Skills Guide

Selma Health Check

VerifiedSafe

Checks system health including Ollama reachability, model availability, config validity, workspace files, skills, sessions, and gateway status.

Download and use
Sby Skills Guide Bot
DevOpsBeginner
7/26/2026
Claude Code
#health-check#ollama#monitoring#local-llm#diagnostics

Recommended for

Backend developerClaude CodeDevOps engineerGit automation

Automated summary

Runs a fixed set of checks against the Selma instance (Ollama, configured model, selma.json, workspace files, skills, sessions, gateway) and emits one consolidated report with an OK, DEGRADED, or ERROR status.

Strengths

  • Fires all tool calls first and writes a single end report with no intermediate chatter
  • Explicit status rules: OK, DEGRADED (workspace or skills warning) and ERROR (Ollama, model, or config failure)
  • Keeps going when a tool call fails and simply marks that check as ❌
  • Documents the expected workspace files, so missing ones are easy to spot

Limitations

  • Targets are hard-coded (localhost:11434, localhost:8000, ../selma.json), so it is not portable to other setups
  • Checks reachability and presence only, not quality or latency
  • Suggests no fixes and keeps no history between runs
When to use it

Use it for a fast, repeatable snapshot of the Selma instance's health before working or after a configuration change.

When not to use it

Avoid it on a system other than Selma, or when you want remediation advice rather than a plain status readout.

Security analysis

Safe
Quality score82/100

The skill only performs local read-only health checks: fetching localhost API endpoints and reading local configuration/session files. It does not exfiltrate data, execute shell commands, modify files, or expose sensitive contents; the report summarizes status rather than dumping file contents.

No concerns found

How this analysis is made

Examples

Slash command
/healthcheck
German status question
Ist Selma ok? Mach bitte einen Status check.
Quick systems check
Everything ok? Run a health check on Selma and show me the report.

name: healthcheck description: "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." user-invocable: true

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_fetch → http://localhost:11434/api/tags
  2. read → ../selma.json
  3. ls → ./
  4. ls → skills/
  5. read → ../agents/main/sessions/sessions.json
  6. web_fetch → http://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.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/selma-health-check-ms1aw595/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/selma-health-check-ms1aw595' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/selma-health-check-ms1aw595/download' --output '.skill-downloads/selma-health-check-ms1aw595/SKILL.md.part' && mv '.skill-downloads/selma-health-check-ms1aw595/SKILL.md.part' '.skill-downloads/selma-health-check-ms1aw595/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/selma-health-check-ms1aw595/SKILL.md' && test -s '.skill-downloads/selma-health-check-ms1aw595/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/healthcheck' && cp -R '.skill-downloads/selma-health-check-ms1aw595' '.claude/skills/healthcheck'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/selma-health-check-ms1aw595'

openskills read 'selma-health-check-ms1aw595'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/selma-health-check-ms1aw595/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Configure a Chat Channel with SecretRefs

DevOps

Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.

Claude CodeCodexintermediateSafe 387,940
Skills Guide Bot

Investigate ClickHouse CI Failures

DevOps

Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.

Claude CodeadvancedSafe 49,516
Skills Guide Bot

Ansible PR Review

DevOps

Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.

Claude CodeintermediateSafe 70,491
Skills Guide Bot