Adonis0123/adonis-skills / .agents/skills/repo-skill-creator
repo-skill-creator
VerifiedCreate and maintain repository skills for adonis-skills. Use when users ask to scaffold a new skill under skills/, generate agents/openai.yaml, run skill validation, refresh web index data, or standardize the skill authoring workflow.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.4 KB |
| evals/evals.json | config | 4.0 KB |
| references/openai_yaml.md | markdown | 2.3 KB |
| scripts/LICENSE.txt | markdown | 11.1 KB |
| scripts/generate_openai_yaml.py | script | 6.5 KB |
| scripts/init_skill.py | script | 14.9 KB |
| scripts/quick_validate.py | script | 3.9 KB |
| scripts/test_init_skill.py | script | 2.5 KB |
| scripts/test_quick_validate.py | script | 1.3 KB |
scripts/test_init_skill.py
View on GitHub"""Exercise author serialization through the real initializer CLI."""
import os
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
import yaml
class InitializerAuthorTests(unittest.TestCase):
def initialize(self, author):
with tempfile.TemporaryDirectory(prefix="skill-author-test-") as directory:
skill_dir = Path(directory) / "author-example"
result = subprocess.run(
[
sys.executable,
str(Path(__file__).with_name("init_skill.py")),
"author-example",
"--path", directory,
"--author", author,
],
capture_output=True,
text=True,
env={**os.environ, "PYTHONDONTWRITEBYTECODE": "1"},
)
self.assertEqual(result.returncode, 0, result.stdout + result.stderr)
content = (skill_dir / "SKILL.md").read_text()
frontmatter = yaml.safe_load(content.split("---", 2)[1])
self.assertEqual(frontmatter["metadata"]["author"], author)
self.assertEqual(set(frontmatter), {"name", "description", "metadata"})
self.assertEqual(set(frontmatter["metadata"]), {"author"})
self.assertTrue((skill_dir / "agents" / "openai.yaml").is_file())
def test_plain_author_round_trip(self):
self.initialize("Platform Team")
def test_unicode_control_author_round_trip(self):
for author in ("Team\u0085Name", "Team\u007fName", "Team\u009fName"):
with self.subTest(author=author):
self.initialize(author)
def test_unicode_scalar_author_round_trip(self):
for author in (
"Team 🦉",
"Team 𠮷",
"Line\u2028Separator",
"Paragraph\u2029Separator",
"Team\uffffName",
("Long author " * 30) + "End",
):
with self.subTest(author=author):
self.initialize(author)
def test_yaml_sensitive_author_round_trip(self):
for author in (
"Platform #1",
"Platform: Tools",
'"Quoted Team"',
"O'Connor",
"Line one\nLine two",
"Team\nextra: injected",
"true",
r"Team\Tools",
"研发 #1",
):
with self.subTest(author=author):
self.initialize(author)
if __name__ == "__main__":
unittest.main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |