Updated 1w ago
by nicolasmelo1
logion
"Does this actually work with my agent?" An open, versioned registry of AI-agent artifacts: skills, plugins, MCP servers, models, etc. with provenance and evidence attached, published over open protocols.
39 GitHub stars (39)
+1 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | +1 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 16 skills (16 skills found in its SKILL.md files)
- 3 forks (3 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add nicolasmelo1/logion
Asks which skills and agents to install. Just one: npx skills add nicolasmelo1/logion --skill logion — add -g for every project.
Claude Code
git clone https://github.com/nicolasmelo1/logioncp -r "logion/packages/agent-companion" ~/.claude/skills/
Copies the logion skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add nicolasmelo1/logion
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
logion
Compact bootstrap skill for recall-first Logion discovery, inspection, install, update, and creator-course-management routing without loading the whole marketplace.
packages/agent-companion/SKILL.md on GitHub (opens in a new tab) -
minimal
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.
examples/courses/minimal/SKILL.md on GitHub (opens in a new tab) -
with-eval
Reviews code diffs against a structured checklist covering security (sql-injection, hardcoded-secret, unvalidated-input), reliability (missing-error-handling, resource-leak), and correctness (off-by-one, wrong-comparison). Use when reviewing PRs, audit diffs, or any code change where you want a categorised, line-anchored review instead of free-form prose. Ships with a bundled deterministic self-t…
examples/courses/with-eval/SKILL.md on GitHub (opens in a new tab) -
with-paid
Paid-course example showing how to package a self-contained Logion bundle with the marketplace paid license. Use as a starting point when you want a benign course that reads local artifacts, produces a structured report, and exercises the paid publication path end to end.
examples/courses/with-paid/SKILL.md on GitHub (opens in a new tab) -
with-references-and-scripts
Logion course example that bundles a runnable script and a reference doc. Use as a starting template when your skill executes a small subprocess (terminal tool) and produces output files. Demonstrates progressive disclosure across SKILL.md, references/, and scripts/.
examples/courses/with-references-and-scripts/SKILL.md on GitHub (opens in a new tab) -
with-scripts
Bundled Gmail CLI example demonstrating the scripts/ entrypoint + src/ implementation split. Use as a template when your course ships real code that goes beyond a single shell script. Shows how to organize a course bundle that owns its codebase — no runtime package installation, all dependencies stdlib-only. Replaces the "tell the user to npm install my CLI" anti-pattern.
examples/courses/with-scripts/SKILL.md on GitHub (opens in a new tab) -
clean_course
No description in the SKILL.md.
packages/scanners/tests/fixtures/clean_course/SKILL.md on GitHub (opens in a new tab) -
dangerous_commands
No description in the SKILL.md.
packages/scanners/tests/fixtures/dangerous_commands/SKILL.md on GitHub (opens in a new tab) -
env_harvesting
No description in the SKILL.md.
packages/scanners/tests/fixtures/env_harvesting/SKILL.md on GitHub (opens in a new tab) -
file_type
No description in the SKILL.md.
packages/scanners/tests/fixtures/file_type/SKILL.md on GitHub (opens in a new tab) -
network_audit
No description in the SKILL.md.
packages/scanners/tests/fixtures/network_audit/SKILL.md on GitHub (opens in a new tab) -
obfuscation
No description in the SKILL.md.
packages/scanners/tests/fixtures/obfuscation/SKILL.md on GitHub (opens in a new tab) -
prompt_injection
No description in the SKILL.md.
packages/scanners/tests/fixtures/prompt_injection/SKILL.md on GitHub (opens in a new tab) -
runtime_install
No description in the SKILL.md.
packages/scanners/tests/fixtures/runtime_install/SKILL.md on GitHub (opens in a new tab) -
secrets_detection
No description in the SKILL.md.
packages/scanners/tests/fixtures/secrets_detection/SKILL.md on GitHub (opens in a new tab) -
fixture-skill
No description in the SKILL.md.
packages/cli/tests/fixtures/capabilities/invalid_bundle/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.