playbook/tests/test_firstparty_skills_qual...

105 lines
4.2 KiB
Python

import re
import unittest
from pathlib import Path
ROOT = Path(__file__).resolve().parents[1]
SKILLS_ROOT = ROOT / "skills"
FIRST_PARTY_SKILLS = {
"commit-message": SKILLS_ROOT / "commit-message" / "SKILL.md",
"style-cleanup": SKILLS_ROOT / "style-cleanup" / "SKILL.md",
"bulk-refactor-workflow": SKILLS_ROOT / "bulk-refactor-workflow" / "SKILL.md",
}
def read_text(path: Path) -> str:
return path.read_text(encoding="utf-8")
def normalize_space(text: str) -> str:
return " ".join(text.split())
def parse_frontmatter(text: str) -> dict[str, str]:
match = re.match(r"^---\n(.*?)\n---\n", text, re.DOTALL)
if match is None:
raise AssertionError("missing YAML frontmatter")
block = match.group(1)
data: dict[str, str] = {}
current_key: str | None = None
current_value: list[str] = []
for raw_line in block.splitlines():
if raw_line.startswith(" ") and current_key is not None:
current_value.append(raw_line.strip())
continue
if current_key is not None:
data[current_key] = " ".join(current_value).strip().strip('"')
current_key = None
current_value = []
key, value = raw_line.split(":", 1)
current_key = key.strip()
current_value = [value.strip()]
if current_key is not None:
data[current_key] = " ".join(current_value).strip().strip('"')
return data
class FirstPartySkillsQualityTests(unittest.TestCase):
def test_first_party_skill_frontmatter_is_minimal_and_named_consistently(self):
for name, path in FIRST_PARTY_SKILLS.items():
with self.subTest(skill=name):
frontmatter = parse_frontmatter(read_text(path))
self.assertEqual(set(frontmatter), {"name", "description"})
self.assertEqual(frontmatter["name"], name)
self.assertRegex(frontmatter["name"], r"^[a-z0-9-]+$")
def test_first_party_skill_descriptions_are_trigger_focused(self):
for name, path in FIRST_PARTY_SKILLS.items():
with self.subTest(skill=name):
description = parse_frontmatter(read_text(path))["description"]
self.assertTrue(description.startswith("Use when"))
self.assertLessEqual(len(description), 500)
self.assertNotIn("Triggers:", description)
def test_first_party_skills_have_required_sections(self):
required_sections = (
"## Overview",
"## When to Use",
"## When Not to Use",
"## Inputs",
"## Procedure",
"## Output Contract",
"## Success Criteria",
"## Failure Handling",
)
for name, path in FIRST_PARTY_SKILLS.items():
text = read_text(path)
with self.subTest(skill=name):
for section in required_sections:
self.assertIn(section, text)
def test_commit_message_skill_handles_missing_or_mixed_staging_states(self):
text = normalize_space(read_text(FIRST_PARTY_SKILLS["commit-message"]))
self.assertIn("If nothing is staged", text)
self.assertIn("If only unstaged changes exist", text)
self.assertIn("strongly recommend splitting the commit", text)
self.assertIn("Do not run `git commit`", text)
def test_style_cleanup_skill_has_clear_non_goals_and_verification_loop(self):
text = normalize_space(read_text(FIRST_PARTY_SKILLS["style-cleanup"]))
self.assertIn("not for semantic refactors", text)
self.assertIn("not for introducing a new formatter or lint configuration", text)
self.assertIn("formatter -> lint/check -> lint --fix -> final check", text)
self.assertIn("second formatter run produces no additional diff", text)
def test_bulk_refactor_skill_is_dirty_aware_and_delegates_final_cleanup(self):
text = normalize_space(read_text(FIRST_PARTY_SKILLS["bulk-refactor-workflow"]))
self.assertIn("Dirty worktrees are allowed", text)
self.assertIn("Do not revert unrelated changes", text)
self.assertIn("Use `style-cleanup` for the final formatting/lint pass", text)
self.assertIn("apply the transformation in bounded batches", text)
if __name__ == "__main__":
unittest.main()