xonecas.io

coder-skills

A collection of agent skills compliant with the agentskills.io open spec

post-AI small skills

6 commits · 2026-03-31 to 2026-04-11 · 9 files

xonecasAdd human-writing skillaacc6382026-04-11
▸ code-review/ 2026-03-31
▸ human-writing/ 2026-04-11
▸ programming-practices/ 2026-04-09
▸ systematic-debugging/ 2026-03-31
▸ testing-practices/ 2026-04-08
· AGENTS.md 2026-04-08
· README.md 2026-04-11

README.md

coder-skills

A collection of agent skills compliant with the agentskills.io open spec.

Skills

Skill Description
code-review Thorough, structured code review with severity-tiered findings
human-writing Teach agents to write in a natural, specific, human-sounding voice instead of AI-generic prose
programming-practices Write and modify production code with strong engineering practices and safeguards against AI-specific failure modes
systematic-debugging Hypothesis-driven bug diagnosis and resolution
testing-practices Write and review tests following proven testing practices, with safeguards against AI-specific blind spots

Usage

Copy or symlink a skill directory into one of the standard discovery paths:

# Project-level (any agent)
<project>/.agents/skills/

# Project-level (client-specific)
<project>/.<client-name>/skills/

# User-level (any agent)
~/.agents/skills/

# User-level (client-specific)
~/.<client-name>/skills/

Any agent that supports the agentskills.io spec will discover and load skills from these locations.

Skill structure

Each skill is a directory containing a SKILL.md file with YAML frontmatter and markdown instructions:

skill-name/
├── SKILL.md        # Required: metadata + instructions
├── scripts/        # Optional: executable scripts
├── references/     # Optional: additional documentation
├── assets/         # Optional: templates, schemas, data files
└── evals/          # Optional: test cases

License

MIT