xiaolai
Community@xiaolai · beijing
A lifelong student.
Agent Skills by xiaolai
Showing 43 vetted skills indexed across 8 GitHub repositories.
init
Detects test lanes, verifies them by dry-run probe, and writes the TDD Guardian lane configuration.
lane-policy
Assigns test behaviors to unit, integration, e2e, or contract lanes with trigger and coverage rules.
test-matrix
Builds a test matrix with assertion strategy, lane, and spec level per case.
tooling-catalog
Catalogs test runners, coverage tools, and probe commands across programming language ecosystems.
coverage-gate
Enforce merged coverage thresholds and behavioral test quality across test lanes.
policy-core
Enforces behavior-driven test quality rules and completion gates for test-driven development.
workflow
Orchestrates seven TDD subagents through planning, testing, implementation, and gated review stages.
mutation-gate
Validate test strength with mutation testing across twelve language-specific tools.
review-gate
Produces severity-ordered code review findings with test-quality and missing-test audits.
conventions-codex
Enforces Codex CLI artifact layout, manifests, and hook conventions for Tier 2-Codex scoring.
conventions-claude
Validate Claude Code plugin artifacts against schema and path conventions.
conventions-antigravity
Standardize Antigravity and Gemini CLI artifact scoring with tool-specific conventions.
vocabulary
Enforce a canonical noun-and-verb registry for naming NLPM artifacts.
claude-code-conventions
Reference Claude Code plugin artifact conventions for audits and development prompts.
writing-hooks
Design and validate Claude Code hooks with event types and matcher patterns.
writing-rules
Automate creation and governance of CLAUDE rules in .claude/rules.
writing-plugins
Document architectural best practices for Claude Code plugin development and publishing.
writing-agents
Define authoring standards for Claude Code agents with structured output schemas.
testing
Automate test-driven development workflows for NL artifacts using .nlpm-test spec files.
writing-prompts
Structure prompts with a five-layer Role, Context, Task, Constraints, and Output framework.
orchestration
Coordinates multi-agent workflows for Claude Code deployments.
scoring
Compute 100-point quality scores for NL programming artifacts using predetermined penalties.
rules
Enforce R01–R50 quality rules on NL programming artifacts.
writing-skills
Standardize SKILL.md files with frontmatter schema and structured body sections.
Frequently Asked Questions About xiaolai
FAQPage SchemaWhat tasks can I accomplish using xiaolai's skills?▼
You can enforce TDD governance with plan-first policies, build test matrices with per-case assertion strategies, run mutation testing across nine language ecosystems, validate Claude Code plugin artifacts against conventions, score NL programming artifacts on a 100-point scale, and map source code to documentation frameworks.
Who should use xiaolai's skill collection?▼
Software engineers practicing strict TDD, Claude Code plugin developers needing artifact validation, and documentation maintainers working with MkDocs, VitePress, Docusaurus, or Sphinx. It also serves teams auditing test quality across Python, Go, Rust, TypeScript, JVM, PHP, Ruby, and Swift codebases.
How does the TDD workflow skill operate in practice?▼
The workflow skill orchestrates planner, test designer, spec adversary, implementer, coverage auditor, mutation auditor, and reviewer subagents. The init skill first detects test lanes via dry-run probes and writes lane configuration, then coverage-gate and mutation-gate enforce thresholds and assertion strength.
Which mutation testing frameworks are supported?▼
The mutation-gate skill covers the Stryker family for JS/TS, .NET, and Scala; PIT for JVM; Infection for PHP; mutmut and cosmic-ray for Python; go-mutesting and gremlins for Go; cargo-mutants for Rust; mutant for Ruby; and muter for Swift, reporting weak assertions.
What prerequisites are needed to use these skills?▼
Skills are designed for Claude Code environments with plugin, hook, and rules support. TDD skills require a repository with detectable test runners and coverage tooling per the tooling-catalog, while documentation skills require MkDocs, VitePress, Docusaurus, Sphinx, or plain Markdown project structures.