agentleFS
tatashbartatashbar/Economic-Modeling-Studio/.agents/skills/stress-test/SKILL.md

stress-test

Skill4 starsChanged 6 days agoMITView on GitHub

Runs macro-financial stress tests: scenario design, satellite models, bank and sector results, policy implications.

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ai-act-readiness, c-level-agents and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not use it when: only macro scenarios are needed without financial-sector mapping (/scenario-analysis).

    line 20
  2. Very specific:

    If a required input is ABSENT, that part is NOT ASSESSED — NO DATA: do not estimate or invent it.

    line 26
  3. Very specific:

    Collaboration: Follow .claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and …

    line 28
  4. Distinctive:

    After scenario design: confirm severity

    line 56
  5. Distinctive:

    After results: confirm policy implications

    line 57

“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from .claude/skills/stress-test/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

/stress-test — Stress Test

Category: Analysis · Primary agent: financial-stability-stress-testing-specialist

Runs macro-financial stress tests: scenario design, satellite models, bank and sector results, policy implications.

Arguments: whatever the user wrote after the command name.

Purpose

Run a macro-financial stress test: design severe but plausible scenarios calibrated to history and current vulnerabilities, map them to credit losses, income and funding pressures through validated satellite models, compute capital and liquidity outcomes including second-round effects, and draw policy implications. The output identifies vulnerabilities and capital or liquidity shortfalls with their sensitivity to assumptions.

Use it when assessing resilience of banks, non-banks or the financial system, or the fiscal implications of financial stress.

Do not use it when only macro scenarios are needed without financial-sector mapping (/scenario-analysis).

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • Balance-sheet data
    • Macro scenarios If a required input is ABSENT, that part is NOT ASSESSED — NO DATA: do not estimate or invent it; name what is missing and which skill produces it. If all required inputs are absent, stop and say so.
  2. Check confidentiality. Identify the data classification level of the inputs (.claude/docs/confidentiality-and-ai-use.md). Do not proceed with restricted or confidential data in a way the policy does not allow.
  3. Collaboration. Follow .claude/docs/collaboration-protocol.md: ask questions first, present options, get approval before writing files, and update production/session-state/active.md after each approved section.

Agents

  • financial-stability-stress-testing-specialist — primary agent; coordinates the work and integrates results
  • macroprudential-housing-specialist — Analyzes macroprudential policy and housing/credit cycles
  • scenario-risk-analysis-specialist — Designs scenarios and risk assessments
  • banking-credit-specialist — Models banks and credit markets

Each agent is defined in .claude/agents/<name>.md. If your tool runs subagents, run these agents as subagents, in parallel where the steps are independent; otherwise read each agent's file and apply its instructions in turn. Subagents only write to the paths named in your instructions.

Key design decisions (present options, let the user choose)

DecisionTypical optionsWhat it changes
Scenario severityhistorical analogues, statistical percentiles, reverse stressCredibility
Coveragelargest banks, all banks, non-banksSystem view
Balance sheetstatic, dynamicInterpretation
Channelscredit, market, funding, contagion, fire salesCompleteness
Horizon1–3 yearsLoss accumulation

Workflow

  1. Design severity-calibrated scenarios and document the calibration
  2. Map to risk drivers with validated satellite models
    • Validate satellites out of sample on historical losses
  3. Compute losses, capital and liquidity outcomes with second-round effects
    • Interbank and common-exposure contagion; fire sales where relevant
  4. Report vulnerabilities and policy responses

Checkpoints with the user

  • After scenario design: confirm severity
  • After results: confirm policy implications

Common pitfalls

  • Scenarios milder than past crises
  • Static balance sheets read as forecasts
  • Ignoring liquidity–solvency interactions
  • Second-round effects omitted without flag

Output

forecasts/stress-tests/<name>.md

The report covers scenario calibration, satellite models and validation, losses and capital and liquidity outcomes by institution or sector, second-round effects, and policy implications.

Gate / verdict

  • Severity calibrated; satellite models validated
  • Balance-sheet assumptions are stated
  • Second-round effects are estimated or their omission is flagged

Suggested next steps

  • /policy-brief
  • /team-stress-test

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.