EarthChen

EarthChen/ai-assets

Agent

Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, and documenting dependencies to inform new development.

EarthChen/ai-assets

Agent

Execution agent for the code-audit skill. Runs the three-axis code audit (Standards+Spec compliance + language-specific trap detection + cross-language review lenses: silent failure, type design, security). Invoke when the user asks for a deep code audit of a branch, PR, file, or module. For a quick diff review…

EarthChen/ai-assets

Agent

Simplifies code inside one git scope — uncommitted changes, recent commits, or a full PR/MR diff — for clarity, consistency, and maintainability while preserving exact behavior. Use PROACTIVELY after writing or modifying a logical chunk of code, or during review when complexity is flagged. For whole-repo dead-code…

EarthChen/ai-assets

Agent

End-to-end testing specialist for web frontends and backend APIs. Detects the target (browser app or service) and existing test stack, then picks the right tools. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos…

EarthChen/ai-assets

Agent

Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Automatically detects Spring Boot or Quarkus and applies framework-specific fixes. Fixes build errors, Java compiler errors, and Maven/Gradle issues with minimal changes. Use when Java builds fail.

EarthChen/ai-assets

Agent

Operate autonomous agent loops, monitor progress, and intervene safely when loops stall.

EarthChen/ai-assets

Agent

Language-agnostic performance analysis and optimization specialist. Use PROACTIVELY for identifying bottlenecks, optimizing slow code, reducing bundle sizes, and improving runtime performance. Profiling, memory leaks, render optimization, and algorithmic improvements across frontend and backend.

EarthChen/ai-assets

Agent

Refactoring and dead code cleanup specialist. Use PROACTIVELY to remove unused code/exports/dependencies, eliminate duplicates, and structurally refactor complex code into clean, maintainable systems — all while preserving existing behavior.

EarthChen/ai-assets

Agent

Extracts behavioral specs from existing codebases for OpenSpec. Produces flat Requirement and Invariant blocks with structured metadata (entities, enforced, id, test anchors). Outputs openspec/specs/ /spec.md. Fully self-bootstrapping — no dependency on codebase-onboarding. Use when onboarding a brownfield project to…

EarthChen/ai-assets

Agent

Fast read-only search agent for locating code. Use it to find files by pattern (e.g. "src/components//.tsx"), grep for symbols or keywords (e.g. "API endpoints"), or answer "where is X defined / which files reference Y." NOT for code review, design-doc auditing, cross-file consistency checks, or open-ended analysis …

EarthChen/ai-assets

Skill Claude CodeCodex

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

EarthChen/ai-assets

Skill Claude CodeCodex

Agent & skill routing: architect vs code-architect boundaries, security review, build failures, parallel subagent fan-out. Use for architectural decisions, security-sensitive code, build breaks, or multiple independent explore/review tasks.

EarthChen/ai-assets

Skill Claude CodeCodex

Deep, systematic code audit along three axes — Standards compliance, Spec fidelity against a diff, and language traps + cross-language review lenses (silent failure, type design, security). Dispatches three parallel sub-agents directly; never nested. For a quick diff review against general code smells, use the…

EarthChen/ai-assets

Skill Claude CodeCodex

Pre-completion quality gate: security incident response, code quality checklist, test-type selection, review criteria and severity. Use before marking work done, before commits/reviews, or when a security issue is discovered.

EarthChen/ai-assets

Skill Claude CodeCodex

Simplify code inside one git scope (uncommitted changes, recent commits, or a full PR/MR diff) while preserving exact behavior.

EarthChen/ai-assets

Skill Claude CodeCodex

E2E testing patterns — web frontends (Playwright: Page Object Model, configuration, CI/CD integration, artifact management, flaky test strategies) and backend APIs (three-layer assertions, auth fixtures, data isolation, schema validation).

EarthChen/ai-assets

Skill Claude CodeCodex

Feature development pipeline: plan → TDD → simplify → review → commit (grill-with-docs → to-spec → to-tickets → tdd → code-review skills). Use when starting a feature or fix.

EarthChen/ai-assets

Skill Claude CodeCodex

Git conventions: Conventional Commits, GitHub Flow branching, PR process, worktrees. Use when committing code, opening a PR, or using worktrees.

EarthChen/ai-assets

Skill Claude CodeCodex

Multi-platform Herdr swarm orchestration: a bounded pool of pi / Claude Code / Codex worker panes working a goal, spec, or tickets. Manual invocation; requires HERDRENV=1. Invocation args: kind= thinking= workers=.

EarthChen/ai-assets

Skill Claude CodeCodex

Java development conventions (Spring Boot / Quarkus) — coding standards, architecture patterns, TDD, pre-release verification, build error troubleshooting. Use when writing or reviewing Java code, or when a Java build fails.

EarthChen/ai-assets

Skill Claude CodeCodex

Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local…

EarthChen/ai-assets

Skill Claude CodeCodex

Initialize and maintain a project's AGENTS.md, CLAUDE.md, and README.md so they faithfully express the project's current state.

EarthChen/ai-assets

Skill Claude CodeCodex

Python development conventions — idioms, type hints, project structure, pytest testing with TDD. Use when writing or reviewing Python code.

EarthChen/ai-assets

Skill Claude CodeCodex

React/TSX development conventions — coding style, component architecture patterns, security, RTL testing. Use when writing or reviewing React/TSX components or hooks.