CtrlK
BlogDocsLog inGet started
Tessl Logo

cloud-devops

Cloud infrastructure and DevOps workflow covering AWS, Azure, GCP, Kubernetes, Terraform, CI/CD, monitoring, and cloud-native development.

50

Quality

55%

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/cloud-devops/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 is well-structured as a multi-phase workflow bundle with clear sequencing and a quality-gates checklist, but it leans on abstract action lists and trivial invocation prompts rather than concrete executable guidance, and lacks per-phase validation checkpoints for its destructive/batch operations. Token efficiency is adequate but weakened by repetitive copy-paste prompts that restate the skills lists.

Suggestions

Add per-phase validation checkpoints (e.g. 'Verify `terraform plan` is clean before apply' or 'Confirm pod readiness before proceeding') to lift workflow_clarity above the destructive-operation cap.

Replace abstract Actions with concrete commands or reference snippets (e.g. `terraform apply`, `kubectl rollout status`) instead of 'Design cloud architecture'.

Remove or consolidate the 'Copy-Paste Prompts' that merely restate the adjacent Skills-to-Invoke lists to reduce redundancy.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the seven-phase structure is repetitive and the 'Copy-Paste Prompts' (e.g. 'Use @terraform-skill to provision AWS infrastructure') largely restate the preceding skills list, so it is 'mostly efficient but could be tightened'.

3 / 5

Actionability

The copy-paste invocation prompts are concrete, but the numbered Actions are high-level and abstract ('Design cloud architecture', 'Set up accounts and billing') with no executable commands, configs, or concrete steps, matching 'some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

The seven phases are clearly sequenced and there is a terminal Quality Gates checklist, but the phases involve destructive/batch operations (provisioning, deployments) with no per-phase validation checkpoints or error-recovery feedback loops, so per the feedback-loops guideline workflow_clarity is capped at 3.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and all content is inline, but it is well organized into clearly signaled sections (Overview, phases, provider workflows, Quality Gates); the long inline per-phase detail could be split out, so it fits 'good structure; minor organization gaps'.

4 / 5

Total

13

/

20

Passed

Description

57%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 scopes the cloud/DevOps domain with strong natural trigger terms, but it lists coverage areas rather than concrete actions and omits any explicit 'Use when' trigger clause. This caps completeness and leaves it moderately broad with notable overlap risk against single-cloud or single-tool skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when provisioning cloud infrastructure, setting up CI/CD pipelines, or deploying Kubernetes workloads across AWS, Azure, or GCP.'

Replace the generic 'covering' with concrete verbs ('provision', 'orchestrate', 'deploy', 'monitor') to raise specificity.

Narrow or qualify the scope (e.g. 'multi-cloud workflow bundle') to reduce overlap with individual provider-specific skills.

DimensionReasoningScore

Specificity

The phrase 'Cloud infrastructure and DevOps workflow covering AWS, Azure, GCP, Kubernetes, Terraform, CI/CD, monitoring, and cloud-native development' names the domain plus many sub-domains, but the only action verb is the generic 'covering' — there are no concrete actions like 'provision', 'deploy', or 'orchestrate', so it sits at the 'names domain and 1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

It gives a clear 'what' (cloud infra and DevOps workflow covering named areas) but has no 'Use when...' or equivalent explicit trigger clause, so per the judging guideline a missing 'Use when' clause caps completeness at 3 ('clear what, when missing or only weakly implied').

3 / 5

Trigger Term Quality

Natural user-facing terms are well covered — 'AWS, Azure, GCP, Kubernetes, Terraform, CI/CD, monitoring' are exactly what users say — though a few natural variants (e.g. 'kubectl', 'infrastructure as code', 'pipelines') are missing, fitting the 'good keyword coverage, a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

It is anchored to the cloud/DevOps niche (distinct from unrelated skills) but spans so many areas that it overlaps heavily with individual skills like aws-skills, terraform, and kubernetes, matching 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

13

/

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.