Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
免费在 GitHub 公开
system-health-check
Verifies repository baseline test passing state and available memory/GPU resources to ensure safe mission execution.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（10）
- SKILL.md1.5 KB
- commands/system-health-check.md119 B
- hooks/post-execute.cjs191 B
- hooks/pre-execute.cjs297 B
- references/research-requirements.md294 B
- rules/system-health-check.md297 B
- schemas/input.schema.json500 B
- schemas/output.schema.json263 B
- scripts/main.cjs1.0 KB
- templates/implementation-template.md193 B
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
System Health Check (Pre-Flight)
Before accepting or starting a large architectural mission, you MUST run this health check to confirm you are not iterating on top of an already broken baseline.
1. Test Baseline Verification
Identify the primary test command for this workspace. Use the command matching the ecosystem:
- Node.js:
npm run testorpnpm test:all - Rust:
cargo test - Python:
pytest
Rule: If the tests FAIL, immediately halt your mission and inform the user. Do not proceed until the existing codebase compiles and tests pass.
2. Resource Verification
Ensure the host machine has adequate capacity to compile your work or run complex LLMs.
Windows PowerShell Examples: Check available memory and CPU cores:
systeminfo | findstr /C:"Total Physical Memory" /C:"Available Physical Memory"
wmic cpu get NumberOfCores,NumberOfLogicalProcessors /format:list
3. Hardware Accelerators (Optional)
If your mission explicitly governs a machine learning or GPU-heavy task, check for an NVIDIA GPU via:
nvidia-smi --query-gpu=name,memory.total,memory.free --format=csv,noheader
If resources look extremely constrained (e.g., <2GB Free RAM), halt and warn the user before proceeding to file modifications.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
中文简介正在准备中。当前显示原文说明。
oimiragieo/agent-studio432026年7月14日 更新