jleechanorg
jleechanorg/claude-commands
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jleechanorg/claude-commands --skill coverage-analysis命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model opinion. Use instead of advisor() which ships the full conversation uncached.
Use this skill when working in repositories managed by Agent Orchestrator or when the user asks how to use `ao` properly. Covers the default AO workflow: bootstrap with `ao start`, dispatch work with `ao spawn`, inspect progress with `ao status` or `ao session ls`, steer sessions with `ao send`, and recover or clean up sessions safely. Includes strict parameter fidelity, pre-spawn cap cleanup, quota-wall fallback, and post-spawn verification.
Generate a full agento PR status report — draft readiness, canonical /green, zero-touch rate, inline display, and Slack summary.
基于 SOC 职业分类
正在显示 SKILL.md
| name | coverage-analysis |
| description | Code coverage analysis using coverage.sh script and pytest-cov |
| type | usage |
| scope | project |
Provide Claude with a comprehensive reference for running code coverage analysis in WorldArchitect.AI. This skill covers the coverage.sh script usage, interpreting results, and best practices.
# Run coverage with HTML report (default)
./coverage.sh
# Run coverage with text report only (faster)
./coverage.sh --no-html
# Include integration tests
./coverage.sh --integration
# Include integration tests, text only
./coverage.sh --integration --no-html
| Output | Location |
|---|---|
| Text report | /tmp/worldarchitectai/coverage/coverage_report.txt |
| HTML report | /tmp/worldarchitectai/coverage/index.html |
| Quick link | file:///tmp/coverage.html (symlink) |
Test Summary:
Total tests: 232
Passed: 204
Failed: 28
Overall Coverage: 69%
Key Files Coverage:
main.py 44%
llm_service.py 74%
game_state.py 57%
firestore_service.py 53%
| Coverage | CI Result | Badge Color |
|---|---|---|
| ≥80% | Pass | Green (MINIMUM_GREEN: 80) |
| 60-79% | Pass (warning) | Orange (MINIMUM_ORANGE: 60) |
| <60% | Fail | Red |
| Coverage | Status | Action | CI Threshold |
|---|---|---|---|
| 80%+ | Excellent | Maintain | Green (MINIMUM_GREEN: 80) |
| 60-79% | Good | Minor improvements | Orange (MINIMUM_ORANGE: 60) |
| 40-59% | Fair | Add targeted tests | Warning |
| <40% | Poor | Prioritize testing | Error |
Priority coverage targets for WorldArchitect.AI:
For focused development, run individual test files:
# Using venv with proper PYTHONPATH
source venv/bin/activate
PYTHONPATH="$PWD:$PYTHONPATH" TESTING=true python mvp_site/tests/test_specific.py
Cause: PYTHONPATH doesn't include project root.
Fix: The coverage.sh script sets PYTHONPATH="$PROJECT_ROOT:$PYTHONPATH" automatically. For manual runs:
export PYTHONPATH="$PWD:$PYTHONPATH"
Fix: Install test dependencies:
pip install numpy fastembed onnxruntime
Some tests require additional setup:
playwright installFor CI coverage reporting, use py-cov-action/python-coverage-comment-action@v3.32 (SHA-pinned in workflow):
- name: Coverage comment
uses: py-cov-action/python-coverage-comment-action@fb02115d6115e7b3325dc3295fe1dcfb1919248a # v3.32
with:
GITHUB_TOKEN: ${{ github.token }}
MINIMUM_GREEN: 80
MINIMUM_ORANGE: 60
See .github/workflows/coverage.yml for the full workflow with threshold checks.
TESTING=true for isolated testingend2end-testing.md - E2E test patternsevidence-standards.md - Test evidence collection