# Scope

> Use when unsettled requirements or decisions need a spec, options, acceptance criteria, authority bounds, or decision record. Not for implementing approved scope or writing files during read-only advice; use implement.

- Skill: `mblauberg/scope` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add mblauberg/scope`
- Raw SKILL.md: https://api.skillmd.com/api/skills/mblauberg/scope/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: mblauberg (https://skillmd.com/u/mblauberg)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/mblauberg/scope

---


# Scope

Produce testable scope.

## Frame

Read the repository's `Repository process` declaration. If absent or ambiguous,
use an unambiguous existing owner or return proposed content in chat; never
invent an owner. Define the decision, users and done in the declared parent
issue or project-docs home. Emit the minimum `config/risk-policy.json` tier,
path/write/resource limits, prohibited actions, external effects, expiry and
approver. Credentials, secrets, unrelated paths, denials and project bans stay
outside authority. Execution permission is not assurance. Ordinary authorised
workspace content proceeds without a
family-separation gate. Only a user may downgrade risk. Judgement-bearing AI
requires `evaluate`.

Writing a tracker needs explicit external-write authority; project-write
authority alone does not grant it.

Scope owns accepted content and decision register: intake, goals,
constraints, alternatives and decided/parked branches. Record disclosure in
the authority envelope, never private memory.

## Grill

Load `grill-me` only when the user explicitly asks to be grilled or dependent owner decisions remain
materially unresolved. Then work purpose -> users ->
constraints -> edge cases -> failure modes -> success -> exclusions. Otherwise
present a compact decision packet with 2–3
choices, a recommendation and parked calls.

Agents decide engineering calls. Business, legal or financial owner calls stay
parked as open-decision rows; never guess. Put every unresolved branch in
scope.

## Resolve uncertainty

Research surviving questions through `orchestrate`; use `prototype` only for a
timeboxed feasibility answer, then harvest it and clean only manifest-owned
scratch.

Compare viable options through correctness, cost and operations. Put
costly-to-reverse choices and rejected alternatives in an ADR; keep reversible
detail in the spec/story. In paired-primary mode one chair asks; the peer audits.
Record authorship.

## Land outputs

Resolve artifact authority. In advisory/read-only
mode, return proposed scope and open decisions in chat; do not change
project files. In project-write mode, land only approved artifacts:

| Output | Owner |
|---|---|
| Durable requirements and normative acceptance criteria | project docs via `engineering-docs` |
| One-way decisions | project ADR process |
| User gates | declared scope/story owner; project-docs may name a register |
| Change scope, stories and delivery acceptance | declared issue tracker or project-docs home |
| Work items | declared project tracker |
| Durable context | declared project-docs owner; run state stays run-local |

Write observable acceptance criteria. Preserve project schemas; pin only
decision-critical interfaces with native locks/constraints. Link or cache
authority with its source and relevant date/version; vendor only with
redistribution permission.

Before handoff, record decided/parked branches, exclusions, risk/authority and
anchored evidence, with user approval of the spec and one-way doors. The
execution handoff is digest-bound; any change creates a new revision and gate.

## Portable artifact

Use the skill-owned [scope handoff schema](portable-workflow.v1.json).