Name: devops-troubleshooter
Rating: 37.6 (1 reviews)
Author: administrakt0r

Blog Docs Log inGet started

devops-troubleshooter

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

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

Quality

Content

25%Weight 40%Scale 1-5

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

The body is a persona resume: an exhaustive catalog of domains and tool names that adds little beyond what Claude already knows, with no executable commands, debugging procedures, or decision trees. Its single pointer to detail lives in a nonexistent file, so the skill provides neither lean overview nor usable depth.

Suggestions

Replace the tool-name catalogs with executable triage recipes (e.g. concrete kubectl/log/tracing command sequences for the 'Example Interactions' scenarios) and move the domain catalogs into a real references/ file.

Fix the broken pointer: create `references/implementation-playbook.md` (or correct the path from `resources/`) so the one progressive-disclosure link actually resolves.

Tighten the Response Approach into a numbered workflow with explicit validation checkpoints (e.g. 'verify hypothesis with a read-only probe before applying any change', 'confirm service recovery before closing the incident') and cut the redundant Knowledge Base and Behavioral Traits sections.

Dimension	Reasoning	Score
Conciseness	Roughly 130 lines catalog tool and platform names Claude already knows (ELK, Prometheus, DataDog, kubectl, dig), plus a 'Knowledge Base' section that restates the Capabilities section and 'Behavioral Traits' padding. This is 'noticeably verbose; several padded sections' rather than level 1, since it is compact list-form padding rather than concept explanation.	2 / 5
Actionability	No executable commands, code, or concrete procedures appear anywhere — 'kubectl mastery: Advanced debugging commands' and 'Network analysis: tcpdump, Wireshark' name tools without any usage. The 9-step 'Response Approach' and 'Example Interactions' are high-level hints missing the specific steps to execute, matching anchor 2 rather than level 1 because a rough sequence and concrete scenario phrasings do exist.	2 / 5
Workflow Clarity	The 'Response Approach' provides a rough 9-step sequence but the steps are abstract ('Gather comprehensive data', 'Implement immediate fixes') with no validation checkpoints or feedback loops, despite incident-response fixes being potentially disruptive. This fits 'Rough sequence present but many gaps; validation absent'.	2 / 5
Progressive Disclosure	The monolithic capabilities catalog is exactly the content that belongs in separate reference files, and the body's only reference — 'open `resources/implementation-playbook.md`' — points to a file that does not exist (no references/, scripts/, or assets/ directories ship with the skill). Broken navigation plus inlined bulk content fits 'Minimal structure; content that clearly belongs in separate files is inlined'.	2 / 5
	Total	8 / 20 Passed

Description

45%Weight 40%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 as a persona title rather than a capability statement with triggers. It conveys the domain clearly but lists no concrete actions and offers no 'Use when...' guidance, limiting both completeness and trigger discoverability.

Suggestions

Replace the role-style sentence with concrete actions, e.g. 'Triage production incidents, debug Kubernetes/network/CI-CD failures, and analyze logs, metrics, and distributed traces.'

Add an explicit trigger clause, e.g. 'Use when the user reports outages, OOMKills, failed deployments, or asks to debug infrastructure or cloud services.'

Include the natural keywords users actually say — Kubernetes, kubectl, logs, metrics, tracing, CI/CD, AWS/Azure/GCP — to improve trigger matching.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Expert DevOps troubleshooter') but its actions are generic role labels ('rapid incident response, advanced debugging, and modern observability') rather than concrete actions like 'analyze logs' or 'trace requests'. It matches the anchor 'Names the domain but actions are minimal or generic', not level 3, which requires 1-2 concrete actions.	2 / 5
Completeness	The 'what' is clear (expert troubleshooter with three named specializations) but there is no 'Use when...' clause or equivalent trigger guidance anywhere; per the judging guidelines, a missing 'Use when...' caps completeness at 3. Not level 4 because 'when' is entirely absent rather than just imprecise.	3 / 5
Trigger Term Quality	'incident response', 'debugging', and 'observability' are natural terms, but the most common user phrasings — Kubernetes/kubectl, logs, metrics, CI/CD, cloud provider names — are absent. This fits 'Some relevant keywords but missing common variations or synonyms' rather than level 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	'DevOps troubleshooter' is a recognizable niche, but the description is broad enough to overlap with cloud, SRE, and general debugging skills, fitting 'Somewhat specific but could still overlap with similar skills'. Not level 4 because no concrete triggers distinguish it from those neighbors.	3 / 5
	Total	11 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/devops-troubleshooter/SKILL.md
Commit: 64adc55

Reviewed: 15 hours ago

Table of Contents

Discovery Implementation Validation

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.