CtrlK
BlogDocsLog inGet started
Tessl Logo

devops-troubleshooter

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

38

Quality

36%

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/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

23%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 skill body is a padded catalogue of DevOps tool names and abstract capability descriptions with no executable commands or diagnostic recipes. Its one reference points to a missing file, and the workflow lacks validation checkpoints, leaving it largely non-actionable despite clear sectioning.

Suggestions

Cut the tool-name enumerations (which Claude already knows) and replace them with concrete, runnable diagnostic commands and recipes for the most common incident classes (OOMKills, 504s, deadlocks, DNS failures).

Add explicit validation/verification checkpoints to the Response Approach (e.g., 'confirm the fix restored service via metrics before declaring resolved') so the workflow can exceed the validation cap of 3.

Move the long capability and behavioral-trait lists into real reference files under references/ and link to them one level deep, fixing or removing the broken 'resources/implementation-playbook.md' pointer.

DimensionReasoningScore

Conciseness

The body is a ~150-line enumeration of tool and capability lists (ELK, DataDog, Prometheus, kubectl, tcpdump, etc.) that Claude already knows, padded across ten subsections with little unique guidance — noticeably verbose with several padded sections, above 'severely verbose explaining concepts' (1) but below 'mostly efficient' (3).

2 / 5

Actionability

Every section only describes ('kubectl mastery: Advanced debugging commands, resource inspection') rather than instructs, with zero executable commands, code, or concrete diagnostic recipes — matching 'entirely vague or abstract; no concrete code or commands; only describes rather than instructs'.

1 / 5

Workflow Clarity

The 'Response Approach' gives a clear 9-step sequence but with no validation checkpoints, no commands, and no feedback loops; incident-response fixes can be destructive, so the missing validation cap of 3 applies, preventing a 4.

3 / 5

Progressive Disclosure

Although section headers exist, the bulk (capability/tool enumerations, behavioral traits, example interactions) is inlined content that belongs in separate reference files, and the lone reference to 'resources/implementation-playbook.md' points to a non-existent path with no bundle files present — 'minimal structure; content that belongs in separate files is inlined'.

2 / 5

Total

8

/

20

Passed

Description

50%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 clearly names the skill's domain and specializations but lacks any explicit 'Use when...' trigger clause, capping completeness, and its keyword set is solid but not comprehensive. It is a competent but generic DevOps troubleshooting description rather than a sharp, trigger-rich one.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when debugging production incidents, analyzing logs/metrics/traces, or troubleshooting Kubernetes, CI/CD, or cloud platform issues').

Replace area-label specializations with concrete verbs (e.g., 'analyzes logs and distributed traces, diagnoses OOMKills and pod failures, performs root-cause analysis') to lift specificity.

Include natural synonyms and tool mentions users actually say ('Kubernetes', 'kubectl', 'Prometheus', 'on-call') to improve trigger-term coverage and distinctiveness.

DimensionReasoningScore

Specificity

Names the DevOps troubleshooter domain plus three specializations ('rapid incident response, advanced debugging, and modern observability'), but these are area labels rather than concrete verbs, leaving coverage non-comprehensive — above the 'minimal/generic actions' anchor (2) but short of 'several specific actions' (4).

3 / 5

Completeness

It states a clear 'what' (a DevOps troubleshooter specializing in incident response, debugging, observability) but has no 'Use when...' or equivalent explicit 'when' clause, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Terms like 'DevOps troubleshooter', 'incident response', 'debugging', and 'observability' are relevant keywords a user might say, but there are no synonyms or common variations and no explicit trigger phrasing, fitting 'some relevant keywords but missing common variations' rather than 'good coverage' (4).

3 / 5

Distinctiveness Conflict Risk

'DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability' is a recognizable niche but the broad DevOps/debugging scope could overlap with Kubernetes, SRE, or observability-specific skills, matching 'somewhat specific but could still overlap' rather than 'mostly distinct' (4).

3 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.