🧩 Codely Skills

A collection of reusable skills for AI coding agents, following Codely's conventions and workflows.

⚡ Quickstart

1. Install the skills with the skills.sh installer:

   npx skills@latest add codelytv/skills

2. Pick the skills you want and the coding agents you want to install them on.

3. Run a skill in your agent, for example /doc-create.

4. Done. Your agent now follows Codely's conventions.

🗂️ Skills

Skills are grouped by category under skills/:

📃 Harness (skills/harness/)

Skill	What it does
doc-create	Generates convention documentation from the current conversation, turning feedback and corrections into reusable docs.

Two ways to use doc-create:

• After a conversation: run /doc-create to turn the corrections the agent received during the session into a new doc.
• Before a conversation: run /doc-create <description> to formalize a convention you want to document upfront.

🗺️ RPI (skills/rpi/)

Skill	What it does
plan-create	Breaks a task into reviewable phases (vertical slices), defines the public contracts to change, and saves an approved plan file.
plan-implement-phase	Executes a single phase of a plan at a time, updates its checkboxes, and stops for review without committing automatically.

Typical flow:

• Plan the work with /plan-create <task> to produce a phased plan file under .agents/plans/.
• Implement it phase by phase with /plan-implement-phase <plan-file-path>, reviewing and committing after each one.

🔀 Git (skills/git/)

Skill	What it does
git-commit	Creates a Git commit following the team's Conventional Commits conventions, scope, and co-author trailer.

Run /git-commit to stage and commit your changes with a conventional message, or /git-commit <message> to use your own.

🚀 Usage

Point your AI agent to this repository's skills directory so the agent can discover and load them. Then invoke a skill:

• Automatically: the agent picks the right skill when a task matches its description.
• Explicitly: type /<skill-name> (for example, /doc-create) to run it on demand.

🎓 Learn more

Learn more about AI-assisted programming in the Agentic AI Programming: Practical Foundations course.