skills

Jon Hill's public collection of portable [Agent

Skills](https://agentskills.io/specification) — self-contained,

model- and harness-agnostic instructions an AI coding agent loads on

demand. Every skill here is individually installable; nothing in this

repository is specific to any one harness, and nothing here depends on

private tooling or evidence.

Install

Browse the collection:

npx skills add jonhill90/skills --list

Install one or more specific skills into the current project:

npx skills add jonhill90/skills --skill tmux --skill github-cli

`npx skills` pins installs by content hash in `skills-lock.json`, so a

project's skill set stays reproducible. See the [skills

CLI](https://www.npmjs.com/package/skills) for the full command

reference.

As an Agent Plugin

This repository is also an [Agent Plugins

1.0.0](https://agent-plugins.org/specification) plugin: `plugin.json` at the

root, 40 skills at `skills//SKILL.md` (measured `ls -d skills/*/ | wc -l`,

verified 2026-08-23), which is the standard's own discovery convention.

Any conformant client can consume the collection whole, with no bespoke

tooling.

That is a portability claim, not a local one. Claude Code reads its own

manifest at `.claude-plugin/plugin.json` and does not look for this file, so

adding it changed nothing for Claude Code users today. `npx skills` above

remains the way to install individual skills, and nothing here replaces it.

Skills in this collection

All 40, flat and alphabetical — matching `skills/`'s own layout (see

Where a skill belongs for why this repository does

not bucket by category). Measured `ls -d skills/*/`, verified 2026-08-23.

This table has drifted from the tree twice: 12 skills short for five days

(`069e2c4`, 2026-08-09) and, a second time, 13 skills short until this

correction (skills#224) — `scripts/validate_repository.py`'s

`validate_readme_table` check now fails CI when the table and `skills/`

disagree, so a hand-edit that drops or misnames a row is caught before it

reaches the public repository.

Each skill's `description` frontmatter is the actual trigger contract —

read the skill itself for exact wording and preconditions. This repository

does not yet distinguish user-invoked from model-invoked skills anywhere a

reader sees before opening `SKILL.md` — tracked as open in

`docs/skills-docs-proposal-161.md`.

Where a skill belongs

Most skills should not live in this repository. Decide placement

first:

Authoring contract

Each skill lives at `skills//SKILL.md`:

skills/example-skill/
├── SKILL.md
├── scripts/       Optional deterministic, tested helpers
├── references/    Optional detail loaded on demand
└── assets/        Optional output resources

Portable frontmatter is `name` and `description` (plus optional

`license`, `compatibility`, `metadata`, `allowed-tools`). The directory

name must match `name`. Keep `SKILL.md` under 500 lines and move detail

into directly linked `references/`. Full conventions: AGENTS.md.

Validate

python3 scripts/validate_repository.py
python3 -m unittest discover -s tests -v

CI runs both on every pull request and on pushes to `main`.

Content boundaries

• This repository holds only portable skill content and the minimal

validation/tests/CI needed to keep it correct.

• Personal harness configuration — canonical instructions, hooks,

agents, settings, MCP declarations, install/sync tooling — lives in a

separate personal harness repository that consumes this collection; it

is not vendored here.

• Behavioral evaluation methodology, scenarios, transcripts, and results

are private and are not published in this repository. Where a skill

references past evidence, it states what happened and when without a

link to private material.

• Employer-owned or project-specific material is never copied here.

See AGENTS.md for contribution rules.