EarthChen/ai-assets

EarthChen/ai-assets

Skill Claude CodeCodex

Part of earthchen-ai-assets

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

EarthChen/ai-assets

Skill Claude CodeCodex

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

Part of earthchen-ai-assets

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

EarthChen/ai-assets

Skill Claude CodeCodex

Part of earthchen-ai-assets

Repo-wide entropy reclamation — prove and safely remove dead code, duplicate representations, speculative generality, and over-engineering.

EarthChen/ai-assets

Skill Claude CodeCodex

Part of earthchen-ai-assets

Ship each project's feature branch in a multi-project workspace to a test-environment branch — commit and push the feature branch, merge into the target branch (test by default), push it (triggers CI/CD), switch back. Manual invocation.

EarthChen/ai-assets

Skill Claude CodeCodex

Part of earthchen-ai-assets

Create new skills, improve existing skills, and measure skill performance with evals and benchmarks. Use when creating, editing, optimizing, or evaluating a skill.

EarthChen/ai-assets

Skill Claude CodeCodex

Part of earthchen-ai-assets

Cross-stack testing principles — unit/integration/E2E boundaries, sociable vs solitary unit tests, narrow integration tests, isolation rules, F.I.R.S.T, naming, mocking schools, flaky prevention. Reference material consumed by the language development skills.

EarthChen/ai-assets

Skill Claude CodeCodex

Part of earthchen-ai-assets

TypeScript/Node backend development conventions — testing conventions (vitest/jest, supertest, testcontainers-node), mock boundaries. Use when writing or reviewing TypeScript backend code.