Name: arn-infra-verify
Rating: 64.8 (1 reviews)
Author: AppsVortex

arn-infra-verify

This skill should be used when the user says "verify deployment", "verify infra", "check deployment", "arn infra verify", "infra verify", "health check", "check health", "verify staging", "verify production", "is my deployment healthy", "check if deployment worked", "run health checks", "deployment verification", "check infrastructure", "validate deployment", "verify environment", "post-deployment check", "infra health", "check dns", "check ssl", "verify endpoints", "smoke test", "integration test", or wants to validate that a deployed environment is healthy and its resources match the expected state. This skill runs health checks, DNS verification, SSL validation, resource state comparison, and updates issue labels and environments.md with verification results.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/arn-infra/skills/arn-infra-verify/SKILL.md

Quality

Content

62%Weight 40%Scale 1-3

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

A well-sequenced orchestration workflow with excellent validation checkpoints and error handling, but it is verbose and relies on templated placeholders plus some unverifiable external references rather than tight, self-contained guidance.

Suggestions

Move the per-status next-steps summaries and the full remediation table into a reference file (e.g. remediation.md) and link to it, reducing the body length and token cost.

Replace templated placeholders like "Read <resource-manifest-path>" and "Endpoints: [list of endpoints...]" with concrete examples or a single worked example so the guidance is copy-paste ready.

Verify that external cross-skill references (experience-derivation.md, ensure-config.md) resolve at the cited plugin paths, or inline the small bits actually needed by this skill.

Dimension	Reasoning	Score
Conciseness	The 276-line body is mostly actionable with little concept-explanation fluff, but repeated full next-steps summaries per PASS/WARN/FAIL branch and long inline remediation tables add length that could be tightened or offloaded to references.	2 / 3
Actionability	Concrete guidance is present (exact label names, exact user prompts, agent invocation with a model parameter, file-update instructions), but code blocks are templated placeholders ("Read <resource-manifest-path>", "Endpoints: [list of endpoints...]") rather than executable commands, consistent with an orchestration skill.	2 / 3
Workflow Clarity	A clear 5-step sequence with explicit validation checkpoints — config-missing and never-deployed stops, PASS/WARN/FAIL branching, an Error Handling section, and a re-running-is-idempotent note — providing strong feedback loops for a risky operation.	3 / 3
Progressive Disclosure	Two real reference files (health-check-patterns.md, verification-report-template.md) are clearly signaled with read directives, but the body is long and several cross-skill references (${CLAUDE_PLUGIN_ROOT}/.../experience-derivation.md, ensure-config.md) point outside the bundle and cannot be verified as present.	2 / 3
	Total	9 / 12 Passed

Description

92%Weight 40%Scale 1-3

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

A strong, third-person description that clearly states capabilities and explicit use-when triggers with good natural-language coverage. Its main weakness is an over-long trigger-term enumeration that could be trimmed without losing coverage.

Suggestions

Trim the trigger-term list to the most natural 6-8 phrases (e.g. keep "verify deployment", "health check", "smoke test", "validate deployment") and drop near-duplicates to reduce verbosity.

Move the secondary mechanics ("updates issue labels and environments.md with verification results") into the body; the description should focus on what/when rather than internal side effects.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "runs health checks, DNS verification, SSL validation, resource state comparison, and updates issue labels and environments.md" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does and when to use it: "This skill should be used when the user says ... or wants to validate that a deployed environment is healthy and its resources match the expected state."	3 / 3
Trigger Term Quality	Strong coverage of natural terms users would say ("verify deployment", "health check", "smoke test", "integration test", "validate deployment"), but the trigger list is unusually long and padded with near-synonyms, which slightly dilutes quality.	2.5 / 3
Distinctiveness Conflict Risk	Clear niche — post-deployment infrastructure verification — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11.5 / 12 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: AppsVortex/arness
Path: plugins/arn-infra/skills/arn-infra-verify/SKILL.md
Commit: 7f87870

Reviewed: 14 days 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.