agentleFS
tatashbartatashbar/Economic-Modeling-Studio/.agents/skills/build-climate-macro/SKILL.md

build-climate-macro

Skill4 starsChanged 6 days agoMITView on GitHub

Builds a climate-macro model: climate-augmented macro or integrated-assessment-style model with damage functions, abatement and carbon pricing.

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 27
  2. Very specific:

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

    line 29
  3. Distinctive:

    Run baseline and policy pathways.

    line 56
  4. Distinctive:

    After choosing the structure: confirm the horizon and questions

    line 63
  5. Distinctive:

    After specifying damages and discounting: confirm which alternatives to report

    line 64
  6. Distinctive:

    After baseline calibration: confirm the emissions baseline

    line 65

≈ “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/build-climate-macro/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

/build-climate-macro — Build Climate Macro

Category: Build · Primary agent: climate-macro-specialist

Builds a climate-macro model: climate-augmented macro or integrated-assessment-style model with damage functions, abatement and carbon pricing.

Arguments: whatever the user wrote after the command name.

Purpose

Build a model that connects climate and the macroeconomy: emissions from economic activity, damages from warming, abatement and its costs, carbon pricing and its revenue, and adaptation. The output is a model whose normative choices (damages, discounting) are explicit and varied, and whose results are presented as ranges that reflect deep uncertainty.

Use it when the question involves carbon pricing paths, the social cost of carbon, long-run damages, transition dynamics, or the macro and fiscal implications of climate scenarios.

Do not use it when the question is a near-term carbon-tax incidence or revenue estimate (/carbon-pricing-analysis), a scenario translation into an existing macro model (/climate-scenario), or sector-level detail without macro feedback (/build-io-sam).

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • Approved model-spec
    • Emissions and energy data
    • Damage-function evidence 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

  • climate-macro-specialist — primary agent; coordinates the work and integrates results
  • carbon-pricing-emissions-specialist — Analyzes carbon pricing and emissions policy
  • physical-climate-risk-specialist — Quantifies physical climate risk
  • transition-risk-energy-specialist — Analyzes energy systems and transition risk
  • economic-reasoning-specialist — Frames the economic question and tests whether results make economic sense

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
Model familyclimate-augmented DSGE, IAM (DICE-type), multi-sector, CGE-linkedHorizon, policy detail, uncertainty treatment
Damage functionquadratic level damages, growth damages, empirically estimated nonlinear, tipping pointsSize and timing of losses
DiscountingRamsey parameters, declining rates, descriptive versus prescriptivePresent value of damages and optimal carbon price
Energy detailaggregate emissions intensity, energy nest, explicit technologiesAbatement costs and transition dynamics
Uncertaintydeterministic scenarios, Monte Carlo over parameters, robust decisionHow uncertainty is reported

Workflow

  1. Choose the structure (climate-augmented DSGE, IAM-style, multi-sector, CGE-linked) with the user
    • Match the horizon and policy question to the family; state what the model cannot answer
  2. Specify emissions, abatement, damage and (if relevant) adaptation blocks; document discounting and damage-function choices
    • Label normative choices as such; keep alternatives ready to run
  3. Calibrate and test the model against historical emissions and energy intensity
    • Reconcile with national inventories and energy balances
  4. Run baseline and policy pathways; test sensitivity to damages, discounting and technology costs
    • Include orderly and delayed transition paths where relevant
  5. Report deep uncertainty as ranges and document limitations
    • Show results across damage functions and discount rates side by side
  6. Register the model as a lego set (/lego-map): a baseplate plus bricks with declared studs (variables, units, timing) and stubs, so components can later be attached, detached or swapped

Checkpoints with the user

  • After choosing the structure: confirm the horizon and questions
  • After specifying damages and discounting: confirm which alternatives to report
  • After baseline calibration: confirm the emissions baseline

Common pitfalls

  • A single damage function presented as fact
  • Discount rates chosen without stating their normative basis
  • Technology-cost assumptions anchored on outdated estimates
  • Mixing scenario sources with incompatible assumptions

Output

models/climate/<name>/ (+ model.lego.json)

The folder holds model code, calibration and emissions-baseline files, scenario scripts, the sensitivity pack across damages, discounting and technology costs, the limitations note and the lego manifest. Every run saves its results to output/<run-id>/ in the model folder, with a run log (.claude/rules/model-code.md).

Gate / verdict

  • Damage-function and discount-rate alternatives shown
  • Emissions accounting consistent with the baseline
  • Lego manifest passes python tools/lego.py check
  • Normative choices are labeled and alternatives reported side by side
  • Results are presented as ranges, not single paths

Suggested next steps

  • /climate-scenario
  • /carbon-pricing-analysis
  • /validate-model
  • /lego-map

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.