prismUse PRISM when: (1) reviewing an architecture decision, security-sensitive change, or major refactor (>500 lines), (2) making a decision you'll live with for...
Install via ClawdBot CLI:
clawdbot install jeremyknows/prismGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdCalls external URL not in known-safe list
https://github.com/tobilu/qmdAI Analysis
The skill definition describes a multi-agent review protocol and does not contain executable code. The flagged signals appear to be examples or test data within the documentation (e.g., '/etc/passwd', 'https://github.com/tobilu/qmd') illustrating evidence rules, not actual operational instructions. No mechanism for data exfiltration or credential harvesting is defined.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
A fintech company uses PRISM to audit a new payment processing module before deployment. The Security Auditor identifies a potential injection vulnerability, while the Devil's Advocate challenges assumptions about input validation, ensuring robust protection against attacks.
A gaming studio applies PRISM to review a graphics rendering engine update. The Performance Analyst benchmarks frame rates and memory usage, while the Simplicity Advocate flags unnecessary complexity, leading to optimized code without sacrificing quality.
A healthcare provider uses PRISM to assess changes to patient data handling systems for HIPAA compliance. Reviewers cross-check data access logs and encryption methods, with prior findings from earlier audits ensuring persistent issues are addressed.
A developer submits a pull request to a large open-source project, and maintainers run PRISM to evaluate the contribution. Multiple specialists review code quality, security, and performance in parallel, speeding up the merge process with thorough feedback.
A cloud services company uses PRISM to audit a new Kubernetes deployment configuration. Reviewers analyze YAML files for security misconfigurations and performance bottlenecks, citing specific lines and commands to prevent downtime.
Offer PRISM as a cloud-based service with tiered pricing based on review frequency and agent count. Customers pay monthly for access to automated multi-agent reviews, with premium tiers including extended audits and governance features.
Sell on-premise licenses to large organizations requiring high-security reviews. Includes custom integration support, dedicated training, and priority updates, targeting industries like finance and healthcare with strict compliance needs.
Release PRISM under the MIT license with core features free, while monetizing advanced capabilities like memory-based prior review search and extended agent roles. Generate revenue through paid plugins and enterprise support contracts.
💬 Integration Tip
Ensure your AI agent can spawn subagents or run sequential reviews; start with Budget PRISM mode for lightweight testing before scaling to full audits.
Scored Jun 17, 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.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
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.