---
name: workspace-context-preparation
description: "Organize evidence into proposed Outloop Workspace Context without sharing client facts globally. Use when the user requests workspace context preparation. Select relevant methods for the requested outcome; unrelated tasks do not require this skill."
metadata:
  version: "1.0.0"
---

# Workspace Context Preparation

Organize evidence into proposed Outloop Workspace Context without sharing client facts globally.

## OLLIE Runtime integration

Use this capability under the active OLLIE Operator. Read live Workspace Context and tenant bindings for client facts and required inputs. This generic package contains no client configuration. Consume ask-ollie-authority-core for authority, outloop-access-fallback for access and recovery, email-lifecycle-core for communication, and the bootstrapper Runtime Contract for ownership, scheduling and completion. Preserve domain constraints; this Skill creates no competing execution path. Use one method, combine skills, or fill missing steps with authorized tools as the task requires.

External access uses the active Workspace’s approved Outloop capabilities. Never request, read, embed or expose credentials. A service named in a method is a possible dependency, not an access grant. Local file and application work uses the host’s authorized tools.

## Required inputs

- Authorized source material
- Current Context
- Current Context schema
- Requested update scope

## Methods

### Resolve workspace identity

Fetch current approved Context and confirm workspace identity before interpreting sources. Keep organization facts, client facts and resource bindings distinct.

### Classify evidence

Label values as confirmed, observed, derived, estimated or unknown. Preserve source and date; identify conflicts explicitly rather than overwriting current truth.

### Prepare scoped proposals

Prepare narrowly scoped proposals in the actual supported Context sections. Contacts require role and side where known; resource identities belong to bindings rather than global skill instructions.

### Verify proposal state

Submit only through the approved learning mechanism when authorized and report proposed versus applied status accurately. Do not create client-specific global skills or copy one workspace’s facts into another.

## Completion

Verify findings against source evidence and read back the resulting artifact or authorized change. Report inputs used, methods selected, output location, assumptions and unresolved dependencies. Do not report a plan, queue entry, draft, test fixture or accepted request as a completed external action. Use the task’s requested format; if a tool is unavailable, finish independent work and identify the exact unfulfilled deliverable.

## Test before relying on it

Read [the synthetic evaluation cases](references/evaluation.md) for activation, output and isolation checks. These cases are test instructions, not evidence that a host or provider test has passed.