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

adopt

Skill4 starsChanged 6 days agoMITView on GitHub

Brings an existing model or codebase into the studio: inventories it, reverse-documents it and plans validation and migration.

31 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-stories, story-done and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 11 projects that use this

  • +10 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 3

    Distinctive

    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:

    Run the model if possible and capture baseline outputs as the reference

    line 41
  4. Distinctive:

    After the inventory: confirm scope

    line 48
  5. Distinctive:

    After the gap list: agree priorities

    line 49

“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “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/adopt/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

/adopt — Adopt

Category: Onboarding · Primary agent: modeling-methodology-specialist

Brings an existing model or codebase into the studio: inventories it, reverse-documents it and plans validation and migration.

Arguments: whatever the user wrote after the command name.

Purpose

Bring an existing model or codebase into the studio without breaking it: inventory it, reverse-document its equations and assumptions, capture its current outputs as the reference before anything changes, rate its risk, list gaps against studio standards, and propose a prioritized plan to document, test, validate and possibly migrate it. A lego manifest makes its components and interfaces explicit.

Use it when an institution's legacy model, an inherited codebase or a published model is to be used or maintained in the studio.

Do not use it when the model will be rebuilt from scratch (/model-spec).

Before you start

  1. Check required inputs. For each input below record FOUND or ABSENT (never 'assumed'):
    • Existing model code/documents at the given path 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

  • modeling-methodology-specialist — primary agent; coordinates the work and integrates results
  • reproducibility-engineer — Guarantees reproducibility
  • technical-documentation-specialist — Writes technical documentation
  • model-validation-specialist — Performs independent model validation
  • matlab-dynare-engineer — Engineers MATLAB, Dynare, IRIS, RISE and Octave codebases; legacy model maintenance and migration

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.

Workflow

  1. Inventory files, languages, dependencies, data and entry points
  2. Reverse-document equations, assumptions and parameters from the code; flag undocumented behavior
  3. Run the model if possible and capture baseline outputs as the reference
    • Pin the environment in which the reference was produced
  4. Rate model risk level and produce a gap list against studio standards
  5. Propose a prioritized adoption plan (document, test, validate, migrate)
  6. Draft a lego manifest of the existing model (/lego-map) so its components, interfaces and simultaneous blocks are explicit before any change

Checkpoints with the user

  • After the inventory: confirm scope
  • After the gap list: agree priorities

Common pitfalls

  • Changing code before capturing reference outputs
  • Trusting existing documentation over the code
  • Migrating before testing

Output

docs/models/<model>/adoption-report.md

The adoption report holds the inventory, reverse documentation, reference outputs and environment, risk rating, gap list, plan and the draft 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

  • Baseline outputs are captured before any code is changed
  • The environment that produced the reference outputs is recorded

Suggested next steps

  • /validate-model
  • /translate-code
  • /model-card

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.