菜单
Run code quality analysis on YAMLGraph. Use when: running ruff, bandit, radon, vulture, pytest coverage, checking code quality, finding dead code, security scanning, or generating improvement recommendations. For autonomous analysis, use the code-analysis agent instead.
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。
基于 SOC 职业分类
Author YAMLGraph prompt YAML files. Use when: writing prompt templates, configuring inline schemas or output_schema, using Jinja2 templates, adding system/user messages, defining structured output fields, or using system_segments for prompt caching.
Author YAMLGraph graph YAML files. Use when: creating or editing graph YAML, adding nodes or edges, configuring routing and conditions, setting up state keys, variables, data_files, tools, loop limits, error handling, or verification gates.
Operate the Chaplain automation system. Use when: starting the chaplain, checking pipeline status, submitting proposals to inbox, debugging pipeline failures, retrying failed topics, cleaning worktrees, running the philosopher or inquisitor.
Create and manage YAMLGraph feature requests. Use when: writing a feature request, planning a feature, following the plan-judge-enforce workflow, submitting a proposal to the chaplain inbox, understanding the FR lifecycle, or writing acceptance criteria.
Release a new YAMLGraph version. Use when: bumping version, creating a release, tagging, pushing a release, freezing changelog, or handling pre-commit hook cascades during release.
Check LangSmith traces for YAMLGraph runs. Use when: debugging graph execution, reviewing LLM latency or token usage, investigating failed runs, verifying tracing config, querying recent traces, troubleshooting LangSmith connectivity.
| name | run-code-analysis |
| description | Run code quality analysis on YAMLGraph. Use when: running ruff, bandit, radon, vulture, pytest coverage, checking code quality, finding dead code, security scanning, or generating improvement recommendations. For autonomous analysis, use the code-analysis agent instead. |
| argument-hint | target path like 'yamlgraph' or specific tool like 'ruff' |
Run automated code quality tools and generate recommendations. Canonical source: reference/code-analysis.md.
Note: The code-analysis agent can run this autonomously. This skill covers manual usage.
yamlgraph graph run examples/demos/code-analysis/graph.yaml \
--var path="yamlgraph" \
--var package="yamlgraph"
ruff check yamlgraph/ # Check
ruff check --fix yamlgraph/ # Auto-fix
ruff format yamlgraph/ # Format
# Fast parallel (skip slow)
pytest tests/unit/ -q --no-cov -m "not slow" -n auto
# With coverage
pytest tests/ --cov=yamlgraph --cov-report=html
bandit -r yamlgraph/ -ll -q
Flags: -ll = medium+ severity, -q = quiet (issues only).
radon cc yamlgraph/ -a -nc # Cyclomatic complexity
radon mi yamlgraph/ # Maintainability index
Target: functions < complexity 10. Module size: < 400 lines, max 450.
vulture yamlgraph/ vulture_whitelist.py
The whitelist file suppresses intentional unused exports.
# Find TODOs/FIXMEs
grep -rn "TODO\|FIXME" yamlgraph/
# Line counts
find yamlgraph/ -name "*.py" | xargs wc -l | sort -n | tail -20
# Import boundary check
lint-imports
| Metric | Target |
|---|---|
| Module size | < 400 lines (max 450) |
| Function complexity | < 10 (radon cc) |
| Test coverage | ≥ 80% |
| Security issues | 0 medium+ (bandit) |
| Dead code | 0 unreported (vulture) |
The code-analysis graph uses an agent node with shell tools:
nodes:
run_analysis:
type: agent
prompt: code-analysis/analyzer
tools: [run_ruff, run_tests, run_bandit, run_radon, run_vulture]
max_iterations: 12
state_key: analysis_results
generate_recommendations:
type: llm
prompt: code-analysis/recommend
requires: [analysis_results]
state_key: recommendations
pip install ruff bandit radon vulture