420company
420company/artemis
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/420company/artemis --skill app-health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。
This skill should be used when the user asks to "call the Spotify Ads API", "create a Spotify ad campaign", "manage Spotify ads", "pull Spotify ad reports", "set up ad sets or ads", "upload ad assets", "target audiences on Spotify", "check campaign status", "get ad account info", "look up API schema or fields", "check what targeting options exist", or asks about Spotify advertising endpoints, request/response formats, enum values, or authentication.
Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
基于 SOC 职业分类
正在显示 SKILL.md
| name | app-health |
| disable-model-invocation | true |
| argument-hint | [application_name] [since_hours] |
| description | Analyze application health across the organization using ZDX scores and metrics. |
Analyze health for: $ARGUMENTS
Extract:
zdx_list_applications()
```text
## Step 3: Get Scores for Each Application
For each application (or the specified one):
```text
zdx_get_application(app_id="<app_id>", since=<hours>)
zdx_get_application_score_trend(app_id="<app_id>", since=<hours>)
```text
## Step 4: Investigate Degraded Applications
For any application with score < 66:
```text
zdx_get_application_metric(app_id="<app_id>", metric_name="dns_time", since=<hours>)
zdx_get_application_metric(app_id="<app_id>", metric_name="availability", since=<hours>)
```text
Identify the metric causing degradation.
## Step 5: Check Most Impacted Users
```text
zdx_list_devices(app_id="<app_id>")
```text
## Step 6: Present Report
**ALWAYS present data in HTML tables** using `<table>`, `<thead>`, `<tbody>`, `<tr>`, `<th>`, `<td>` tags with inline styling. Use color-coded rows: green (score 66-100), yellow (score 34-65), red (score 0-33).
Include:
1. **Application health overview table** (app name, score, status, PFT, DNS, availability, impacted users, bottleneck)
2. **Detailed analysis** for each degraded/poor application explaining what the bottleneck metric indicates
3. **Root cause** per degraded app (DNS resolver, server-side, CDN, ISP, etc.)
4. **Next steps / resolution** prioritized by user impact count:
- Critical apps: immediate investigation, check service health, engage vendor
- Degraded apps: monitor trend, investigate bottleneck metric, check ISP paths
- Healthy apps: no action, note any borderline (66-70) for proactive monitoring
## Step 7: Generate Downloadable Artifacts — MANDATORY
**You MUST create BOTH files. Do NOT skip the HTML page.**
1. **Word document** (`application_health_report_<date>.docx`): Executive summary, application health table, per-app deep dive for degraded apps, root cause analysis, user impact breakdown, prioritized remediation actions.
2. **Interactive HTML page** (`application_health_report_<date>.html`): Use the complete HTML template from the `zdx-analyze-application-health` skill. The file must be fully functional with working search bar, sortable columns, filter dropdowns, color-coded rows, summary dashboard, and CSV export button. All CSS and JavaScript inline — no external dependencies. Populate the `<tbody>` with one `<tr>` per application from the collected data.
**Write both files to disk and provide the file paths to the user.**