72f16d26b89b49bb8c6519301e5453801c0d9ae2
- Add SKILL.md with workflow and guidelines for generating Conventional Commits messages - Add agent config (.kiro/agents/commit-message.json) with tool permissions and skill resource - Add evals (evals.json) with 3 test cases covering feat/fix/refactor scenarios - Add Conventional Commits 1.0.0 reference documentation - Add compiled skill bundle (commit-message.skill)
common-skills
Shared Kiro agent skills for the team. All skills are evaluated before merge.
Structure
skills/
├── codereview/
│ ├── SKILL.md
│ └── evals/evals.json
├── docs-rag/
│ ├── SKILL.md
│ ├── data/index.json
│ └── evals/evals.json
├── python/
├── testing/
└── typescript/
scripts/
├── run_evals.py ← eval runner with regression protection
└── sync.sh ← sync skills into a project
.githooks/
└── pre-push ← blocks push if changed skills regress
baselines.json ← recorded pass rates (committed to repo)
Using Skills in Your Project
# Sync all skills
COMMON_SKILLS_DIR=~/common-skills bash scripts/sync.sh
# Sync specific skills only
COMMON_SKILLS_DIR=~/common-skills bash scripts/sync.sh codereview python
Contributing a New Skill
- Create
skills/<name>/SKILL.mdwith YAML frontmatter (name,description) - Add
skills/<name>/evals/evals.jsonwith at least 3 eval cases - Run evals locally and update baseline:
python scripts/run_evals.py <name> --update-baseline - Push — the pre-push hook will verify no regressions on changed skills
Running Evals
# Run all skills
python scripts/run_evals.py
# Run single skill
python scripts/run_evals.py codereview
# Check for regressions against baselines.json
python scripts/run_evals.py --check-regression
# After improving a skill, record new baseline
python scripts/run_evals.py codereview --update-baseline
Install pre-push Hook
cp .githooks/pre-push .git/hooks/pre-push && chmod +x .git/hooks/pre-push
Description
Languages
JavaScript
46.6%
Python
41.7%
Shell
11.7%