agentleFS
tatashbartatashbar/Economic-Modeling-Studio/.agents/skills/data-requirements/SKILL.md

data-requirements

Skill4 starsChanged 6 days agoMITView on GitHub

Defines data requirements and checks availability, vintages, confidentiality classification and quality for a model.

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 25
  2. Very specific:

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

    line 27
  3. Distinctive:

    Check availability and source.

    line 48
  4. Distinctive:

    After the list: confirm observables and samples

    line 55
  5. Distinctive:

    After quality review: confirm proposed treatments

    line 56
  6. Distinctive:

    No plan for vintages

    line 62

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

/data-requirements — Data Requirements

Category: Scoping & Design · Primary agent: data-engineer

Defines data requirements and checks availability, vintages, confidentiality classification and quality for a model.

Arguments: whatever the user wrote after the command name.

Purpose

Define what data a model needs and check, series by series, whether they exist, where they come from, what they mean, how reliable they are, and how confidential they are. The output is a data sheet and a pipeline plan that prevent late surprises: missing series, mismatched concepts, short samples or data that cannot legally be used.

Use it when a model is scoped and its observables and calibration targets are known, or an existing model moves to a new country.

Do not use it when the data pipeline already exists and only needs refreshing.

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • docs/models/<name>/model-spec.md 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

  • data-engineer — primary agent; coordinates the work and integrates results
  • national-accounts-specialist — Specializes in national accounts and macro statistics
  • data-governance-metadata-specialist — Owns data governance and metadata
  • 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
Sourcesnational statistics, international databases, private dataCoverage, cost, licensing
Frequencyannual, quarterly, monthlyModel design
Samplefull history, post-breakEstimation reliability
Treatmentsseasonal adjustment, splicing, interpolationData quality

Workflow

  1. List the observables, frequency, sample and concept for each series
    • Match each concept to the model variable definition
  2. Check availability and source; classify confidentiality class
    • Record licenses and redistribution rights
  3. Assess quality (revisions, breaks, seasonality) and propose treatments
  4. Produce a data sheet and pipeline plan
    • Note vintages needed for real-time evaluation

Checkpoints with the user

  • After the list: confirm observables and samples
  • After quality review: confirm proposed treatments

Common pitfalls

  • Concepts that differ from model definitions (cash versus accrual, gross versus net)
  • Licenses checked too late
  • Ignoring breaks and rebasing
  • No plan for vintages

Output

docs/models/<name>/data-sheet.md

The data sheet lists each series with definition, source, frequency, sample, classification, license, quality notes and proposed treatments, plus the pipeline plan.

Gate / verdict

  • Each series has a source, definition, classification and quality note
  • Licenses and redistribution rights are recorded
  • Concept mismatches with the model are documented

Suggested next steps

  • /calibration-plan
  • /build-dsge

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.