Make and document a consequential software architecture decision using constraints, alternatives, tradeoffs, boundaries, failure modes, migration, and validation.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add Dadmin88/hermes-profile-packs --skill architecture-decision --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Architecture Decision?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dadmin88-architecture-decision)More formats (shields.io, HTML) on the badges page.
---
name: architecture-decision
description: Make and document a consequential software architecture decision using constraints, alternatives, tradeoffs, boundaries, failure modes, migration, and validation.
---
# Architecture Decision
Use when a decision affects multiple components, durable interfaces, dependency direction, protocol, persistence strategy, or future change cost.
## Procedure
1. State the problem and forces: product needs, constraints, scale, reliability, security, team/runtime realities, and existing architecture.
2. Identify the decision boundary and what is deliberately not being decided.
3. Generate credible alternatives, including preserving the current design where applicable.
4. Compare alternatives on the forces that matter rather than generic pros/cons.
5. Define the chosen boundaries, interfaces, data/control flow, ownership, and failure behavior.
6. Plan migration and compatibility if existing callers/data are affected.
7. Record consequences, risks, and conditions that would justify revisiting the decision.
8. Validate risky assumptions with a spike, benchmark, prototype, or primary documentation where useful.
## Quality gate
An architecture decision must make downstream implementation clearer and acknowledge the costs it introduces.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!
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', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
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.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling