SkillAgentSearch skills...

enterprise-risk-management

An AI Agent Skill for Enterprise Risk Management (ERM) to identify Enterprise risks (Strategic, Operational, Financial), rate and rank the risks, develop risk control measures to mitigate the risks, and output a comprehensive Risk Register.

Install / Use

npx skills add wai-kwan/enterprise-risk-management

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

82/100

Supported Platforms

Universal

Tags

Our assessment of enterprise-risk-management

enterprise-risk-management scores 82/100 on our quality scale, 3225th of 4,717 Development & Engineering skills we index.

Its SKILL.md is 13 KB long, well organised into 28 sections with 4 code examples: a thorough specification that gives an agent plenty to work with.

It has 2 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
2/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 4 days ago, so enterprise-risk-management is actively maintained.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 92/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-18. Automated pattern scan on 2026-11-18. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

enterprise-risk-management compared with similar skills

All 4 of these similar skills score higher than enterprise-risk-management; compare them before choosing.

SkillScoreStarsUpdatedFormat
enterprise-risk-management (this skill)by wai-kwan8224d agoSKILL.md
taste-skillby Leonxlnx100118.3k10d agoCLAUDE.md
hyperframesby heygen-com10086.4ktodayCLAUDE.md
ai-job-searchby ai-job-search-dev10072.4ktodayCLAUDE.md
claude-howtoby luongnv8910047.4k4d agoCLAUDE.md

Frequently asked questions

How do I install enterprise-risk-management?
Run npx skills add wai-kwan/enterprise-risk-management. The install tabs above show the steps for each supported agent.
Which AI agents does enterprise-risk-management work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is enterprise-risk-management safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 92/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is enterprise-risk-management still maintained?
The repository was last updated 4 days ago, so enterprise-risk-management is actively maintained.

Enterprise Risk Management (ERM) AI Agent Skill

License: Apache-2.0
Specification: agentskills.io framework compatible
Author: wai-kwan (https://github.com/wai-kwan)

An AI agent skill optimized for conducting structured enterprise risk assessment and profiling. Built using the open agentskills.io specification, this skill enables coding assistants and workspace LLM models to analyze corporate text assets and output an analytical, Excel-ready risk_register.csv file.

It works in two modes:

  • Generation Mode: identifies N new risks from a project, scenario or company profile and builds a complete register.
  • Completion Mode: takes a risk register you have only partly filled in, in any layout, or a plain list of risks, and completes it, keeping your own values.

The AI agent can also use two companion skills alongside it: risk-discovery to discover risks through a facilitated workshop or interview, and kri to create Key Risk Indicators for the risks in the register (see Companion Skills).


Key Framework Capabilities

  • Context-Aware Scoping: Dynamically identifies N unique risks based on a project, scenario, or provided company profile context.

  • Granular Multi-Scope Sorting: Supports isolated or blended evaluation runs across Strategic, Operational, Financial, and Enterprise categories. The 'Enterprise' option will encompass a balanced mix of top Strategic, Operational, and Financial risks.

  • Focused Cause-and-Effect Analysis: Identifies 2 to 3 distinct, material Causes and 2 to 3 Effects for each risk, choosing the most important ones without padding. Each Cause is a root driver specific enough to design a preventive control for.

  • Strict Analytical Score-Coupling: Likelihood is rated strictly from the Causes and Impact strictly from the Effects, which prevents arbitrary scores and model logic drift.

  • Dual-Action Controls Engine: Generates specific Preventive actions to break risk drivers, and Reductive actions to soften actual business impacts.

  • Register Completion: Fills the gaps in a partial or non-standard register, so you can start from the risks you already know.

