Credit Agreement Review logo

Credit Agreement Review

Organization
open-legal-products
credit-agreement-review

Review the uploaded credit agreement and produce a comprehensive table-based legal review from the perspective of the party represented by the user/client.

Overview

Publisheropen-legal-products
Repositorymike-workflows
Skill namecredit-agreement-review
Stars
91
Forks
43
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by open-legal-products on GitHub. Read the source before you install it.

Installation

Install the Credit Agreement Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/open-legal-products/mike-workflows/tree/main/assistant-workflows/credit-agreement-review
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/open-legal-products/mike-workflows.git /tmp/mike-workflows
mkdir -p .claude/skills
cp -r /tmp/mike-workflows/assistant-workflows/credit-agreement-review .claude/skills/credit-agreement-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Credit Agreement Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Credit Agreement Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Credit Agreement Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Credit Agreement Review

Instructions

Review the uploaded credit agreement and produce a comprehensive table-based legal review from the perspective of the party represented by the user/client. If the user has not already identified which party they represent, ask them to clarify that party before producing the review.

Once the represented party is clear, provide exactly one Markdown result table. Use one row for each material issue found in the agreement, guided by the review checklist below, and add a final row called Overall Risk Rating. The result table must have exactly these columns:

  • Issue
  • Summary
  • Recommended Change

Use these risk ratings inside the Summary column: Low means standard or minimal concern; Medium means a manageable negotiation concern; High means a material legal, commercial, operational, or enforceability concern requiring negotiation; Critical means a severe issue that may block signing unless resolved. Start each summary with the risk rating, e.g. "High — covenant headroom is tight".

The Summary column should include only the relevant points from the General checklist column and the party-specific checklist column for the represented party, together with clause or schedule references where available. Do not include issues that are adverse only to the other party unless they also create risk for the represented party. The Recommended Change column must be drafted from the represented party's perspective. Also flag general drafting errors that may affect the represented party, including inconsistent defined terms, inconsistent entity names, cross-reference errors, numbering issues, duplicated provisions, missing schedules, and internal inconsistencies. Keep the response concise and avoid long prose outside the table.

Result Table Format

Use this result table structure. Cite the relevant clause, section, schedule, or page directly in the Summary and Recommended Change columns. The example rows are illustrative only; tailor the actual rows to the uploaded agreement and represented party.

IssueSummaryRecommended Change
Financial CovenantsHigh — Clause [x] sets the leverage covenant at [x]x with quarterly testing and no equity cure right. The borrower-specific checklist point indicates limited headroom and no remedy for a technical breach.For the borrower, widen the covenant threshold, add an equity cure right, and reduce testing frequency to semi-annual.
Drafting ConsistencyMedium — Clauses [x] and [y] use inconsistent defined terms for the facility amount. The general drafting point indicates ambiguity that may affect the represented party's rights.For the represented party, align defined terms, amounts, and cross-references before signing.

Review Checklist

Use this checklist as guidance for what to review and flag. It is not the result-table template and should not be reproduced verbatim. For each checklist issue, consider both the General column and the party-specific column for the represented party (Borrower or Lender).

