Version updated for https://github.com/CodeJonesW/sensei-eval to version v0.5.0. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary The sensei-eval GitHub Action is designed to evaluate AI-generated educational content using deterministic checks and LLM-based scoring. It automates the detection of prompt quality regressions in CI workflows by comparing content against predefined baselines and identifying any significant score drops.

Version updated for https://github.com/daveymoores/carrick to version carrick-v0.1.1. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Carrick is a GitHub Action designed to detect and resolve API mismatches between producers (Express apps) and consumers by analyzing routes, HTTP calls, and TypeScript types across repositories. It automates the identification of issues such as type mismatches, method conflicts, and missing or unused endpoints during CI workflows.

Version updated for https://github.com/Forge-Space/forge-ai-action to version v1.1.0. This action is used across all versions by ? repositories. Action Type This is a Node action using Node version 20. Go to the GitHub Marketplace to find the latest changes. Action Summary The Forge AI Action is a GitHub Action designed to enhance code quality and governance by automatically analyzing pull requests for quality regressions, AI anti-patterns, security vulnerabilities, and other issues. It provides quality reports with scores, insights, and pass/fail gates, enabling teams to ensure that AI-assisted or manual code changes improve rather than degrade the codebase.

Version updated for https://github.com/gabe565/moreutils-go to version v0.6.1. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary The moreutils-go GitHub Action provides a Go-based implementation of the original moreutils toolkit, offering a collection of lightweight Unix command-line tools rewritten to eliminate dependencies like Perl. It automates and simplifies various text processing, system information retrieval, file handling, and process management tasks through self-contained binaries.

Version updated for https://github.com/HOSHO-AI/Hosho-prompt-optimization-public to version v1.26.0. This action is used across all versions by ? repositories. Action Type This is a Node action using Node version 20. Go to the GitHub Marketplace to find the latest changes. Action Summary The Hosho Prompt Reviewer GitHub Action evaluates AI agent prompts against research-backed prompt engineering best practices, ensuring they are well-structured, goal-oriented, and optimized for models like GPT, Claude, and Gemini. It automates the review process by identifying weaknesses, providing detailed feedback with suggested fixes, and offering ratings across six key quality factors.

Version updated for https://github.com/integsec/turbopentest-action to version v1.0.2. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary TurboPentest GitHub Action enables automated AI-driven penetration testing of web applications directly from your CI/CD pipeline. It simplifies security assessments by identifying vulnerabilities efficiently during development workflows. Key capabilities include initiating pentests, retrieving detailed results, and optionally waiting for completion to ensure continuous security monitoring.

Version updated for https://github.com/invariant-systems-ai/aiir to version v1.0.11. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary AIIR (AI Integrity Receipts) is a GitHub Action that provides cryptographically tamper-evident receipts for tracking AI involvement in code commits. It helps organizations meet transparency, compliance, and auditing requirements, such as those under the EU AI Act, by recording whether commits were AI-generated and ensuring the integrity and provenance of code changes.

Version updated for https://github.com/JNZader/ghagga to version v2.5.0. This action is used across all versions by 0 repositories. Action Type This is a Node action using Node version 20. Go to the GitHub Marketplace to find the latest changes. Action Summary GHAGGA is an AI-powered code review tool that automates the process of analyzing pull request (PR) changes by combining static analysis tools, project memory, and language models (LLMs). It detects issues, provides intelligent suggestions, and posts structured review comments directly on PRs, while continuously learning from past reviews to improve over time.

Version updated for https://github.com/k15z/axiom to version v0.1.3. This action is used across all versions by 0 repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. Action Summary Axiom is a GitHub Action designed to automate the verification of high-level behavioral invariants, such as architectural boundaries, security requirements, and error-handling contracts, by leveraging a large language model (LLM). It allows users to define plain-English assertions about their codebase, which are automatically tested to catch issues that might otherwise go unnoticed during refactoring or code review.