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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

77%

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 runbook with strong validation and error-recovery structure. Its main weakness is conciseness (some inferable prose) and progressive disclosure (a single long file rather than split reference files for per-phase detail).

Suggestions

Trim inferable explanatory prose such as the App Home settings sentence and the Google OAuth consent-screen rationale to improve conciseness.

Extract large per-phase blocks (full terraform.tfvars template, Slack/GitHub bot post-deploy setup) into reference files and link them one level deep, keeping SKILL.md as an overview.

The body is command-dense; consider marking the conditional phases (4b, 5, 9, 10) more tersely as 'if enabled, see X.md' to reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	Mostly command-dense and efficient, but includes explanatory prose Claude could infer (e.g., "The App Home provides a settings interface where users can configure their preferred Claude model" and the Google OAuth consent-screen rationale), so it could be tightened.	2 / 3
Actionability	Fully executable commands with concrete substituted values throughout — e.g. "openssl pkcs8 -topk8 ... -out /tmp/github-app-key-pkcs8.pem", "terraform init -backend-config=backend.tfvars" — copy-paste ready.	3 / 3
Workflow Clarity	A 13-phase numbered sequence seeded via a TodoWrite checklist, with the two-phase Terraform split, explicit verification curls, and an Error Handling section providing feedback loops for recovery.	3 / 3
Progressive Disclosure	Well-sectioned but monolithic: ~340 lines in a single SKILL.md with no reference files, even though per-phase detail (e.g. full Terraform tfvars, Slack/GitHub bot setup) could be split out for one-level-deep navigation.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, concise description that states concrete capabilities and gives an explicit 'Use when' trigger tied to natural user phrasing. It is clearly niche-scoped to Open-Inspect deployment with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "repository setup, credential collection, Terraform deployment, and verification with user handoffs" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ("Deploy your own Open-Inspect instance") and when ("Use when the user wants to set up, deploy, or onboard...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	"Use when the user wants to set up, deploy, or onboard to Open-Inspect" covers natural terms (set up, deploy, onboard) a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Targets a single named product's deployment lifecycle with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: ColeMurray/background-agents
Commit: 04a1ba7

Reviewed: 4 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.