A bare-minimum Logion course example. Use as a starting template when authoring a new skill that needs no tools, no network, no filesystem writes, and no env vars. Demonstrates the smallest valid SKILL.md plus capabilities.yaml pairing.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add nicolasmelo1/logion --skill minimal --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Minimal?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nicolasmelo1-minimal)More formats (shields.io, HTML) on the badges page.
---
name: minimal
description: A bare-minimum Logion course example. Use as a starting template when authoring a new skill that needs no tools, no network, no filesystem writes, and no env vars. Demonstrates the smallest valid SKILL.md plus capabilities.yaml pairing.
license: MIT
---
# Minimal Logion Course
This is the smallest valid Logion course. It exists as a copy-paste starting point.
## What this course does
Nothing meaningful — it returns the literal string `"hello from minimal logion course"` when an agent reads it.
## Structure
```
minimal/
├── SKILL.md # this file
└── course/
└── capabilities.yaml # near-empty Logion manifest
```
No `scripts/`, no `references/`, no `assets/`. Add those when your real course needs them.
## When to use this
When you're starting a new course and want a known-good skeleton that already validates against both:
- the agentskills.io SKILL.md frontmatter spec
- the Logion `course/capabilities.yaml` schema
Copy this whole directory, rename it, edit `SKILL.md` and `course/capabilities.yaml`, then run `logion course validate ./your-course/` before uploading.
## What an agent should do here
Nothing — this skill has no behavior. Real skills go in their body where this paragraph is.
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', ...
**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.