Menu
Cross-product troubleshooting of user connectivity across ZCC, ZDX, ZPA, and ZIA.
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/420company/artemis --skill troubleshoot-userThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
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.
Based on SOC occupation classification
Showing SKILL.md
| name | troubleshoot-user |
| disable-model-invocation | true |
| argument-hint | <username_or_email> [application_or_url] [symptom] |
| description | Cross-product troubleshooting of user connectivity across ZCC, ZDX, ZPA, and ZIA. |
Perform end-to-end troubleshooting for user: $ARGUMENTS
Follow this systematic workflow:
Extract from the arguments:
If any required information is missing, ask the administrator.
zcc_list_devices(search="<user>")
```text
Check enrollment status, ZCC version, last seen time. Verify traffic is being forwarded:
```text
zcc_list_forwarding_profiles()
zcc_list_trusted_networks()
```text
## Step 3: ZDX Digital Experience
```text
zdx_list_devices(search="<user>")
zdx_get_device(device_id="<id>")
zdx_list_applications()
zdx_get_application_score_trend(app_id="<id>")
zdx_list_alerts()
```text
Evaluate: Score > 80 = good, 50-80 = degraded, < 50 = poor. Check DNS time, TCP connect time, server response time.
### Step 3a: Deep Trace Diagnostics (if score is degraded/poor)
Check for existing deep trace sessions and analyze or start a new one:
```text
zdx_list_device_deep_traces(device_id="<id>")
```text
If a trace exists, analyze the diagnostics data:
```text
zdx_get_device_deep_trace(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_webprobe_metrics(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_cloudpath(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_cloudpath_metrics(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_health_metrics(device_id="<id>", trace_id="<trace_id>")
zdx_list_deeptrace_top_processes(device_id="<id>", trace_id="<trace_id>")
zdx_get_deeptrace_events(device_id="<id>", trace_id="<trace_id>")
```text
If no trace exists and the symptom suggests network issues, discover probe IDs and start one (requires write tools):
```text
zdx_get_web_probes(device_id="<id>", app_id="<app_id>")
zdx_list_cloudpath_probes(device_id="<id>", app_id="<app_id>")
zdx_start_deeptrace(device_id="<id>", session_name="Cross-Product-<user>-<date>", app_id=<app_id>, web_probe_id=<id>, cloudpath_probe_id=<id>, session_length_minutes=15, probe_device=True)
```text
Use deep trace findings to narrow down: is the issue at the device (CPU/memory), network (cloud path hops), DNS, or application layer?
## Step 4: ZPA (Private Apps)
```text
zpa_list_application_segments()
zpa_get_application_segment(segment_id="<id>")
zpa_get_server_group(group_id="<id>")
zpa_get_app_connector_group(group_id="<id>")
zpa_list_access_policy_rules()
```text
Verify app segment exists, is enabled, connectors are healthy, and user has an ALLOW rule.
## Step 5: ZIA (Internet Apps)
```text
zia_url_lookup(urls=["<url>"])
zia_list_url_filtering_rules()
zia_list_ssl_inspection_rules()
zia_list_cloud_firewall_rules()
zia_get_activation_status()
```text
Evaluate URL filtering, SSL inspection, and firewall rules in priority order.
## Step 6: Broader Impact
Check if multiple users affected via ZDX alerts. Check ZIA activation status for pending changes.
## Step 7: Present Report
Provide a structured diagnosis report with: user details, device status, experience scores, configuration findings, root cause, and recommended actions. Prioritize findings as [LIKELY], [POSSIBLE], [UNLIKELY].