CtrlK
BlogDocsLog inGet started
Tessl Logo

devops-troubleshooter

Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability.

29

Quality

23%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/devops-troubleshooter/SKILL.md

The canonical home for this skill is devops-troubleshooter in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

10%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is essentially a persona description and tool catalog rather than actionable guidance. It extensively lists DevOps tools and concepts Claude already knows, provides no executable code or commands, and lacks concrete troubleshooting procedures. The content would need a fundamental restructuring to provide actual value — replacing tool lists with specific runbooks, debugging commands, and worked examples.

Suggestions

Replace the tool/platform catalog with concrete, executable troubleshooting runbooks (e.g., specific kubectl commands for debugging OOMKilled pods, actual log query examples for ELK/Loki).

Add worked examples with specific commands and expected outputs for common scenarios like debugging 504 errors, Kubernetes pod failures, or CI/CD pipeline issues.

Add explicit validation and verification steps to the workflow — e.g., 'Run `kubectl describe pod <name>` to confirm fix, verify no new OOMKill events in last 15 minutes'.

Remove or drastically reduce the 'Capabilities', 'Behavioral Traits', and 'Knowledge Base' sections — Claude already knows what these tools are and doesn't need a personality description to troubleshoot effectively.

DimensionReasoningScore

Conciseness

Extremely verbose and padded. The vast majority of content is listing tools, platforms, and concepts Claude already knows. The 'Capabilities' section is essentially a resume/catalog of DevOps topics with no actionable value — Claude doesn't need to be told what ELK Stack or Prometheus are. The 'Behavioral Traits' and 'Knowledge Base' sections restate obvious troubleshooting principles. This could be reduced by 80%+ without losing useful information.

1 / 5

Actionability

There is zero executable guidance — no commands, no code snippets, no concrete troubleshooting steps, no specific procedures. The entire skill is abstract descriptions and bullet-point lists of tool names. 'Example Interactions' are just task descriptions, not worked examples. The 'Response Approach' is a generic methodology with no specifics. Nothing here tells Claude what to actually do.

1 / 5

Workflow Clarity

The 'Response Approach' section provides a rough 9-step sequence but it's entirely generic (assess, gather data, form hypotheses, implement fixes) with no validation checkpoints, no specific commands, no error recovery loops, and no concrete verification steps. For a skill involving potentially destructive incident response operations, the absence of any validation or feedback loops is a significant gap.

2 / 5

Progressive Disclosure

The content is a monolithic wall of bullet points with no meaningful structure beyond category headers. It references `resources/implementation-playbook.md` but no bundle file exists to support it. The massive inline listing of tools and capabilities should either be removed (Claude knows these) or placed in a reference file. The skill fails to provide a concise overview pointing to detailed materials.

2 / 5

Total

6

/

20

Passed

Description

36%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description reads more like a job title or persona statement than a functional skill description. It relies on buzzwords ('expert,' 'rapid,' 'advanced,' 'modern') without specifying concrete actions, lacks a 'when to use' clause, and uses no file types, tool names, or specific trigger phrases that would help Claude reliably select it.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g., 'Use when the user reports a production incident, service outage, high error rates, or needs help with logs, metrics, or tracing.'

Replace vague qualifiers with specific actions, e.g., 'Analyzes logs, interprets metrics dashboards, traces distributed requests, diagnoses container/Kubernetes failures, and guides incident triage.'

Include natural keywords and tool names users would mention, such as 'Kubernetes, Docker, Prometheus, Grafana, CloudWatch, PagerDuty, error logs, latency spikes, 5xx errors.'

DimensionReasoningScore

Specificity

Names the domain (DevOps troubleshooting, incident response, debugging, observability) but provides no concrete actions. Terms like 'rapid,' 'advanced,' and 'modern' are vague qualifiers rather than specific capabilities.

2 / 5

Completeness

Provides a vague 'what' (troubleshooting, debugging, observability) but has no 'when' clause at all. There is no explicit guidance on when Claude should select this skill, which per the rubric should cap completeness at 3 maximum, and the weak 'what' brings it to 2.

2 / 5

Trigger Term Quality

Includes some relevant keywords like 'incident response,' 'debugging,' and 'observability' that users might naturally use, but misses common variations and synonyms such as 'logs,' 'monitoring,' 'alerts,' 'downtime,' 'outage,' 'metrics,' 'tracing,' or specific tool names.

3 / 5

Distinctiveness Conflict Risk

The DevOps/incident response domain provides some specificity, but 'debugging' and 'troubleshooting' are broad enough to overlap with general coding or sysadmin skills. Without concrete actions or tool references, it could conflict with other debugging-related skills.

3 / 5

Total

10

/

20

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.