  • Spreadsheet-Safe Data Generation: Formats the risk register into a comprehensive 14-column schema in a standard CSV file layout featuring the following explicit headers:

    | Column Name | Description / Values | | :--- | :--- | | Risk ID | Sequential identifier (R1, R2, ..., RN), or your own IDs in Completion Mode | | Category | Strategic, Operational, or Financial | | Risk Title | Concise, risk-perspective name for the risk | | Description | Single-sentence description of the risk | | Causes (Drivers) | 2 to 3 specific root catalysts | | Effects (Consequences) | 2 to 3 specific downstream impacts | | Likelihood Scale (1-5) | Numerical probability rating integer 1-5 | | Likelihood | Qualitative text definition (Rare to Almost-Certain) | | Impact Scale (1-5) | Numerical severity rating integer 1-5 | | Impact | Qualitative text definition (Insignificant to Severe) | | Risk Score | Mathematical product of Likelihood Scale × Impact Scale | | Risk Criticality | Risk threshold text tag (CRITICAL, HIGH, MODERATE, LOW) | | Preventive Controls | Risk control measures breaking root drivers, at least one per Cause | | Reductive Controls | Risk control measures minimizing consequences, at least one per Effect |


Risk Assessment Framework

Each identified risk is evaluated dynamically against its explicit qualitative drivers and consequence outcomes using standard, structured Enterprise Risk Management methodology.

Causes and Effects

Each risk gets 2 to 3 Causes and 2 to 3 Effects, never more than 3. The skill picks the most important ones and stops when further items would overlap or be minor. A risk that genuinely has a single cause or effect keeps just one rather than being padded with near duplicates.

Likelihood Scale

Likelihood is assessed based on the mathematical probability of the underlying Causes materializing:

  • 1 = Rare
  • 2 = Unlikely
  • 3 = Possible
  • 4 = Likely
  • 5 = Almost certain

Impact Scale

Impact is assessed based on the direct severity of the downstream Effects if the risk event occurs:

  • 1 = Insignificant
  • 2 = Low
  • 3 = Moderate
  • 4 = High
  • 5 = Severe

Risk Criticality Matrix

Calculated automatically via the formula: (\text{Risk Score} = \text{Likelihood (1-5)} \times \text{Impact (1-5)}).

The tool maps boundaries into four clear text-only risk classification tags optimized for seamless spreadsheet sorting and data filtration:

  • CRITICAL (Risk Scores 20 to 25)
  • HIGH (Risk Scores 10 to 19)
  • MODERATE (Risk Scores 5 to 9)
  • LOW (Risk Scores 1 to 4)

The register is sorted from the highest Risk Score to the lowest (ties: higher Impact first).

Tip: Open risk_register.csv in Microsoft Excel, select your Risk Criticality column, and navigate to Home -> Conditional Formatting -> Highlight Cells Rules -> Equal To... to instantly apply custom corporate background highlight fills to the tags.

Risk Controls

To ensure comprehensive governance coverage, a dual-action set of Preventive and Reductive risk control measures are generated for every single risk item: at least one Preventive Control for each Cause, and at least one Reductive Control for each Effect.


Required Configuration Parameters (Generation Mode)

Before processing, the AI agent evaluates the user prompt for three core parameters:

  1. Number of Risks (N): Defaults to 10 risks if unspecified.
  2. Risk Category Filter: Filters strictly by Strategic, Operational, Financial, or Enterprise (default). The 'Enterprise' option will encompass a balanced mix of top Strategic, Operational, and Financial risks.
  3. Risk Context Validation: Expects a clear operational context (project brief, timeline, scenario, or company profile). If the context is ambiguous, the agent will pause and prompt the user for clarification before executing.

The output is saved as risk_register.csv in the workspace directory. If a file of that name already exists, the skill asks before replacing it, and otherwise saves the new register as risk_register_2.csv (or the next unused number).


Completion Mode: Completing Your Own Register

Give the skill a register you have started, whether it is a CSV or spreadsheet, a pasted table, or just a list of risks, and it fills in the rest in the standard 14-column format.

Your values always win.

  • Your words are never reworded, shortened, reordered or removed. Only empty fields are filled.
  • If you gave only one Cause or Effect, the skill keeps yours first and adds one more to reach the minimum of 2 (up to 3 only if you ask it to enrich the register). Each added Cause or Effect gets a matching control.
  • Formatting is made spreadsheet safe without changing any words: list markers such as -, • or 1. become *.

