Verified:GitHub

shared-workspace-policy

Enforce tenant workspace deployment policies for DSE-subject environments.

Updated Aug 27, 2026

Search Tags:#credentials #workspace-policy #tenant-deployment #policy-inheritance #vlm-restrictions #dpi-defaults #sub-agent-conventions

Ready to run

npx skills add https://github.com/AKCqhzdy/dse-subject-grading --skill shared-workspace-policy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: shared-workspace-policy
Source: https://github.com/AKCqhzdy/dse-subject-grading/tree/main/skills-v3/shared-workspace-policy
Command: npx skills add https://github.com/AKCqhzdy/dse-subject-grading --skill shared-workspace-policy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Tier-2 (tenant) deployment policy for DSE-subject workspaces. Model inheritance, VLM restrictions, DPI defaults, sub-agent conventions, report-language sourcing, credentials rule. Reference-only — do not invoke directly; other skills cite this.

Core Features & Use Cases

Sub-agents inherit the main agent's model. Do NOT pass a model override to sub-agent tool calls. Let them inherit.
VLM tasks: Kimi K2.5 only. For any task requiring a vision-language model (OCR from scanned PDFs, art-work grading, handwriting inspection), use kimi-k2.5 exclusively.
No LLM/VLM API calls for narrative/feedback/analysis text. This is also enforced at Tier 1 (WARNING.md). All prose must come from sub-agents, never from direct API calls in scripts.

Quick Start

Cite this policy in workspace deployment configurations and reference it from other skills when configuring sub-agent workflows.

Frequently Asked Questions about shared-workspace-policy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I configure sub-agent model inheritance for tenant workspace deployment?▼

To configure sub-agent model inheritance, omit model overrides in sub-agent tool calls so they automatically inherit the main agent's model configuration per the tenant workspace policy.

Which VLM should I use for OCR and handwriting inspection in DSE-subject environments?▼

For vision-language model tasks like OCR and handwriting inspection in DSE-subject environments, you must use Kimi K2.5 exclusively as mandated by the tenant deployment policy.

Can I make direct LLM API calls to generate narrative text in workspace provisioning scripts?▼

No, direct LLM or VLM API calls for narrative, feedback, or analysis text are prohibited; all prose must be sourced from sub-agents rather than direct script API calls.

What are the DPI defaults and credential rules for tenant workspace deployment?▼

Tenant workspace deployment policy enforces specific DPI defaults and credential rules, but as a reference-only policy, it must be cited by other skills rather than invoked directly during configuration.

How do I reference workspace policy when configuring sub-agent workflows?▼

You reference workspace policy by citing it within your workspace deployment configurations and sub-agent workflow setups, ensuring model inheritance and VLM restrictions are applied correctly.