openshell-cli

Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing. Covers basic through advanced multi-step workflows. Trigger keywords - openshell, sandbox create, sandbox exec, sandbox connect, logs, provider create, provider profile, provider refresh, policy set, policy get, settings, service expose, forward, port forward, BYOC, bring your own container, inference, use openshell, run openshell, CLI usage, manage sandbox, manage provider, gateway add, gateway select.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

77%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.

The body is highly actionable with clear, validated multi-step workflows, but it is verbose with redundant sections and relies on a non-existent cli-reference.md reference. Tightening duplication and either providing or removing the broken reference would raise the weaker dimensions.

Suggestions

Remove the duplicate --help self-teaching explanation (keep it in one place) and consider dropping or trimming the Quick Reference table that repeats commands already shown in the workflows.

Provide the referenced cli-reference.md bundle file or remove the dangling [cli-reference.md](cli-reference.md) link so progressive disclosure points at real material.

Consider moving the large command-flag reference and Quick Reference table into cli-reference.md so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is ~660 lines with redundant material: the "Self-Teaching via --help" guidance is explained twice (Overview and a dedicated section) and the Quick Reference table restates commands already shown in the workflows. It avoids score 1 because it largely assumes Claude's competence and does not explain basic concepts, but it is not lean enough for score 3.	2 / 3
Actionability	The body is dominated by concrete, executable, copy-paste-ready bash commands with specific flags and values (e.g., "openshell provider create --name my-github --type github --from-existing"). It does not drop to 2 because guidance is complete and executable rather than pseudocode or abstract.	3 / 3
Workflow Clarity	Workflow 4 provides an ASCII flow diagram, seven numbered steps, and explicit validation checkpoints (verify revision status "loaded" vs "failed", documented exit codes 0/1/124) with a feedback loop; destructive and batch operations carry warnings. It does not fall to 2 because validation checkpoints and feedback loops are explicit.	3 / 3
Progressive Disclosure	The body references [cli-reference.md](cli-reference.md) for the command tree, but no such bundle file exists, so the reference is broken; additionally, content that could be split out (the large Quick Reference table, detailed flag lists) is inline. It does not drop to 1 because internal organization via headers and tables is strong and references are not deeply nested.	2 / 3
	Total	10 / 12 Passed

Description

100%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.

The description is specific, comprehensive, and provides explicit trigger guidance for a clearly distinct CLI niche. Its only weakness is that the trigger guidance is presented as a verbose keyword dump rather than a clean "Use when..." clause.

Dimension	Reasoning	Score
Specificity	The description names multiple specific capability areas for the OpenShell CLI: "sandbox management, gateway registration, provider configuration and refresh, policy iteration, settings, service exposure, BYOC workflows, and inference routing", matching the anchor for listing multiple specific concrete actions.	3 / 3
Completeness	It clearly answers "what" (the enumerated CLI capability areas) and "when" via an explicit "Trigger keywords -" list, which constitutes equivalent explicit trigger guidance. It does not fall to 2 because the when-guidance is explicit rather than merely implied.	3 / 3
Trigger Term Quality	The explicit "Trigger keywords" list gives good coverage of natural terms a user would say, including "openshell", "BYOC", "bring your own container", "port forward", "use openshell", "run openshell", and "manage sandbox". It is not stuck at 2 because it goes beyond a single relevant keyword to broad natural-language coverage.	3 / 3
Distinctiveness Conflict Risk	The OpenShell CLI niche with distinct triggers ("openshell", "BYOC", "sandbox create", "gateway select") is unlikely to conflict with other skills. There is no overlap concern pulling it down to 2.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (661 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/OpenShell
Path: .agents/skills/openshell-cli/SKILL.md
Commit: deced87

Reviewed: 6 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.