Flexible input.

  • Columns are matched by meaning, not exact header: "Risk Name" is read as the Risk Title, "Root cause" as Causes, "Probability" as Likelihood, and so on.
  • Text ratings are converted to numbers ("Likely" becomes 4, "Medium" becomes 3).
  • Columns that do not belong in the register (such as Owner or Status) are left out, and the skill tells you which.
  • The only requirement is a Risk Title or a Description for each risk.

Consistent scoring. Risk Score and Risk Criticality are always recalculated from the final Likelihood and Impact. If this changes a score you supplied, the skill flags it.

Your IDs are kept. Rows are sorted by score, but your own Risk IDs stay as they are so your references remain valid. IDs are assigned only where none were given.

Your file is never changed. The completed register is saved next to your input with _completed added to the name, for example Q3_risks.xlsx becomes Q3_risks_completed.csv. Pasted input is saved as risk_register_completed.csv.

A clear report. A CSV cannot show which values were yours and which were generated, so the skill ends with a short report: for each risk, which fields it generated or topped up, plus every conversion, recalculation, formatting fix and dropped column. Generated ratings and controls are proposals for the risk owner to review.

Example

Input:

Risk,Root cause,Likelihood,Owner
Loss of our sole supplier disrupting production,Single source contract,Likely,Head of Procurement
Key engineers leaving during the product launch,,,

The skill keeps "Single source contract" as the first Cause of the first risk and adds a second, converts "Likely" to 4, generates every other field with 2 to 3 Causes and Effects per risk, sorts the risks by score, assigns R1 and R2, and reports that the Owner column was not carried over.


Companion Skills

ERM is the foundation of a family of risk management skills that share the same 14-column register format. When they are installed, the AI agent can use them alongside ERM to discover risks and create KRIs:

| Skill | What the AI agent uses it for | |---|---| | risk-discovery | Discover risks through a facilitated, time-boxed workshop or interview, drawing out the participants' own top risks into an ERM format register. A session can be handed over to ERM to complete the register | | kri | Create Key Risk Indicators with Green, Amber and Red thresholds for the risks in the register, calling ERM to fill in a register that is missing information |

A typical flow: discover risks with risk-discovery, complete and rate them with ERM, then create KRIs with kri to monitor them. ERM suggests risk-discovery when you want to find risks with your team, and offers kri after producing or completing a register. If a companion is not installed, it gives you the link.


Installation & Setup

Place the erm skill folder into your active local workspace or global agent configurations directory. As the agentskills.io specification requires, SKILL.md sits at the top of the folder and the folder name (erm) matches the skill name.

Workspace Setup (Local Repo)

To activate this skill automatically inside your specific project workspace, copy the folder footprint like so:

your-project-repository/
└── .github/
    └── skills/
        └── erm/
            └── SKILL.md

Other agents load skills from their own folders (for example .claude/skills/erm/ for Claude Code), so use the location your agent expects.

Direct CLI Installation (When using tools like agentskills CLI)

npx skills add wai-kwan/enterprise-risk-management

Claude (claude.ai)

Download the packaged erm.skill file from this repository and upload it under Settings, Capabilities, Skills, or use the Save skill button on the file card.

Recommended companions

npx skills add wai-kwan/risk-discovery
npx skills add wai-kwan/key-risk-indicator

Usage Guide & Prompt Triggers

Once the skill folder is added to your environment workspace, ask in plain language or reference the slash command /erm.

Generation Mode

1. Default Blended Evaluation

"Run /erm across our recent project architecture documentation to find 10 risks."

2. Tailored Operational Run

"Analyze our business plan using the erm skill. Identify 5 operational risks to audit our security and business continuity vectors."

3. Strategic Fiscal Run

"Using /erm, evaluate our compliance files to extract 8 financial risks."

Completion Mode

4. Complete

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars2
CategoryDevelopment
Updated4d ago
Forks0

Trust signals

92/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low