agentsclimarketplace
Sign in

Vendor risk playbook

Skill maxwellokumu/okaudit-claude-skills/vendor-risk/vendor-risk-playbook

Guide Claude through a structured third-party risk audit covering vendor inventory, tiering, assessment, contract review, ongoing monitoring, and reporting.From its SKILL.md

Install
npx -y skills add maxwellokumu/okaudit-claude-skills --skill vendor-risk-playbook

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.6 KB, 266 tokens by cl100k_base, as published. Nobody here has run it

Vendor Risk Playbook

Use this skill when the user needs a step-by-step vendor risk audit methodology or wants help sequencing third-party review activities.

Goal

Help Claude act like a third-party risk lead by breaking the review into manageable phases and keeping the work focused on inventory quality, risk tiering, assessment depth, contractual coverage, and monitoring.

Workflow

  1. Identify the vendor population, audit objective, and current stage of the review.
  2. Select the relevant playbook step such as inventory, tiering, assessment, contract review, monitoring, or reporting.
  3. Outline the activities, evidence, and stakeholders needed for that stage.
  4. Highlight common blind spots such as weak inventories, inconsistent tiering, shallow assessments, or missing contract protections.
  5. Return a concise next-step plan the user can apply immediately.

Inputs

Expected inputs from the bundled tool metadata:

  • step: Optional playbook step or phase to focus on.

Bundled Files

  • main.py contains the executable playbook helper.
  • README.md provides narrative guidance and examples.
  • skill.yaml captures the repo-native metadata for this skill.
  • sample_input may contain example prompts or stage definitions.

Guidance

Stay practical and risk-based. Connect vendor findings back to business dependency, contractual protection, ongoing assurance, and audit evidence needs.

What ships with it: 3 files

10.6 KB alongside SKILL.md, 1 of them executable

Gives 0 of the 12 instructions most operations skills give in 266 tokens

Counted across 483 of the 484 authors here whose files we hold, read 2026-08-07

  • Collect monitoring data throughout the simulationin 14 of 483, across 6 files
  • Set the random seed for reproducibilityin 14 of 483, across 6 files
  • Validate simulations against analytical solutionsin 12 of 483, across 4 files
  • Clarify goals, constraints, and inputsin 11 of 483, across 2 files
  • Implement contract tests for integration pointsin 11 of 483, across 2 files
  • Implement strangler fig infrastructure with API gatewayin 11 of 483, across 2 files
  • Audit modernized components for security vulnerabilitiesin 11 of 483, across 2 files
  • Avoid Python blocking calls in processesin 10 of 483, across 3 files
  • Use resource context managers for automatic cleanupin 9 of 483, across 2 files
  • Maintain consistent time unitsin 9 of 483, across 2 files
  • Validate outcomes against success criteriain 8 of 483, across 1 file
  • Analyze the legacy codebase for technical debtin 8 of 483, across 1 file

Said here and by no other author read

  • identify the vendor population and current review stage
  • select the relevant playbook step to focus on
  • outline activities evidence and stakeholders needed
  • highlight common blind spots in vendor reviews
  • return a concise next-step plan for the user
  • stay practical and risk-based throughout

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.