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

Compliance

ASecurity

Builds a compliance checklist covering information barriers and conflicts of interest so a deal process respects the firm's information and conflict rules.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Compliance?

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

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

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

Download with Pro
Files
SKILL.md
---
name: compliance
description: Builds a compliance checklist covering information barriers and conflicts of interest so a deal process respects the firm's information and conflict rules.
---

# Compliance Agent

## When to use
Use this agent when a process must respect information and conflict rules: a new mandate is being taken on, a live deal is moving material non-public information between teams, or a wall-crossing is being contemplated. Reach for it before sharing sensitive data across desks or engaging a new counterparty. It is meant to be run early and refreshed whenever scope or parties change.

## What it does
Produces a compliance checklist covering information barriers and conflicts, with explicit control steps and named sign-offs, so the deal team can evidence that information and conflict rules were respected.

## Method
1. Scope the mandate: capture the client, the transaction type, the deal codename, and which internal teams need access.
   - Record the value at stake and the expected timeline, since both affect sensitivity and listing status.
   - Common pitfall: scoping too broadly and putting more people over the wall than the work requires.

2. Map information barriers between the public side and the private side.
   - Define who is above the wall, and set need-to-know as the default rather than the exception.
   - Document the wall-crossing procedure: who requests a crossing, who approves it, and how each crossing is logged with a name and timestamp.

3. Build the restricted and watch lists.
   - Add the target and any listed counterparties to the restricted list, and note research and proprietary-trading restrictions.
   - Set a review date so entries do not linger after the deal is public or dead.

4. Run conflict checks across the firm.
   - Screen for prior or current mandates with the same parties, cross-holdings by the firm or affiliated funds, personal-account dealing by team members, and any advisory role on the other side of the table.
   - What good looks like: a documented search, not a memory check.

5. Classify each conflict as clear, manageable with controls, or blocking.
   - For manageable conflicts, specify the control, for example a separate deal team, an information barrier, or an independent adviser.
   - A blocking conflict stops the mandate until resolved; do not paper over it.

6. Set information-handling rules for the whole team.
   - Cover naming conventions, secure data-room access, distribution controls, and clean-desk expectations.
   - Note how draft materials are stored and who may forward them externally.

7. Assign sign-offs to close the loop.
   - Route the checklist to the control room or compliance officer, the deal lead, and the supervising principal, each with a name and date.
   - Do not treat the checklist as complete until every sign-off is captured.

8. Set a review cadence and trigger conditions.
   - Refresh the checklist when scope, parties, or listing status changes, and re-run conflict checks before any new counterparty is contacted.

## Inputs
- Client name, transaction type, and deal codename
- The list of internal teams and individuals who need access
- Known related parties, counterparties, and any listed entities
- Any existing or prior firm mandates involving the same parties
- Firm holdings or affiliated-fund positions in relevant names
- The name of the compliance or control room contact

## Output format
Claude returns a titled checklist with these sections:
- Information barriers: each control as a line item with a status marker and an owner, covering the public/private split, the wall-crossing log, and need-to-know scope.
- Conflicts: each identified conflict described in prose, naming the party, the nature of the conflict, the classification, and the mitigating control.
- Information handling: naming, access, and distribution rules as line items.
- Sign-offs: each required approver by role with a blank for name and date.
- Residual-risk note: a short closing statement on what remains after controls.

## Example
Northwind Logistics has engaged the bank to advise on the sale of its cold-chain division. Information barriers: deal codename "Project Frost" set, with the private side limited to four named bankers and the wall-crossing of one sector analyst requested and logged with compliance sign-off. Restricted list: Northwind added, research and proprietary trading restricted, review date set for the announcement window. Conflict check: the firm advised a rival bidder eighteen months ago on an unrelated matter, classified manageable with a separate deal team; an affiliated fund holds a small stake in a listed logistics peer, classified clear after review. Sign-offs remain pending from the control room officer, the deal lead, and the supervising managing director, and the residual note flags the affiliated-fund position for monitoring through close.

Attribution

andreworiaandreworia
View sourceMore from andreworia →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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".

1066601 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.

651 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 →