A guide for building accessible and multilingual software. Accessibility means making interfaces usable with tools such as keyboards and screen readers; internationalisation prepares them for different languages, regions, and writing directions.
An architecture guide for AI agent systems, including how agents choose routes, call tools, manage context, remember information, and handle state. It also covers permissions, human involvement, monitoring, replay, and governance.
An AI evaluation engineering specialist for testing models and prompts. The description does not provide enough detail to state which concrete operations it performs.
A default, read-only analysis workflow that prioritises facts found in the code. It uses related investigations and convergence checks to validate conclusions.
An architecture guide for public APIs, including HTTP services, software-development kits, command-line tools, schemas, types, errors, pagination, filtering, and compatibility.
An API verification workflow that creates both an .http request file and a .cjs JavaScript file, then runs an automation script to test them. An API is an interface through which software exchanges requests and responses.
A shared baseline audit check covering dimensions named G0G5 and a profile-freshness check. The available description does not explain what those dimensions measure.
A set of review checks for README files, architecture documents, and developer guides. The available description lists the review categories but does not explain their individual checks.
An execution-review guide for checking coding work in prioritized batches and targeted subsets. Its excerpt does not provide more detail about the checks it performs.
An engineering review skill covering twelve project-audit areas. The listed areas include code quality, project structure, dependency safety, and resource leaks.
A review checklist for README files and user documentation, focused on how people start, follow examples, configure the software, troubleshoot it, and move through the documented usage path.
A report-review skill described only as covering review dimensions RA-1 through RA-6. The supplied information does not explain what those dimensions assess.
A review guide for checking requirements documents, from the initial definition through functional details and verifiable facts. It also distinguishes what can be tested directly from what must be derived from the requirements.
A workflow for keeping the state of an audit between coding sessions. It stores audit rounds, findings, and whether the review has converged in JSON files under /.audit-state/.
A review workflow for documentation used by end users and developers. It covers README files, documentation sites, setup guides, navigation, configuration, troubleshooting, and the path users follow to complete real tasks.
A review guide for backend and business-domain design. It examines business rules, workflows, permissions, APIs, transactions, consistency, repeated requests, compatibility, data boundaries, and service responsibilities.
A review guide for checking how a technical product or feature creates and supports business value. It covers pricing, costs, revenue, sales channels, operations, and long-term viability.
An entry check and compliance-validation skill for a process with PC0–PC10 checks and FC, SC, RC, and T rules. The description does not explain what those abbreviations mean.
A validation workflow for checking a software package across separate repositories. It covers SDKs, command-line tools, frameworks, and shared packages using both linked source code and the packaged artifact users install.