/model-brief — Model Brief
Category: Scoping & Design · Primary agent: project-planning-specialist
Creates the model brief: purpose, model class, mechanisms, data, validation level, team, timeline and risks.
Arguments: whatever the user wrote after the command name.
Purpose
Write the model brief: the one document that says what a model is for and what it is not for, which class it belongs to, which mechanisms it must contain, what data it needs, how deeply it will be validated, who will build it, by when, and what could go wrong. The output is the reference against which every later decision and the final validation are judged.
Use it when a modeling project has been scoped and the model class chosen, before specification starts.
Do not use it when the work is exploratory and labeled as such (/quick-model), or the question is not yet precise (/scope-question).
Before you start
- Check required inputs. For each input below record
FOUND or ABSENT (never 'assumed'):
- docs/briefs/-scope.md (recommended)
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.
- 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.
- 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
project-planning-specialist — primary agent; coordinates the work and integrates results
economic-reasoning-specialist — Frames the economic question and tests whether results make economic sense
modeling-methodology-specialist — Chooses methods and architecture across model families, sets code and data standards, and resolves technical trade-offs between traditional, structural and AI approaches
model-risk-governance-specialist — Defines model risk levels and validation depth, enforces builder-validator independence, governs AI/LLM use and recommends release or block
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)
| Decision |
Typical options |
What it changes |
| Purpose |
forecasting, policy analysis, scenario, research |
Validation focus |
| Risk level |
low, medium, high |
Validation depth and sign-offs |
| Ownership |
studio team, counterpart, shared |
Documentation and training |
| Timeline |
weeks, months |
Model size and scope |
Workflow
- Collect the scoping note, the chosen model class and available resources
- Draft the brief from
docs/templates/model-brief.md, one section at a time, with approval for each
- State non-purposes explicitly
- Assign risk level with the model-risk-governance-specialist
- Set milestones sized to the model class and flag dependencies
- Include data, validation and documentation milestones
Checkpoints with the user
- After each section of the brief
- After risk assignment: confirm validation depth
Common pitfalls
- No non-purposes, so the model is later used for everything
- Timelines that ignore validation
- Unclear ownership after delivery
Output
docs/models/<name>/model-brief.md
The brief covers purpose and non-purposes, model class, mechanisms, data, validation level, team, timeline, risks and dependencies.
Gate / verdict
- Purpose and non-purposes are stated
- Risk level and validation depth are agreed
- Milestones include validation and documentation
- Ownership after delivery is stated
Suggested next steps
/literature-review
/model-spec
1---2name: model-brief3description: "Creates the model brief: purpose, model class, mechanisms, data, validation level, team, timeline and risks."4metadata:5 source: https://skillmd.com/skills/majiayu000/model-brief6---78<!-- Generated from .claude/skills/model-brief/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->910# /model-brief — Model Brief1112**Category:** Scoping & Design · **Primary agent:** `project-planning-specialist`1314Creates the model brief: purpose, model class, mechanisms, data, validation level, team, timeline and risks.1516Arguments: whatever the user wrote after the command name.1718## Purpose19Write the model brief: the one document that says what a model is for and what it is not for, which class it belongs to, which mechanisms it must contain, what data it needs, how deeply it will be validated, who will build it, by when, and what could go wrong. The output is the reference against which every later decision and the final validation are judged.2021**Use it when** a modeling project has been scoped and the model class chosen, before specification starts.2223**Do not use it when** the work is exploratory and labeled as such (`/quick-model`), or the question is not yet precise (`/scope-question`).2425## Before you start261. **Check required inputs.** For each input below record `FOUND` or `ABSENT` (never 'assumed'):27 - docs/briefs/<name>-scope.md (recommended)28 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.292. **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.303. **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.3132## Agents33- `project-planning-specialist` — primary agent; coordinates the work and integrates results34- `economic-reasoning-specialist` — Frames the economic question and tests whether results make economic sense35- `modeling-methodology-specialist` — Chooses methods and architecture across model families, sets code and data standards, and resolves technical trade-offs between traditional, structural and AI approaches36- `model-risk-governance-specialist` — Defines model risk levels and validation depth, enforces builder-validator independence, governs AI/LLM use and recommends release or block3738Each 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.3940## Key design decisions (present options, let the user choose)41| Decision | Typical options | What it changes |42|---|---|---|43| Purpose | forecasting, policy analysis, scenario, research | Validation focus |44| Risk level | low, medium, high | Validation depth and sign-offs |45| Ownership | studio team, counterpart, shared | Documentation and training |46| Timeline | weeks, months | Model size and scope |4748## Workflow491. Collect the scoping note, the chosen model class and available resources502. Draft the brief from `docs/templates/model-brief.md`, one section at a time, with approval for each51 - State non-purposes explicitly523. Assign risk level with the model-risk-governance-specialist534. Set milestones sized to the model class and flag dependencies54 - Include data, validation and documentation milestones5556## Checkpoints with the user57- After each section of the brief58- After risk assignment: confirm validation depth5960## Common pitfalls61- No non-purposes, so the model is later used for everything62- Timelines that ignore validation63- Unclear ownership after delivery6465## Output66`docs/models/<name>/model-brief.md`6768The brief covers purpose and non-purposes, model class, mechanisms, data, validation level, team, timeline, risks and dependencies.6970## Gate / verdict71- Purpose and non-purposes are stated72- Risk level and validation depth are agreed73- Milestones include validation and documentation74- Ownership after delivery is stated7576## Suggested next steps77- `/literature-review`78- `/model-spec`