Use when implementing features or writing code. TDD enforcement is opt-in via --tdd / MEOWKIT_TDD=1. Provides code patterns, skill loading, and coding standards.
Scanned 5/29/2026
Install via CLI
openskills install ngocsangyem/MeowKit---
name: mk:development
description: "Use when implementing features or writing code. TDD enforcement is opt-in via --tdd / MEOWKIT_TDD=1. Provides code patterns, skill loading, and coding standards."
keywords: [development, feature-implementation, tdd-optional, coding-standards, skill-loading]
when_to_use: "Use when implementing features or writing code. TDD opt-in via --tdd. NOT for orchestrated pipelines (see mk:cook)."
user-invocable: true
---
# Development Toolkit
Reference guides for implementation: code patterns, TDD enforcement (opt-in), and skill lazy-loading.
## When to Use
- During Phase 3 (Build) for implementation guidance
- When the `developer` agent needs coding pattern references
- For TDD enforcement rules during red/green/refactor cycle (TDD mode only)
## Workflow Integration
Operates in **Phase 2 (Test)** and **Phase 3 (Build)**. Output supports the `developer` and `tester` agents.
TDD enforcement (`tdd-enforcement.md` reference) is OPT-IN as of the TDD-optional migration. Default mode skips RED-phase enforcement; enable with `--tdd` or `MEOWKIT_TDD=1`.
## References
| Reference | When to load | Content |
|-----------|-------------|---------|
| **[code-patterns.md](./references/code-patterns.md)** | During implementation | Coding patterns, architecture patterns, file organization |
| **[tdd-enforcement.md](./references/tdd-enforcement.md)** | Phase 2-3 | RED/GREEN/REFACTOR cycle, test-first rules, coverage requirements |
| **[skill-loader.md](./references/skill-loader.md)** | Skill activation | How to load skills on-demand, lazy loading patterns |
## Gotchas
- **TDD enforcement blocking exploratory prototyping**: Strict red-green cycle slows rapid iteration → Default mode (TDD off) is now the right choice for prototypes; opt into `--tdd` only when shipping production-quality work
- **200-line file rule on generated code**: Auto-generated files (migrations, schemas) exceed limit by design → Exempt generated files explicitly in plan constraints
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.