Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    disruption scenario stress tester

    1

    - **Exposure analysis** maps correlated group risks to find which specific cohorts (e.g., shared transport or ward teams) create the highest vulnerability.

    $2.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    disruption scenario stress tester

    disruption scenario stress tester

    Example session with this skill installed

    Run a stress test on the attached March roster. We need to test a scenario where the 'Blue Team' transport group is 100% absent on March 12th due to the planned strike. Use a 75% coverage floor.

    • Read your context and instructions
    • Compiled the disruption scenario stress

    I have processed the March roster against the transport strike scenario for the 'Blue Team' group. The analysis used the labor rules and shift templates provided in your records.

    Disruption Scenario Stress Test — Logistics North, 2024-03-12

    1. Scope, sources and assumptions

    • Sources: March Roster (E1), Labor Agreement 2023 (E2), Staff Records (E3).
    • Horizon: 2024-03-12 to 2024-03-13.
    • Labor Limits: 11h min rest, 48h max weekly (Source: E2).
    • Assumptions: 100% absence for group 'Blue Team' on 2024-03-12 (User assertion).

    2. Scenario results

    ScenarioRequiredShortfallCoverage beforeMeets floorCoverage after coverMeets floor afterResidual lower bound
    Baseline4001.0000Yes1.0000Yes0
    Blue Strike40120.7000No0.8500Yes6

    3. Shortfalls and proposed cover (drafts)

    On 2024-03-12, Shift 'NIGHT' at Site 'A' shows a shortfall of 8.

    • Proposed Cover: EMP_082, EMP_091, EMP_104.
    • Residual: 5 (Site 'A' remains below optimal staffing).

    4. Correlated-group exposure

    GroupMembersShortfallCoverage
    Blue Team15120.7000
    Red Team1201.0000

    The 'Blue Team' represents the largest operational exposure due to concentrated roles in the Night shift.

    5. Rule checks on the supplied roster

    No rest or weekly-hour violations found in the baseline roster.

    6. Warnings and exclusions

    • Warning W04: 3 staff members excluded due to missing cover_consent.
    • Exclusions: 5 records outside of access_scope.sites.

    7. Items for human review

    • Computed result: The 0.70 coverage ratio fails the 0.75 floor requirement.
    • Analytical estimate — validation required: Proposed cover relies on EMP_091 who has a preference for Day shifts.
    • Management decision required: Approval needed for 3 draft assignments to clear the coverage floor.

    This analysis supports, and does not replace, supervisor judgment and management's decision.

    Next steps

    1. Review the draft cover assignments for EMP_082 and EMP_104.
    2. Verify if additional staff from 'Red Team' can provide cross-site support.
    3. Confirm if the 75% coverage floor is acceptable for an emergency strike scenario.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Manual roster checking is a recipe for disaster when multiple disruptions hit at once. This skill stress-tests existing schedules against correlated absences, demand surges, and site outages using a deterministic script to identify single points of failure before they manifest.

    What it does

    • Scenario execution runs deterministic scripts to test rosters against flu waves, transport failures, or site closures.
    • Shortfall reporting identifies specific site, date, shift, and role combinations where staffing falls below the required floor.
    • Exposure analysis maps correlated group risks to find which specific cohorts (e.g., shared transport or ward teams) create the highest vulnerability.
    • Draft cover generation identifies qualified, consenting staff to fill gaps while respecting rest and weekly-hour limits.
    • Compliance checking flags rest period violations and weekly-hour overages in both the baseline roster and proposed cover.

    How it works

    1. Register sources by indexing all provided shift templates, labor rules, and staff records as evidence pointers.
    2. Build request by mapping your roster and staff data into a structured request.json file.
    3. Run simulation via the scripts/run.py engine to calculate coverage ratios and shortfall counts without manual estimation.
    4. Analyze results by reviewing the status envelope for warnings, rule violations, and residual lower bounds.
    5. Generate report following the mandatory seven-section structure to present data, group exposures, and items for human review.

    Frameworks & tools

    The skill utilizes a custom Python-based calculation engine (scripts/run.py) and validates data against strict JSON schemas for labor rules and employee records.

    Why this beats prompting it yourself

    Generic prompts often hallucinate coverage ratios or ignore complex rest-period overlaps. This skill uses a deterministic script to ensure every calculation is grounded in your specific labor rules and employee consent data.

    Use cases

    • Pandemic planning to see how a 20% absence rate across a specific transport group affects night shift coverage.
    • Demand surge testing to determine if current staffing levels can handle a 50% increase in site activity.
    • Infrastructure failure analysis to assess the impact of a specific site closure on the remaining network.
    • Vulnerability auditing to identify which staff cohorts represent a single point of failure for the organization.

    Known limitations

    Does not optimize rosters or build them from scratch. Cannot forecast absence probabilities or provide legal compliance certification. Only processes staff who have explicitly provided cover consent.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Does not build/optimize rosters. No forecasting or probability modeling. Requires explicit labor rules and employee consent data. Only handles operational groups, not protected attributes.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 2 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed2 days ago

    What's inside

    Frequently Asked Questions

    Unlike LLMs that might guess coverage, this skill uses a deterministic Python-based engine to verify every shift against your specific labor rules, ensuring no hallucinated coverage or missed rest-period violations.

    The skill requires three structured JSON files: your current roster/shift templates, your organization's labor rules (e.g., rest periods, hour limits), and staff records including their qualifications and cover consent.

    No, this is a diagnostic and resilience tool; it identifies gaps and suggests available staff to fill them, but it does not generate initial schedules or perform automated roster optimization.

    The package includes the `scripts/run.py` calculation engine, the mandatory JSON schemas for data mapping, and the reporting framework that generates the final seven-section exposure analysis.

    The skill is designed for any AI agent capable of executing Python scripts and handling JSON data structures, making it compatible with most advanced orchestration platforms and developer-tier agents.

    It identifies staff cohorts that share common risks—such as the same transport route or ward team—to reveal if a single localized incident could cause a total operational collapse.