Browse Skills

Automatically extracts and verifies Chinese legal citations (statutes, articles, cases) against authoritative databases, returning accuracy judgments. Acts as a mandatory quality gate for formal legal documents or a standalone citation checker.

Use when designing or reviewing an HTTP API. Covers resource modeling, status codes, pagination, idempotency, versioning, error formats, and the contract details that break clients when you get them wrong.

Build Django applications with efficient ORM usage, secure settings, and safe migrations. Use when developing or reviewing Django apps, APIs, or database designs.

Simulates multi-perspective academic review (journal, thesis blind review, defense committee) with scored evaluations and typical critique points, helping authors pre-test manuscripts before submission or defense.

Verifies citation existence via real API calls, checks reference format against GB/T 7714, and analyzes claim exaggeration. Produces a detailed report for pre-submission paper self-inspection.

Checks if a research method can answer a given research question, guides methodology selection, and forces ethical review reminders for human-subject research. Designed for academic writing and thesis design.

Run four pass/fail diagnostic scripts to troubleshoot ROS 2 Jazzy issues like QoS mismatches, TF frame errors, IMU gravity misalignment, and odometry direction discrepancies. Use when code inspection alone can't pinpoint the fault.

Use when reviewing or improving an existing agent skill. Covers triggering accuracy, content quality, redundancy with the base model, and measuring whether the skill actually changes behavior.

Initialize, develop, fix, refactor, and deliver Python projects with auditable specification-driven development (SDD), strict TDD, and secure Git gates. Use for tasks that modify source code, tests, specs, dependencies, or Git history.

Multi-reviewer peer-review system that simulates an editorial panel for food and nutrition manuscripts, grounding critiques in cited sources and field literature. Use before submission for a rigorous check.

Reviews code changes since a fixed point along two independent axes: coding standards compliance and spec/issue fidelity. Runs both reviews in parallel sub-agents and reports findings side by side. Ideal for reviewing branches, PRs, or work-in-progress changes.

A shared vocabulary and principles for designing deep, testable modules with small interfaces and high leverage. Use when designing or improving module interfaces, deciding where to place seams, or making code more maintainable and AI-navigable.