← Back to Skills Marketplace
Arch Review
by
codenova58
· GitHub ↗
· v1.0.0
· MIT-0
130
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install arch-review
Description
Stress-test designs before they ship—constraints, trade-offs, failure modes, and ADR-worthy decisions. Use for ADRs, big refactors, new services, or when ‘it...
README (SKILL.md)
Architecture Review
Challenge a design without owning the team’s roadmap: clarify forces (scale, money, people, regulation), surface risks, and leave decisions traceable—usually as an ADR or review notes.
Inputs you need (ask early)
- Goal and non-goals; users and SLAs; constraints (budget, deadline, org skills).
- Current pain—latency, incidents, cost, velocity—not buzzwords.
- Alternatives considered, even if rough.
Review lens (pick what fits)
- Failure: blast radius, partial outages, data loss, replay.
- Ops: deploy model, rollbacks, observability, on-call load.
- Change: team size, Conway’s law, long-term ownership.
- Security: trust boundaries, secrets, supply chain—at architecture depth, not a full pentest.
Output shape
- Summary of the proposal in your own words (catches misunderstandings).
- Top risks with severity; mitigations or experiments.
- Open questions for the team—not a pretend-final design.
Not this
- Replacing the team’s product judgment; rubber-stamping; 20-page templates nobody reads.
Done when
- The team can explain what they decided, why, and what would falsify the choice later.
Usage Guidance
This skill is instruction-only and coherent with its purpose — low technical risk. Before using it, avoid pasting secrets, credentials, or sensitive infrastructure diagrams into prompts; provide sanitized goals, constraints, and incident summaries instead. Because the skill is just guidance text (no code), it won't install or run binaries, but any context you give the agent can be exposed in the agent's logs or outputs — only share what you're comfortable having reviewed. If you want extra safety, restrict use to interactive, user-invoked sessions rather than enabling broad autonomous invocation.
Capability Analysis
Type: OpenClaw Skill
Name: arch-review
Version: 1.0.0
The skill bundle contains only metadata and conceptual guidelines in SKILL.md for performing architecture reviews. It lacks any executable code, shell commands, or instructions that would lead to unauthorized data access or malicious behavior.
Capability Assessment
Purpose & Capability
The name/description (architecture review / ADR-style guidance) matches the SKILL.md content. The skill declares no binaries, env vars, config paths, or installs — which is appropriate for a purely advisory review aid.
Instruction Scope
SKILL.md contains only guidance for eliciting inputs and producing review outputs (risks, mitigations, open questions). It does not instruct the agent to read system files, access credentials, or send data to external endpoints. It does encourage asking for inputs; users should avoid pasting secrets or sensitive configs into the prompt.
Install Mechanism
No install spec and no code files are present. Being instruction-only means nothing is written to disk or fetched at install time—lowest installation risk.
Credentials
The skill requests no environment variables, credentials, or config paths. This is proportionate for an advisory architecture-review skill. Note: the skill expects users to provide architecture context; those inputs can be sensitive if they contain secrets or credentials, so users should sanitize before sharing.
Persistence & Privilege
Registry flags are default (always:false, agent-autonomy allowed by platform default). There's no request for permanent presence or system-wide config changes. Autonomous invocation is permitted by platform defaults but is not combined with other concerning privileges here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install arch-review - After installation, invoke the skill by name or use
/arch-review - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of **arch-review** skill.
- Provides a repeatable structure for technical architecture reviews.
- Guides users to clarify constraints, surface risks, and document key decisions.
- Suggests inputs to gather, including goals, constraints, current pain points, and alternatives.
- Offers review lenses: failure, operations, change management, and architecture-level security.
- Outlines recommended output: summary, top risks, mitigations, and open questions.
- Distinguishes review scope from product decisions and excessive documentation.
- Defines completion as traceable, explained technical decisions.
Metadata
Frequently Asked Questions
What is Arch Review?
Stress-test designs before they ship—constraints, trade-offs, failure modes, and ADR-worthy decisions. Use for ADRs, big refactors, new services, or when ‘it... It is an AI Agent Skill for Claude Code / OpenClaw, with 130 downloads so far.
How do I install Arch Review?
Run "/install arch-review" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Arch Review free?
Yes, Arch Review is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Arch Review support?
Arch Review is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Arch Review?
It is built and maintained by codenova58 (@codenova58); the current version is v1.0.0.
More Skills