xonecas.io
696
Cs

coder-skills / commit 331f684

Add CLAUDE.md and README.md

Project instructions and readme with skill listing, usage docs,
and contribution conventions.

xonecas2026-03-31 331f6841888da24f143c797697edfb57c2bd42cd parent 148febe

2 files changed

CLAUDE.md+22−0
@@ -0,0 +1,22 @@
1+# CLAUDE.md
2+
3+This repo contains agent skills that follow the [agentskills.io](https://agentskills.io) open spec.
4+
5+## Structure
6+
7+Each skill is a top-level directory named after the skill, containing a `SKILL.md` file. The directory name must match the `name` field in the SKILL.md frontmatter.
8+
9+## Conventions
10+
11+- Skills must be compliant with the agentskills.io spec
12+- SKILL.md frontmatter requires: `name`, `description`
13+- SKILL.md body should stay under 500 lines / 5,000 tokens
14+- Move detailed reference material to `references/` subdirectory
15+- Scripts go in `scripts/` and should be self-contained, non-interactive, and produce structured output (JSON/CSV to stdout, diagnostics to stderr)
16+- Description field should use imperative phrasing ("Use when...") and list trigger contexts explicitly
17+
18+## Adding a new skill
19+
20+1. Create a directory: `skill-name/`
21+2. Add `SKILL.md` with YAML frontmatter (`name`, `description`) and markdown instructions
22+3. Update the skills table in `README.md`
README.md+46−0
@@ -0,0 +1,46 @@
1+# coder-skills
2+
3+A collection of agent skills compliant with the [agentskills.io](https://agentskills.io) open spec.
4+
5+## Skills
6+
7+| Skill | Description |
8+|-------|-------------|
9+| [code-review](code-review/) | Thorough, structured code review with severity-tiered findings |
10+
11+## Usage
12+
13+Copy or symlink a skill directory into one of the standard discovery paths:
14+
15+```
16+# Project-level (any agent)
17+<project>/.agents/skills/
18+
19+# Project-level (client-specific)
20+<project>/.<client-name>/skills/
21+
22+# User-level (any agent)
23+~/.agents/skills/
24+
25+# User-level (client-specific)
26+~/.<client-name>/skills/
27+```
28+
29+Any agent that supports the agentskills.io spec will discover and load skills from these locations.
30+
31+## Skill structure
32+
33+Each skill is a directory containing a `SKILL.md` file with YAML frontmatter and markdown instructions:
34+
35+```
36+skill-name/
37+├── SKILL.md # Required: metadata + instructions
38+├── scripts/ # Optional: executable scripts
39+├── references/ # Optional: additional documentation
40+├── assets/ # Optional: templates, schemas, data files
41+└── evals/ # Optional: test cases
42+```
43+
44+## License
45+
46+MIT