onboarding

Deploy your own Open-Inspect instance. Use when the user wants to set up, deploy, or onboard to Open-Inspect. Guides through repository setup, credential collection, Terraform deployment, and verification with user handoffs.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

78%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.

A highly actionable, well-sequenced deployment guide with concrete commands and useful error-handling feedback loops. Its main weakness is that it is monolithic — a long, single-file guide with no progressive disclosure via referenced bundle files.

Suggestions

Split per-service credential collection (Cloudflare, Vercel, Modal, GitHub App, Slack) and the Terraform config details into separate reference files, keeping SKILL.md as a concise phase overview with one-level-deep links.

Add an explicit validation checkpoint before each destructive `terraform apply` (e.g., `terraform plan` review) rather than relying on the two-phase split alone.

Tighten the opening framing paragraph and the per-phase prose to lift conciseness toward a 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean concrete commands, URLs, and config with little padding of concepts Claude already knows; only minor framing sentences ('This is a multi-phase process requiring user interaction...') could be trimmed, landing just below a 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands and exact config blocks (terraform.tfvars, backend.tfvars) covering the common cases, with specific URLs and permission scopes throughout.	5 / 5
Workflow Clarity	Thirteen phases are clearly sequenced with an upfront TodoWrite checklist, a two-phase Terraform pattern, a dedicated verification phase, and an error-handling section with feedback loops; minor validation gaps between phases keep it just below a 5.	4 / 5
Progressive Disclosure	Well organized into phase headers, but the entire ~360-line detailed deployment guide is inlined in SKILL.md with no one-level-deep references to separate files, so content that could be split (per-service credential guides, terraform details) is inline rather than progressively disclosed.	3 / 5
	Total	16 / 20 Passed

Description

95%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.

A strong, specific deployment description with clear what/when structure and good trigger-term coverage. The only weakness is second-person voice ('your own') in the opening clause, which the rubric penalizes on specificity.

Suggestions

Rewrite the opening in third person to avoid the specificity penalty, e.g. 'Deploys a self-hosted Open-Inspect instance. Use when the user wants to set up, deploy, or onboard to Open-Inspect.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('repository setup, credential collection, Terraform deployment, and verification with user handoffs') but opens with the second-person imperative 'Deploy your own Open-Inspect instance', which the rubric penalizes by reducing specificity by one from an otherwise comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Deploy your own Open-Inspect instance... Guides through repository setup, credential collection, Terraform deployment, and verification') and when ('Use when the user wants to set up, deploy, or onboard to Open-Inspect') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural synonyms users would say are comprehensively covered — 'set up, deploy, or onboard to Open-Inspect' — giving multiple phrasings a user would naturally use.	5 / 5
Distinctiveness Conflict Risk	Targets a named product (Open-Inspect) with a clear deployment niche and distinct triggers, creating minimal overlap risk with other skills.	5 / 5
	Total	19 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: ColeMurray/background-agents
Path: .claude/skills/onboarding/SKILL.md
Commit: f3cd32d

Reviewed: about 8 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.