Skills Guide

System Health Audit

VerifiedCaution

Run complete system health audit of DQIII8 — checks DB integrity, agent performance, pipeline connections, error log, and services. Produces a scored Markdown report.

Download and use
Sby Skills Guide Bot
DevOpsIntermediate
7/27/2026
Claude Code
#health-check#monitoring#sqlite#audit-report#agent-observability

Recommended for

Backend developerClaude CodeDevOps engineerGit automation

Automated summary

Runs a project-specific health audit of the DQIII8 SQLite database to produce a dated Markdown report and an overall score out of 100.

Strengths

  • Aggregates agent_actions, error_log, sessions and skill_metrics into a single 0-100 score
  • Writes a timestamped Markdown report into database/audit_reports/ and inserts a summary row into the audit_reports table
  • Supports --period and --agent options to narrow the time window or scope to one agent
  • Can auto-trigger through the stop.py hook after 7 days without a report or when errors pile up

Limitations

  • Hardcoded schema (database/dqiii8.db, specific tables and views) with no configuration for other projects
  • The scoring formula and the 80/60 thresholds are fixed and undocumented
  • Depends on the auditor agent and the stop.py hook being present; it only analyses and reports, it does not remediate
When to use it

When you want a periodic health snapshot of the DQIII8 agent pipeline, or after a session where errors have been accumulating.

When not to use it

On another project or database schema, or when you need real-time incident response rather than a periodic scored report.

Security analysis

Caution
Quality score80/100

The skill performs legitimate, bounded local operations: read-only metric queries, an aggregate score, a Markdown report write, and a summary-row insert. No network calls, secret access, obfuscated payloads, or destructive commands are present. The main concerns are the use of Bash for DB writes and the unconditional auto-invoke behavior, which is why it is rated caution rather than safe.

Findings
  • •Uses Bash to execute SQLite queries and writes rows into database/dqiii8.db, a state-mutating operation
  • •auto-invoke block can trigger /audit without the user explicitly requesting it (after 7 days or 3+ errors)
  • •Creates new files under database/audit_reports/ — acceptable but write access is broad
  • •No sandboxing or dry-run option; report path and DB path are hardcoded, which limits blast radius but assumes a trusted project layout
How this analysis is made

Examples

Default weekly audit
/audit
Audit over a longer window
/audit --period 30d
Scope to one agent
/audit --agent python-specialist

name: audit description: Run complete system health audit of DQIII8 — checks DB integrity, agent performance, pipeline connections, error log, and services. Produces a scored Markdown report. command: /audit allowed-tools: [Bash, Read, Grep] user-invocable: true auto-invoke:

  • when: "7+ days since last audit OR 3+ unresolved errors detected in session" action: "Run /audit automatically to surface problems"

/audit -- System Health Audit

Triggers the auditor agent to analyze database/dqiii8.db and produce a structured health report.

Usage

/audit
/audit --period 30d       # analyze last 30 days instead of default 7
/audit --agent python-specialist   # scope to one agent

What it does

  1. Queries all metric tables: agent_actions, error_log, sessions, skill_metrics
  2. Uses views agent_performance and error_keywords_freq
  3. Computes an overall health score (0-100)
  4. Writes a Markdown report to database/audit_reports/audit-YYYY-MM-DD-HH.md
  5. Inserts a summary row in the audit_reports table
  6. Prints a one-line summary to the terminal

Output

[AUDIT] Score: 87/100 | Actions: 106 | Success: 100.0% | Failures: 0 | Unresolved errors: 0
Report: database/audit_reports/audit-2026-03-11-14.md

Score interpretation

| Score | Status | Cadencia recomendada | |-------|--------|----------------------| | > 80 | HEALTHY | next audit in 7 days | | 60-80 | WARNING | next audit in 3 days | | < 60 | CRITICAL | next audit in 1 day, notify user |

Auto-trigger

The stop.py hook automatically triggers /audit when 7+ days have passed since the last report in audit_reports. Also auto-invoked when errors accumulate during a session.

Agent

Handled by: .claude/agents/auditor.md Model: claude-sonnet-4-6

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/system-health-audit-ms2s7bvd/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/system-health-audit-ms2s7bvd' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/system-health-audit-ms2s7bvd/download' --output '.skill-downloads/system-health-audit-ms2s7bvd/SKILL.md.part' && mv '.skill-downloads/system-health-audit-ms2s7bvd/SKILL.md.part' '.skill-downloads/system-health-audit-ms2s7bvd/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/system-health-audit-ms2s7bvd/SKILL.md' && test -s '.skill-downloads/system-health-audit-ms2s7bvd/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/audit' && cp -R '.skill-downloads/system-health-audit-ms2s7bvd' '.claude/skills/audit'

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/system-health-audit-ms2s7bvd'

openskills read 'system-health-audit-ms2s7bvd'

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/system-health-audit-ms2s7bvd/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