agentleFS
tatashbartatashbar/Economic-Modeling-Studio/.agents/skills/distributional-analysis/SKILL.md

distributional-analysis

Skill4 starsChanged 6 days agoMITView on GitHub

Analyzes distributional effects of a policy or shock using microsimulation, HANK links or survey-based incidence.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Use consumption baskets for price effects.

    line 49
  4. Distinctive:

    After defining groups and welfare: confirm before computation

    line 56
  5. Distinctive:

    After results: confirm compensation options to cost

    line 57

≈ “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/distributional-analysis/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

/distributional-analysis — Distributional Analysis

Category: Analysis · Primary agent: inequality-distribution-specialist

Analyzes distributional effects of a policy or shock using microsimulation, HANK links or survey-based incidence.

Arguments: whatever the user wrote after the command name.

Purpose

Analyze how a policy or shock affects different households: who gains, who loses, by how much, and what happens to poverty and inequality. Macro or sector results are mapped to households through income, price and employment channels, using microsimulation, survey-based incidence or links to heterogeneous-agent models. The output reports results with sampling uncertainty and costs compensation options.

Use it when tax, subsidy, transfer, carbon-pricing, inflation or other shocks have distributional consequences that matter for the decision.

Do not use it when a full heterogeneous-agent macro model is required for transmission (/build-hank).

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • Household survey data
    • Macro scenario 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

  • inequality-distribution-specialist — primary agent; coordinates the work and integrates results
  • tax-benefit-microsimulation-specialist — Builds tax-benefit microsimulation
  • hank-specialist — Builds heterogeneous-agent (HANK) models
  • survey-microdata-specialist — Works with household and firm survey microdata

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
Welfare measureincome, consumption, real purchasing powerRanking of households
Methodstatic incidence, behavioral microsimulation, macro–micro link, HANKChannels captured
Groupsdeciles, regions, urban/rural, gender, household typeWhat is reported
Poverty linenational, international, relativePoverty results

Workflow

  1. Define groups and welfare measure (income, consumption, real purchasing power)
  2. Map macro changes to households; include price and employment channels
    • Use consumption baskets for price effects; income sources for wage and transfer effects
  3. Compute winners/losers, poverty and inequality changes with sampling uncertainty
    • Design-based standard errors; sensitivity to the poverty line
  4. Propose compensation or mitigation options and their cost
    • Targeting performance: coverage and leakage

Checkpoints with the user

  • After defining groups and welfare: confirm before computation
  • After results: confirm compensation options to cost

Common pitfalls

  • Ignoring survey design in standard errors
  • Averages that hide large losses for some groups
  • Assuming full take-up of compensation
  • Ignoring under-coverage of top incomes

Output

forecasts/distribution/<name>.md

The report presents the method, groups, winners and losers, poverty and inequality effects with uncertainty, and compensation options with costs.

Gate / verdict

  • Sampling uncertainty reported
  • Gains and losses are shown separately
  • Compensation options are costed

Suggested next steps

  • /policy-brief
  • /chart-pack

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.