Use when a workflow asks the user to copy, edit, approve, restart, configure, repair, or verify steps that software may be able to perform.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add ShugokiFable/Ultimate-AI-Starter-Bundle --skill automation-first --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Automation First?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/shugokifable-automation-first-20c6a939)More formats (shields.io, HTML) on the badges page.
---
name: automation-first
description: Use when a workflow asks the user to copy, edit, approve, restart, configure, repair, or verify steps that software may be able to perform.
---
# Automation First
## Core rule
Every required **manual step** is a potential failure point. **Automate** deterministic setup and verification when the platform provides a safe interface.
## Decision
Automate when the action is deterministic, scoped, reversible or verifiable, and supported by a CLI/API/config contract. Preserve an explicit **fallback** only for capabilities that truly cannot be automated safely.
Good automation:
- detects existing state;
- preserves user config;
- is idempotent;
- checks exit codes;
- verifies the result;
- fails with an actionable reason.
Bad automation guesses undocumented schemas, disables security globally, or hides failures behind warnings.
Documentation should describe what automation did and how to recover—not offload routine machine work back to the user. If a fresh install still says “now manually edit/copy this”, treat it as an engineering gap and investigate first.
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.
