Provides a comprehensive status report on Selma's operational health. Checks Ollama, configuration, workspace files, and gateway status.

Install

mkdir -p .claude/skills/healthcheck-gkvoelkl && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11102" && unzip -o skill.zip -d .claude/skills/healthcheck-gkvoelkl && rm skill.zip

Installs to .claude/skills/healthcheck-gkvoelkl

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Check Selma's system health: Ollama reachability, configured model availability, config validity, workspace files, loaded skills, session store, and gateway status. Trigger on: healthcheck, health check, /healthcheck, alles ok, status check, ist selma ok, system status.
270 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Check Ollama reachability
  • Validate configuration files
  • Verify workspace file integrity
  • Check gateway status

How it works

It executes a series of diagnostic tool calls in order, collects the results, and aggregates them into a single status report.

Inputs & outputs

You give it
Health check trigger command
You get back
Structured health report with status indicators

When to use healthcheck

  • Verify local Ollama model availability
  • Troubleshoot system configuration errors
  • Confirm workspace file integrity
  • Validate gateway connectivity

About this skill

Selma Health Check

Instructions

Call ALL tools first without producing any intermediate output. Collect all results, then write ONE complete report at the end.

Tool calls (execute all, in order)

  1. web_fetchhttp://localhost:11434/api/tags
  2. read../selma.json
  3. ls./
  4. lsskills/
  5. read../agents/main/sessions/sessions.json
  6. web_fetchhttp://localhost:8000/

Report (write after all tools completed)

Selma Health Check
──────────────────────────────────────

✅/❌/⚠️  Ollama:    <reachable — N models> or <not reachable>
✅/❌/⚠️  Modell:    <model name> — <found / not found in Ollama>
✅/❌/⚠️  Config:    selma.json — <valid / error: ...>
✅/❌/⚠️  Workspace: <N files> — <missing: X, Y if any>
✅/❌/⚠️  Skills:    <N loaded: name1, name2, ...> or <none>
✅/❌/⚠️  Sessions:  <N sessions> or <no sessions yet>
✅/❌/⚠️  Gateway:   <running on :8000 / not reachable>

Status: OK / DEGRADED / ERROR

Status rules:

  • OK — all ✅ (⚠️ on sessions or gateway still counts as OK)
  • DEGRADED — at least one ⚠️ on workspace or skills
  • ERROR — at least one ❌ (Ollama, model, or config)

Notes

  • Continue even if a tool call fails — use ❌ for that check.
  • Expected workspace files: AGENTS.md, SOUL.md, IDENTITY.md, TOOLS.md, USER.md, HEARTBEAT.md, BOOTSTRAP.md
  • Do not suggest fixes unless the user asks.

When not to use it

  • When the user requests system fixes
  • When the environment is not a local Selma instance

Prerequisites

Ollama serviceselma.json configuration

Limitations

  • Does not suggest fixes unless requested
  • Continue even if a tool call fails

How it compares

It provides a centralized, automated diagnostic report instead of requiring manual verification of individual system components.

Compared to similar skills

healthcheck side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
healthcheck (this skill)02moNo flagsBeginner
coderabbit-observability127dReviewAdvanced
pipeline-reflection-ux03moReviewIntermediate
phoenix-observability37moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

coderabbit-observability

jeremylongshore

Set up comprehensive observability for CodeRabbit integrations with metrics, traces, and alerts. Use when implementing monitoring for CodeRabbit operations, setting up dashboards, or configuring alerting for CodeRabbit integration health. Trigger with phrases like "coderabbit monitoring", "coderabbit metrics", "coderabbit observability", "monitor coderabbit", "coderabbit alerts", "coderabbit tracing".

10

pipeline-reflection-ux

oimiragieo

Improve router-facing pipeline and reflection narration to reduce noisy status churn and make Step 0/Reflection outcomes explicit. Use when updating Router output contract, reflection reminder wording, or post-pipeline notification batching.

00

phoenix-observability

davila7

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

323

phoenix-tracing

Arize-ai

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.

13

genkit-production-expert

jeremylongshore

Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.

01

klingai-usage-analytics

jeremylongshore

Build usage analytics and reporting for Kling AI. Use when tracking generation patterns, analyzing costs, or creating dashboards. Trigger with phrases like 'klingai analytics', 'kling ai usage report', 'klingai metrics', 'video generation stats'.

10

Search skills

Search the agent skills registry