agentleFS
tatashbartatashbar/Economic-Modeling-Studio/.agents/skills/debt-sustainability/SKILL.md

debt-sustainability

Skill4 starsChanged 6 days agoMITView on GitHub

Runs debt sustainability analysis: baseline, shocks, stochastic fan charts, realism checks and financing needs.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

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

    line 26
  2. Very specific:

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

    line 28
  3. Distinctive:

    Run realism checks vs. history and peers

    line 53
  4. Distinctive:

    Write the risk assessment with explicit limits

    line 56
  5. Distinctive:

    After the baseline: confirm macro and fiscal assumptions

    line 59
  6. Distinctive:

    After stress tests: confirm tailored shocks capture country risks

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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/debt-sustainability/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

/debt-sustainability — Debt Sustainability

Category: Analysis · Primary agent: debt-sustainability-analyst

Runs debt sustainability analysis: baseline, shocks, stochastic fan charts, realism checks and financing needs.

Arguments: whatever the user wrote after the command name.

Purpose

Run a debt sustainability analysis: a baseline whose debt dynamics decompose exactly into primary balance, interest, growth, inflation, exchange-rate and stock-flow effects; standardized and tailored stress tests; stochastic fan charts; realism checks; and an assessment of financing needs and debt-structure risks. The output is a sustainability judgment stated in probabilistic terms with its limits.

Use it when public or external debt must be assessed for a budget, program, risk statement or restructuring discussion.

Do not use it when a structural default model is needed for spreads and crisis zones (/build-game-model), or the full macro framework is missing (/build-financial-programming).

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • Fiscal and macro baseline
    • Debt composition data 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

  • debt-sustainability-analyst — primary agent; coordinates the work and integrates results
  • fiscal-risk-specialist — Assesses fiscal risks
  • sovereign-crisis-games-specialist — Models sovereign debt, default and currency crises
  • revenue-tax-policy-specialist — Forecasts and analyzes tax revenue
  • extractives-natural-resources-specialist — Analyzes resource-rich economies

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
Coveragecentral government, general government, plus SOEs and guaranteesMeasured debt and risks
Frameworkmarket-access framework, low-income-country frameworkIndicators and thresholds
Stochastic methodVAR-based shocks, bootstrapped historyFan-chart width
Tailored shockscontingent liabilities, disasters, commodity pricesCountry-specific risks
Horizon5, 10 years or longerVisibility of long-run pressures

Workflow

  1. Build the baseline and verify the debt-dynamics decomposition
    • State coverage; include stock-flow adjustments explicitly
  2. Apply standardized and tailored shocks; run stochastic simulations
    • Include combined shocks and contingent-liability realizations
  3. Run realism checks vs. history and peers
    • Fiscal adjustment against historical distributions; growth–adjustment consistency with multipliers
  4. Assess financing needs, contingent liabilities and rollover risk
  5. Write the risk assessment with explicit limits

Checkpoints with the user

  • After the baseline: confirm macro and fiscal assumptions
  • After stress tests: confirm tailored shocks capture country risks

Common pitfalls

  • Optimistic baselines with large adjustment and unchanged growth
  • Narrow coverage missing SOEs and guarantees
  • Ignoring exchange-rate valuation
  • Fan charts from calm periods only

Output

forecasts/dsa/<country>-<date>.md

The report presents the baseline and decomposition, stress tests, fan charts, realism checks, financing needs and the risk assessment with limits.

Gate / verdict

  • Decomposition closes exactly
  • Realism checks documented
  • Coverage is stated and contingent liabilities are stress-tested
  • The judgment states its probability basis

Suggested next steps

  • /policy-brief
  • /team-fiscal

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.