software-concept-architect-refineUntangle Overloaded Concepts
Install via ClawdBot CLI:
clawdbot install agenticweb4/software-concept-architect-refineGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://essenceofsoftware.com/posts/design-moves/Uses known external API (expected, informational)
arxiv.orgAudited Oct 9, 2026 · audit v1.0
Generated Oct 9, 2026
A fintech startup's payment domain model has become overloaded: a single 'Transaction' concept handles authorization, settlement, refund, and fraud detection. The architect uses this skill to reconstruct purpose and identify overloading, then splits it into 'Payment', 'Refund', and 'Settlement' concepts while preserving contracts.
An e‑commerce platform has redundant concepts like 'Cart' and 'Basket' with overlapping responsibilities, causing synchronization bugs. The skill guides merging into a unified 'ShoppingCart' concept, with evidence from user scenarios and counterexamples to ensure no behavior loss.
A healthcare app's patient onboarding is fragmented across 'Registration', 'Intake', and 'Consent' concepts that are under-synchronized. The architect uses the skill to investigate fragmentation and synchronize these concepts, verifying end-to-end scenarios and local purposes.
An IoT platform's 'Device' concept is too narrow, only supporting sensors, but now needs to include actuators and gateways. The skill helps generalize the concept, weighing unify vs. specialize moves, and provides a refactoring plan with minimal impact.
A logistics system has over-synchronized 'Shipment' and 'Inventory' concepts, causing performance bottlenecks. The architect uses the skill to loosen synchronization, respecting concept contracts and validating both local and system-wide scenarios.
Offer a monthly subscription where architects review and refine software concept designs for clients, using the skill to diagnose overload, redundancy, and fragmentation. Deliverables include refactoring plans and verification reports.
Provide a fixed-price engagement where the architect analyzes an existing concept system, identifies issues, and executes authorized changes with a detailed report. Ideal for teams needing a focused intervention.
Offer workshops and certification courses teaching teams how to apply the skill's evidence-led refactoring techniques, including moves and evidence references. Includes hands-on exercises with real-world cases.
💬 Integration Tip
Integrate this skill into design review or architecture decision records to systematically address concept overload; ensure references/moves.md is available and that the team agrees on stopping criteria and verification steps.
Scored Oct 9, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.