菜单
Create agent feedback for harness self-improvement. Use after completing complex tasks (>30 min) to document what worked, what failed, and patterns detected. This feeds the continuous improvement loop.
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
Execute deterministic code quality validations as a quality gate for smart-ralph task execution. Runs Layer 3A smoke test (Tier A AST, <1 min), Layer 1 (test execution), Layer 2 (test quality analysis), Layer 3B (Tier B BMAD Party Mode, ~15 min), and Layer 4 (Security & Defense, ~2-5 min). Uses Two-Tier approach: Tier A (AST deterministic) + Tier B (BMAD Party Mode consensus). Layer 4 covers 8 security tools: bandit, safety/pip-audit, gitleaks, semgrep, checkov, deptry, vulture, trivy. Generates a checkpoint JSON consumed by smart-ralph VERIFY steps. Use when you need to validate that code meets quality and security standards before COMMIT.
Create and manage Home Assistant YAML configuration files including automations, scripts, templates, blueprints, Lovelace dashboards, and file organization. Use when working with Home Assistant configuration files (.yaml, .yml) or discussing HA automations, scripts, sensors, or dashboards.
Design, update, and refactor Home Assistant Lovelace dashboards (YAML views/partials) with a constrained, machine-safe design system: button-card-first structure, minimal card-mod styling, optional flex-horseshoe + mini-graph telemetry, strict grid/vertical-stack layout rules, centralized templates, deterministic ordering, and config validation. Use for Home Assistant dashboard work (especially config/dashboards/**), when refactoring views, adding infra/home/energy/environment panels, or translating Stitch design inspiration into safe Lovelace YAML.
Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.
Iterative consensus-building skill that runs BMAD Party Mode in loops until agents reach consensus. Each iteration enriches context with previous round findings, project domain knowledge, and relevant evidence. Use when you need multi-agent validation, architectural decisions, technical debates, or any situation where consensus is the goal and isolated opinions are insufficient.
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
| name | bmad-agent-feedback |
| description | Create agent feedback for harness self-improvement. Use after completing complex tasks (>30 min) to document what worked, what failed, and patterns detected. This feeds the continuous improvement loop. |
Follow the instructions in ./workflow.md
