Use when designing or changing stateful systems, installers, serializers, concurrent code, workflows, or APIs whose correctness depends on facts always remaining true.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add ShugokiFable/Ultimate-AI-Starter-Bundle --skill invariant-driven-design --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Invariant Driven Design?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/shugokifable-invariant-driven-design-0283a9e5)More formats (shields.io, HTML) on the badges page.
---
name: invariant-driven-design
description: Use when designing or changing stateful systems, installers, serializers, concurrent code, workflows, or APIs whose correctness depends on facts always remaining true.
---
# Invariant-Driven Design
## Core rule
Define what must always remain true before choosing implementation details.
Write each important **invariant** as a checkable statement: one active registration per provider, manifest hashes match final bytes, a failed install never prints success, user config survives repair, or a lock has one owner.
Place enforcement at the narrowest **boundary** where invalid state can enter or leave. Tests should attempt a direct **violation** and prove it is rejected or repaired.
Prefer a small number of strong invariants over many procedural reminders. If correctness requires every caller to remember five steps in order, move those steps behind an interface or automated gate that preserves the invariant by construction.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
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', ...
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.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**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. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.