An interactive AI design coaching and documentation skill that aligns system architecture using rigorous interviews, domain glossaries, and Architectural Decision Records (ADRs).
The fastest way to install a skill directly from the registry.
npx clawhub@latest install grill-docs
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install grill-docs using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Grill with Docs is a system design alignment utility among the ecosystem of Openclaw Skills, designed to ruthlessly interrogate and refine architectural plans. Acting as an expert design partner, this skill conducts a relentless, branch-by-branch interview to uncover ambiguities, resolve domain conflicts, and establish shared understanding between developers and AI agents.
By probing edge cases and cross-referencing decisions against the existing codebase, it prevents domain drift and ensures alignment. Instead of waiting for the end of a session, it dynamically captures and updates domain terms inline inside a standardized documentation framework, making it a highly effective asset for team alignment.
To implement this tool within your active project directories utilizing Openclaw Skills configurations, construct your workspace profiles as follows:
# Navigate to your repository or workspace folder
cd your-project-repo
# Ensure you have your openclaw or AI assistant configuration files active
# Initialize or copy the grill-with-docs prompt into your active skills path
mkdir -p .claws/skills
cp grill-with-docs.md .claws/skills/
Configure your agent environment to recognize the system prompts, enabling automated file system checks and codebase exploration protocols automatically.
The skill enforces a clean, implementation-free documentation hierarchy across single or multi-context environments:
| Path | Purpose | Content Type |
|---|---|---|
CONTEXT.md |
Single-context domain glossary | Concepts, canonical terms, definitions |
CONTEXT-MAP.md |
Multi-context directory layout map | Pointers to distributed context roots |
docs/adr/ |
Global architectural decisions | High-impact architectural history (.md) |
src/<context>/CONTEXT.md |
Context-specific glossary | Local domain term mappings |
src/<context>/docs/adr/ |
Context-specific decisions | Local architectural history (.md) |
Loading
A production-tested memory and self-evolution blueprint designed to give AI agents persistent contextual awareness and adaptive performance across sessions.

An AI-powered career development and education planning skill that tracks global job market shifts, salary benchmarks, and education ROI across 800+ occupations.

A structural analysis skill that directs AI agents to stop low-level code reading and synthesize a high-level architectural map of code modules, APIs, and dependencies.

An AI-powered personal finance and wealth management intelligence engine designed to analyze portfolios, project retirement goals, and optimize debt payoff strategies.

A disciplined, multi-phase diagnosis loop designed for AI agents to systematically reproduce, isolate, and resolve complex software bugs and performance regressions.

An AI agent skill enabling cost-effective, secure discovery and multi-provider inference of open-source models and datasets on Hugging Face.








































