Version updated for https://github.com/snapsynapse/skill-provenance to version v6.2.0. 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 This GitHub Action automates the validation of Agent Skill bundles to ensure they are portable, have accurate versions and integrity, and detect any drift between the manifest and actual bundle contents. It helps teams track the version history and integrity of their skills across different platforms and sessions. The action ensures that a downloaded or shared bundle matches its recorded state before installing it, using SHA-256 hashes to catch tampering and accidental drift.

Version updated for https://github.com/snapsynapse/graceful-boundaries to version v1.5.4. 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 Graceful Boundaries is an open specification that grades API responses based on their conformance to a set of standards. It provides proactive discovery, structured refusal, and constructive guidance to help autonomous agents understand and act on operational limits efficiently. The action automates the process of checking response codes and providing actionable feedback for improving API reliability.

Version updated for https://github.com/snapsynapse/harnessie-verify-action to version v0.1.3. 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 The harnessie-verify-action automates the verification of claims in pull requests by running deterministic checks and a fresh-context verifier model on the artifacts. It helps reviewers adjudicate by summarizing results in a table, uploading reports and proof files as workflow artifacts, and exiting with appropriate codes for verification status. The action provides input controls like criteria, checks, models, and security settings to tailor verification workflows.

Version updated for https://github.com/snapsynapse/skill-provenance to version guidecheck-1.2.0. 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 Skill Provenance is a portable provenance, integrity, and drift control tool for Agent Skills. It ensures that the version, integrity, and staleness of agent bundles are tracked throughout their lifecycle across various platforms and surfaces, providing teams with essential verification capabilities to trust and manage Agent Skills effectively.

Version updated for https://github.com/snapsynapse/harnessie-verify-action to version v0.1.2. 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 This GitHub Action automates the verification of claims made in pull requests by executing deterministic checks and running a fresh-context verifier model. It prevents untrusted diffs from leaving machines under control and ensures that only verified claims are accepted before merging a pull request. The action is powered by harnessie verify, with an option to use OpenAI-compatible endpoints for verification, enhancing security and flexibility.

Version updated for https://github.com/snapsynapse/harnessie-verify-action to version 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 The harnessie-verify-action claims-by-claim verification of pull requests, automating deterministic checks against actual artifacts and providing a review interface. It solves problems related to ensuring code correctness through automated testing and reduces reliance on untrusted diffs by running verifiers in sandboxed environments. The action is powered by Harnessie and supports OpenAI-compatible endpoints for model inference, ensuring security and compliance with GitHub’s protection mechanisms.