software-concept-architect-reviewFind Design Gaps and Code Drift
Install via ClawdBot CLI:
clawdbot install agenticweb4/software-concept-architect-reviewGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/ontology-of-everything/concept-skillsUses known external API (expected, informational)
arxiv.orgAudited Oct 9, 2026 · audit v1.0
Generated Oct 17, 2026
A platform team invokes this skill at the end of each sprint to audit concept documents and confirm whether the implementation still matches the confirmed behavioral contracts. Findings are merged by root cause and routed either to design, PRD, or build skills so remediation happens before shipping.
An enterprise architect runs a read-only review of legacy service designs to check whether each concept's operational principle still fits the real business need and whether product subsets preserve required entry points. Missing specifications are marked unverified rather than treated as defects.
A consultancy ingests a client's codebase and PRD and uses the skill to detect drift between documented synchronization specifications and the actual implementation. It separates omissions from contradictions and reports each with scenario-backed evidence and severity.
A product manager planning a modular suite uses the review to verify that each product subset independently preserves its purpose, entry points, required synchronizations, and resources. The resulting report guides the fix order across merged root causes.
An AI engineering team wires this skill into an agent pipeline that triggers only on explicit invocation, reads references and staged links, and produces a Markdown audit table. The read-only constraint keeps the review from mutating specifications or code.
Sell recurring review engagements where certified reviewers run the skill against client repositories each cycle. Clients receive structured reports listing fitness, independence, composition, and drift findings ranked by severity.
License the review skill as an add-on module for CI/CD and agent platforms so teams can run design-conformance gates automatically. Licensing tiers scale with repository count and invocation volume.
Use the free or low-cost audit report as a lead generator, then monetize follow-on design, PRD, and build remediation services routed from each finding. The read-only review creates a clear handoff to billable implementation work.
💬 Integration Tip
Invoke it only on explicit user request and keep it read-only, routing findings to the design, prd, or build skills rather than editing artifacts directly. Feed it confirmed behavioral contracts and code together, and mark conclusions backed by missing material as unverified.
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.