Implement a bounded end-to-end feature slice across UI, API, domain logic, and persistence while preserving contracts and avoiding unnecessary cross-system redesign.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add Dadmin88/hermes-profile-packs --skill vertical-slice --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Vertical Slice?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dadmin88-vertical-slice)More formats (shields.io, HTML) on the badges page.
---
name: vertical-slice
description: Implement a bounded end-to-end feature slice across UI, API, domain logic, and persistence while preserving contracts and avoiding unnecessary cross-system redesign.
---
# Vertical Slice
Use when a cohesive feature is small enough for one engineer to own across frontend and backend boundaries.
## Procedure
1. Confirm product behavior and architecture boundaries; identify where specialist review is still required.
2. Trace the complete current path from user action to persistence/external effects and back.
3. Define the minimal interface/data changes needed to deliver one coherent outcome.
4. Implement from contract inward, keeping validation and authorization on appropriate server boundaries.
5. Preserve transactional/data consistency and handle user-visible failure/retry behavior.
6. Add tests at each layer only where they provide distinct confidence, plus an integration or E2E proof of the slice.
7. Validate the complete flow in a representative environment.
## Quality gate
Full-stack ownership is not permission to bypass architecture, security, design, or review authority. Escalate cross-cutting decisions to the relevant specialist.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