Skip to content
Development
Skill

/log-check

Investigate logs in ELK — time window, KQL, error patterns, redacted samples, correlation, report. Primary log-ops skill. Evidence-only.

From plugin
agentic-awesome-kits
932 skills
Install
$ npx -y skills add KhaiTrang1995/agentic-awesome-kits --skill log-check --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/log-check

Context preview

The summary Claude sees to decide when to auto-load this skill.

Investigate logs in ELK — time window, KQL, error patterns, redacted samples, correlation, report. Primary log-ops skill. Evidence-only.

SKILL.md

log-check.SKILL.md
name: log-check
description: Investigate logs in ELK — time window, KQL, error patterns, redacted samples, correlation, report. Primary log-ops skill. Evidence-only.
user-invocable: true
argument-hint: "<service or symptom> [--env prod] [--since 1h] [--level ERROR] [@paste-or-export]"

/log-check — Log Investigation

Examples

/log-check booking-api --env prod --since 1h --level ERROR
/log-check "timeout payment" --since 30m
/log-check booking-api @logs-sample.ndjson

Process

1. Frame

Symptom, service, env, window, timezone, data view (or TBD), available paste?

2. Query plan (READ-ONLY)

service.name: "{{service}}" and env: "{{env}}" and log.level: error

Refine with symptom keywords. See `@references/kql-cheat.md`.

3. Analyze evidence only

Timeline, top patterns (`log-patterns.md`), ≤10 redacted samples, deploy window, correlate metrics/deps.

4. Conclude

Findings, ranked hypotheses, READ-ONLY next steps, MUTATIVE human-only options, escalate if user-facing impact.

5. Output

Chat summary always; optional L1 save → `docs/ops/elk/log-checks/{id}.md`

Definition of done

See `ELK-BRAIN.md` — query, evidence, hypothesis, next step.

Output template

`@_templates/log-check-report.md`

Rules

  • No invented counts/stacks; redact secrets; no delete-index “fixes”
  • @.claude/rules/elk-conventions.md
  • @.claude/rules/approval-gate.md
Read more
Ships withagentic-awesome-kits

Reusable AI Skill Kits for coding agents (Claude Code and any other subagent/slash-command-compatible tool).

Get the whole plugin
Stats
9
Stars
3
Forks
Maintained
Maintenance
Python
Language
1mo ago
Last commit
2mo ago
Created

Repo: KhaiTrang1995/agentic-awesome-kits

Other skills on agentic-awesome-kits.