Pmstudio Arb

Community

coco-research

pmstudio-arb

Generate an Architecture Review Board (ARB) presentation in Coco Inc's standard 11-slide format. Use when someone asks to "create an ARB deck", "architecture review presentation", "prepare for architecture review board", "ARB slides", or needs to present a product/platform architecture for sign-off. Reads PRD, architecture maps, and project memory to pre-fill technical content. Produces a self-contained HTML slide deck.

Overview

Publisher	coco-research
Repository	`coco`
Skill name	`pmstudio-arb`
Stars	550
Forks	12
Bundled files	1
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by coco-research on GitHub. Read the source before you install it.

Installation

Install the Pmstudio Arb AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/coco-research/coco/tree/main/skills/arb-review
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/coco-research/coco.git /tmp/coco
mkdir -p .claude/skills
cp -r /tmp/coco/skills/arb-review .claude/skills/pmstudio-arb

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pmstudio Arb in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pmstudio Arb on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pmstudio Arb is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

ARB Review — Architecture Review Board Presentation

Purpose

Generates an 11-slide architecture review presentation following Coco Inc's standard ARB format. Used when a product needs architecture sign-off for a new instance, major integration, platform migration, or periodic review.

Process

Step 1: Read Context

Required sources (read all that exist):

CLAUDE.local.md — project context, architecture decisions, stakeholders, ProdID
PRD/*.html or PRD/*.md — requirements, NFRs, technical considerations, integrations, data model
Architecture/ or *Architecture*.html — existing diagrams, maps

Optional sources:

.sync-watch.json — project name
Operational/DR-Plan*.html — RTO/RPO targets (for slide 8)
Data/Stakeholder-Directory.* — presenter and audience names

Step 2: Ask Discovery Questions

Only ask what cannot be inferred from context:

Review type? New Product / Major Change / Periodic Review / Decommission
Data classification? Purple / Red / Yellow / Green (if not in PRD)
Audience? Firm-level ARB / Department-level / Technical review
Known constraints or mandates? (e.g., "must use existing Snowflake instance")
Decision you need? Approve / Approve-with-conditions / Defer — what specifically?

Step 3: Generate 11-Slide Deck

Output: Presentations/ARB-Review-{ProductName}-{Date}.html

Self-contained HTML file with:

System fonts (no CDN dependencies)
Click/keyboard navigation between slides
Print CSS for PDF export
Mermaid.js (CDN) for architecture diagrams

Slide structure — see references/arb-format.md for section details:

#	Slide	Key Content
1	Title & Context	Product name, ProdID, review type, date, presenters
2	Business Context	Problem statement, strategic alignment, sponsor
3	Current State	AS-IS architecture (Mermaid diagram), pain points
4	Proposed Architecture	TO-BE architecture (Mermaid diagram), what changes
5	Data Architecture	Data classification, flows, retention, residency
6	Security & Access	AuthN/AuthZ, RBAC, encryption, CUECs
7	Integration Points	Upstream/downstream, protocols, error handling
8	NFRs & SLAs	Performance, availability, RTO/RPO, scalability
9	Risk Assessment	Architecture risks, mitigations, residual acceptance
10	Implementation Plan	Phases, timeline, rollback, blast radius
11	Decision Request	What you need from the board, options, recommendation

Step 4: Populate Content

For each slide, pull from project sources:

Slide 1: Product name and ProdID from CLAUDE.local.md. Review type from Step 2. Presenters from stakeholder directory.
Slides 3-4: Generate Mermaid diagrams from PRD architecture section and Architecture maps. If current-state diagram exists, use it. If not, build from PRD integrations and technical considerations.
Slide 5: Data classification from PRD or discovery. Data flows from integrations section. Retention from NFRs.
Slide 6: RBAC from PRD. CUECs from operationalization section. SSO/AuthN from technical considerations.
Slide 7: Extract all integration points from PRD. Add protocol, frequency, error handling.
Slide 8: Pull NFRs directly from PRD table. RTO/RPO from DR plan if it exists.
Slide 9: Pull risks from PRD risk section. Add architecture-specific risks.
Slide 10: Pull timeline from PRD. Add rollback strategy.
Slide 11: Decision request from Step 2. Frame options with recommendation.

Step 5: Present for Review

Show the deck outline with key content per slide. Ask:

"Does this cover the right scope?"
"Any slides that need different emphasis?"
"Who are the presenters for slide 1?"

Apply feedback, then write the file.

Critical Rules

Mermaid diagrams are mandatory for slides 3 and 4. Architecture reviews without diagrams fail.
Data classification must be explicit. If unknown, mark as "TBD — requires classification" in red. Never assume.
Slide 11 must have a clear ask. Not "please review" but "approve this architecture for production deployment" or "approve with condition: validate cascading before Phase 2."
No implementation details on architecture slides. Show components, interfaces, and data flows — not code, configs, or step-by-step procedures.
Keep it to 11 slides. If more content is needed, add appendix slides clearly labeled "APPENDIX" after slide 11.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

references/arb-format.md4 KB

Frequently asked questions

What does the Pmstudio Arb AI skill do?

Why use Pmstudio Arb on TypingMind?

Because you install it once and use it with any model. Pmstudio Arb is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pmstudio Arb in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coco-research/coco/tree/main/skills/arb-review. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pmstudio Arb?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pmstudio Arb?

As many as you like. As long as a model supports skills, you can use Pmstudio Arb with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pmstudio Arb AI skill free?

It is published on GitHub by coco-research. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Release Openclaw Announcement

openclaw

OrganizationPopular

Draft or post OpenClaw beta, stable, or extended-stable Discord release announcements from changelog, tag, registry, and validation evidence. Use when announcing a release, release candidate, or…

Security Triage

Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.

Add Model Provider

Add and live-prove a model provider with non-interactive config one-liners, without exposing credentials.

Diagnose Gateway

Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

ARB Review — Architecture Review Board Presentation

Purpose

Process

Step 1: Read Context

Step 2: Ask Discovery Questions

Step 3: Generate 11-Slide Deck

Step 4: Populate Content

Step 5: Present for Review

Critical Rules

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now