Skill UI

Implements an ENFP-style SB Leader persona that keeps the core PUA guardrails (rules, escalation, methodology) while swapping pressure for empathy, praise, and playful banter to motivate engineers without losing rigor or closure.

This comprehensive guide outlines essential best practices and structural checks for developing robust Salesforce Apex code. It covers critical areas such as preventing governor limit exceptions (e.g., bulk safety), enforcing security (CRUD/FLS), preventing SOQL injection, adhering to sharing models, and implementing modern Apex idioms. It also mandates rigorous testing strategies (Positive, Negative, Bulk) and proper trigger architecture.

This guide details how to implement robust content safety guardrails for applications powered by Claude. It covers essential techniques such as system prompt hardening, input validation to detect injection patterns and length limits, and output validation to prevent system prompt leakage. It ensures compliance with Anthropic's policies, making the AI integration secure and reliable.

Implements automated, multi-layered policy enforcement and guardrails for Adobe integrations. This skill provides crucial security checks, including detecting sensitive credentials (e.g., p8_ secrets), pre-screening content for services like Firefly (blocking trademarks or explicit material), and enforcing usage quotas for PDF Services. It is essential for maintaining secure and compliant CI/CD pipelines.

This comprehensive skill provides multi-layered guardrails for integrating with LLMs like Claude. It enforces security and compliance by implementing input validation (PII detection, length checks), system prompt restriction (scope control, safety rules), output filtering (preventing sensitive data leakage), cost governance, and model access policies. Ideal for building secure, robust, and governed AI applications.

Implements automated policy enforcement and guardrails for Canva Connect API integrations. This system enforces best practices such as preventing hardcoded credentials, ensuring proper rate limit handling (429 responses), and validating robust OAuth configurations. It is essential for maintaining high code quality and security in CI/CD pipelines and pre-commit hooks.

Automated guardrails for enforcing security policies and coding standards across all Figma API integrations. This tool is essential for CI/CD pipelines, helping to prevent credential leaks (PATs), validate API scopes, enforce request best practices, and ensure stable, secure connectivity with Figma.

This setup implements a pre-execution hook to safeguard code repositories by intercepting and blocking destructive Git operations (e.g., `git push`, `git reset --hard`, `git clean`). It prevents accidental or unauthorized data loss during automated code generation or tool use within AI environments, ensuring robust version control safety.

A comprehensive guide for implementing robust policy enforcement and security guardrails in HubSpot integrations. This methodology covers secret scanning within CI/CD pipelines to prevent token leaks, utilizes ESLint rules for enforcing modern authentication practices, and leverages TypeScript for compile-time and runtime checks. Use this when setting up secure, scalable, and compliant codebases for HubSpot APIs.

This structured mode acts as an experiment design partner for Product Managers. It guides users through formulating testable, falsifiable hypotheses, designing rigorous A/B tests (including sample size, duration, and guardrails), and interpreting results honestly. It helps PMs move from vague beliefs to clear, data-backed decisions: Ship, Iterate, or Kill.

This skill defines canonical, ordered middleware patterns for LangChain and LangGraph agents. It addresses critical production-level LLM deployment issues, including PII leakage across tenants, token budget overconsumption, prompt injection defense (Guardrails), and cache key corruption. Use this to build secure, scalable, and cost-aware AI applications.

A comprehensive framework for establishing governance standards across Notion integrations. It enforces naming conventions for bots, manages page sharing policies to prevent data leaks, validates database schemas (e.g., required property naming, date formats), and provides access audit scripts. Ideal for maintaining consistency and security in large, multi-team Notion environments.