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

climate-scenario

Skill4 starsChanged 6 days agoMITView on GitHub

Runs climate and transition scenarios: translating climate pathways to macro, fiscal and financial impacts.

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:

    Run physical and transition channels separately and jointly

    line 52
  4. Distinctive:

    After mapping: confirm pathway sources and translations

    line 58
  5. Distinctive:

    After results: confirm ranges and how they will be communicated

    line 59

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

/climate-scenario — Climate Scenario

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

Runs climate and transition scenarios: translating climate pathways to macro, fiscal and financial impacts.

Arguments: whatever the user wrote after the command name.

Purpose

Translate climate pathways (orderly, delayed or disorderly transitions; higher or lower warming) into macro, fiscal and financial impacts for a country, running physical-risk and transition-risk channels separately and together. The output is a set of conditional scenarios with deep-uncertainty ranges and explicit damage and discounting alternatives.

Use it when climate scenarios are needed for projections, fiscal-risk statements, financial stress tests or adaptation planning.

Do not use it when a new climate-macro model must be built (/build-climate-macro) or a carbon-pricing design is the question (/carbon-pricing-analysis).

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • Climate scenario data
    • Macro model 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
  • transition-risk-energy-specialist — Analyzes energy systems and transition risk
  • fragility-disaster-specialist — Analyzes fragility, conflict, pandemics and natural disasters
  • fiscal-risk-specialist — Assesses fiscal risks
  • carbon-pricing-emissions-specialist — Analyzes carbon pricing and emissions policy
  • physical-climate-risk-specialist — Quantifies physical climate risk

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
Pathwayspublished scenario sets, customComparability and consistency
Channelsphysical, transition, bothCoverage of risks
Modelsmacro model with climate bricks, CGE, sector modelsChannel detail
Damageslevel, growth, hazard-basedSize of physical losses
Horizonto 2030, 2050, 2100Relevance of each channel

Workflow

  1. Select pathway assumptions and map them to macro drivers
    • Carbon prices, energy prices, productivity, investment, hazard frequencies
  2. Run physical and transition channels separately and jointly
  3. Report impacts with deep-uncertainty ranges; show damage-function alternatives
  4. Summarize fiscal and financial implications and adaptation needs
    • Feed results into fiscal-risk and stress-test work where relevant (/stress-test)

Checkpoints with the user

  • After mapping: confirm pathway sources and translations
  • After results: confirm ranges and how they will be communicated

Common pitfalls

  • Mixing scenario sources with incompatible assumptions
  • Single damage function presented as fact
  • Long-run damages treated as short-run shocks
  • Ignoring transition inflation and investment

Output

forecasts/climate/<name>.md

The report documents pathway translations, separate and joint channel results, uncertainty ranges, damage alternatives and fiscal and financial implications.

Gate / verdict

  • Alternatives to damage function and discount rate shown
  • Physical and transition channels are reported separately and jointly
  • Pathway translations are documented

Suggested next steps

  • /policy-brief
  • /distributional-analysis

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.