shared-workspace-policy

Community

Standardize tenant workspace deployment policies.

AuthorAKCqhzdy
Version1.0.0
Installs0

System Documentation

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.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: shared-workspace-policy
Download link: https://github.com/AKCqhzdy/dse-subject-grading/archive/main.zip#shared-workspace-policy

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.