IssueGeneralBorrowerLender
PartiesIdentify all lenders, borrowers, guarantors, agents, and other finance parties with full legal names, roles, and jurisdictions. Flag missing or incorrect entities, unclear agent roles, missing authority confirmations, or transfer mechanics that could result in unknown lenders.
GuarantorsIdentify guarantors, guarantee scope, limits, and coverage requirements.Flag uncapped guarantees, missing limits, or upstream guarantee concerns exposing the borrower group.Flag weak guarantor coverage, missing entities, or guarantees not covering the full facility.
Other PartiesIdentify facility agent, security agent, arrangers, issuing banks, and other material parties.Flag unclear agent roles or mechanics creating additional obligations on the borrower.Flag inconsistent secured party mechanics or missing parties affecting security validity.
Date of AgreementState signing date, effective date, and conditions to effectiveness. Flag inconsistent or unclear dates or effectiveness conditions.
FacilitiesList each facility, type, tranche, availability, and key structural features.Flag excessive lender discretion, unclear facility purpose, or mismatched terms restricting drawdown.Flag unclear facility structure or purpose creating enforcement ambiguity.
AmountState total commitments, currencies, tranche amounts, and accordion or incremental facilities.Flag unclear currency exposure, uncapped accordion provisions without borrower consent, or inconsistent commitment figures.Flag uncapped increase mechanics or dilutive accordion provisions not agreed at signing.
PurposeSummarize permitted use of proceeds and restrictions.Flag vague purpose wording restricting flexibility or creating sanctions risk.Flag broad purpose language permitting restricted payment leakage or unapproved use of proceeds.
InterestIdentify reference rate, margin, floors, fallback rates, interest periods, and default interest.Flag high margins, aggressive floors, benchmark fallback gaps, or high default interest.Flag unclear fallback rate mechanics or interest calculation ambiguities.
Commitment FeeState commitment, utilisation, ticking, arrangement, agency, and other fees.Flag hidden fees, fees payable after cancellation, or unclear calculation basis.Flag missing fee provisions or fee timing delaying recovery.
Repayment ScheduleSummarize amortisation, scheduled repayments, bullet payments, and cash sweep.Flag aggressive amortisation, unclear prepayment application, or cash sweep uncertainty.Flag bullet repayments without adequate covenant or security protection.
MaturityState final maturity date and any extension options.Flag short maturity, lender-only extension discretion, or mismatch with the business plan.Flag unclear extension conditions or borrower-controlled extension mechanics.
SecurityIdentify security package, assets, entities, perfection steps, and post-closing obligations.Flag all-asset security beyond deal scope, onerous post-closing steps, or missing release mechanics on disposal.Flag gaps in the security package, missing perfection steps, or inadequate post-closing obligations.
GuaranteesSummarize guarantee obligations, guarantors, limitations, and release triggers.Flag broad all-monies language, unlimited guarantees, or no release mechanics after repayment or disposal.Flag guarantee gaps, weak limitations, or no coverage test requirements.
Financial CovenantsIdentify covenant metrics, thresholds, testing frequency, cure rights, and reporting.Flag tight headroom, frequent testing, no equity cure, or ambiguous EBITDA adjustments.Flag loose covenant thresholds or wide EBITDA adjustments obscuring true financial performance.
Events of DefaultSummarize default triggers, grace periods, materiality thresholds, cross-default, and MAE.Flag low materiality thresholds, no cure periods, broad cross-default, or subjective MAE defaults.Flag weak default triggers, long cure periods, or materiality thresholds delaying enforcement.
AssignmentSummarize lender transfer rights, borrower consent mechanics, and disqualified institutions.Flag free transfers to competitors, distressed investors, or lenders on a borrower blacklist.Flag consent mechanics giving the borrower excessive veto over lender transfers.
Change of ControlIdentify triggers and resulting prepayment, cancellation, or default consequences.Flag broad triggers, no cure period, or definitions catching ordinary-course ownership changes.Flag narrow change of control definitions missing material ownership shifts.
Prepayment FeeIdentify make-whole, soft-call, premium periods, and exceptions.Flag excessive fees, long premium periods, or unclear exceptions for mandatory prepayments.Flag exceptions allowing free prepayment during premium periods.
Governing Law and Dispute ResolutionState governing law, jurisdiction, forum, and service of process. Flag unclear or ambiguous governing law, jurisdiction, or service mechanics.

Deliver the review inline in your chat response. Do not generate a downloadable Word document unless the user explicitly asks for one.

Frequently asked questions

What does the Credit Agreement Review AI skill do?

Review the uploaded credit agreement and produce a comprehensive table-based legal review from the perspective of the party represented by the user/client.

Why use Credit Agreement Review on TypingMind?

Because you install it once and use it with any model. Credit Agreement Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Credit Agreement Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/open-legal-products/mike-workflows/tree/main/assistant-workflows/credit-agreement-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Credit Agreement Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Credit Agreement Review?

As many as you like. As long as a model supports skills, you can use Credit Agreement Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Credit Agreement Review AI skill free?

Yes. It is published on GitHub by open-legal-products under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