable syndications
- The borrower's tolerance for pricing and structure flex

## Output format
Claude returns:
- A statement of the underwriting basis and the rationale for it.
- The role structure naming the lead, any co-leads, and the participant tier with responsibilities.
- The allocation stack described as a list of holders with their ticket sizes summing to the facility (in prose, not a table).
- The flex terms with their caps.
- The timeline with its go/no-go checkpoints.
- The risk-management and contingency plan, including the lead's worst-case hold.

## Example
Northwind Logistics is raising a 500 million dollar term loan, and a bulge-bracket bank leads on a firm underwrite basis targeting a 150 million dollar final hold. The allocation stack places the lead at a 150 million dollar final hold, two co-leads at 100 million dollars each, and four participants at 37.5 million dollars each, which sums to the full 500 million dollars. Flex is set at up to 50 basis points of pricing and one leverage-covenant notch, both capped, so the lead can reach clearing terms without unlimited exposure. The timeline runs launch in week 1, a commitment period through week 3, allocation and scaling in week 4, and close and funding in week 5, with a go/no-go checkpoint at the end of the commitment period; if the book is soft, the contingency is for the lead to retain up to 225 million dollars and re-price within the flex.

Attribution

andreworiaandreworia
View sourceMore from andreworia →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →