api-and-namespace-design
API design conventions, namespace coordinate system, RBAC roles, ClawHub compatibility layer, OpenAPI contract sync rules, and CSRF/session handling.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
API design conventions, namespace coordinate system, RBAC roles, ClawHub compatibility layer, OpenAPI contract sync rules, and CSRF/session handling.
Rules for the SkillHub backend Maven multi-module clean architecture. Ensures agents place new code in the correct module and respect dependency direction.
Code style, logging, and testing conventions for SkillHub backend (Java) and frontend (TypeScript). Use when writing or reviewing code.
Coding conventions, architecture patterns, and testing rules for the SkillHub React frontend. Ensures agents follow Feature-Sliced Design and use the generated OpenAPI types.
PR title format, commit conventions, and pre-PR checklist for SkillHub. Use when preparing or reviewing pull requests.
Testing conventions, CI pipeline rules, and smoke test coverage for SkillHub. Ensures agents write tests correctly and understand the CI gate requirements.
Use when adding, updating, pinning, or reviewing any dependency in this repo's requirements/*.txt files, including taking a Dependabot bump or writing a requirement line by hand. Also use when a pip install fails on the older Python jobs while newer ones pass, or when CI errors with "Could not find a version that satisfies", "No matching distribution found", "Requires-Python >=3.x", or "ResolutionImpossible". Triggers include: "add <package> to requirements", "bump/update <package>", "pin <package>", "fix this dependabot PR", "CI can't install <package> on Python 3.7/3.8/3.9", "requires-python error in the install step". This skill defines the layout and version-constraint conventions to follow; reach for it before hand-editing any requirements/*.txt file.
Operates TscanPlus security scanner via MCP tools or CLI for authorized targets only. Use when the user mentions TscanPlus, port/URL/POC/subdomain scanning, MCP integration, ip_scan, tscan_scan, or recon on IPs, domains, or URLs in any AI assistant with MCP support.
Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when writing a benchmark paper, structuring a benchmark paper, checking whether a benchmark idea is substantive, drafting a benchmark Introduction, or planning the data-construction pipeline or experiments.