launch-openshell-gator

Launch and supervise OpenShell gator agents. Use when starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting stuck gators, inspecting gator logs, or experimenting with gator harness/model overrides. Trigger keywords - launch gator, start gator, run gator, gator sandbox, supervised gator, gator logs, restart gator.

Quality

92%

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

Quality

Content

85%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 content is highly actionable with a well-sequenced, validation-backed workflow and clean organization. Its main weakness is token efficiency from repeating the same input-normalization block across multiple sections rather than defining it once.

Suggestions

Extract the repeated gateway-name/PR-number regex validation into a single named snippet or a short helper script, then reference it from each launch section instead of duplicating the block verbatim.

Move the per-section marker/sentinel explanation duplicates (e.g. the gateway validation echoed in Monitoring and Restarting) to the single Input Normalization section and link back to it.

Consider moving the long Troubleshooting symptom/action pairs into a reference file once a bundle is introduced, keeping SKILL.md as the launch-and-monitor overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly task-focused and assumes operator competence, but the gateway-name and PR-number regex validation block is duplicated verbatim across roughly six launch/monitoring sections, adding tokens that a single shared snippet or referenced helper would remove.	2 / 3
Actionability	Provides fully executable bash commands, concrete sandbox-name formats, and complete copy-paste-ready `run.sh` invocations with inline validation guards.	3 / 3
Workflow Clarity	A clearly sequenced Preflight (Steps 1–6), input normalization, launch flows, and a sentinel/status table give explicit checkpoints, and destructive restarts include a 'check that the sandbox is truly stale' guard before deletion.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so the single SKILL.md is appropriately organized into well-signaled sections with a Key Paths table; cross-references point to sibling skills rather than nested bundle files.	3 / 3
	Total	11 / 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, complete, and distinctive, covering concrete actions plus an explicit 'Use when' clause and natural trigger keywords. It is a strong, concise frontmatter description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting stuck gators, inspecting gator logs, or experimenting with gator harness/model overrides' — matching the multi-action anchor.	3 / 3
Completeness	Clearly answers both what ('Launch and supervise OpenShell gator agents') and when ('Use when starting gator on issues or PRs...') with an explicit 'Use when' clause and enumerated triggers.	3 / 3
Trigger Term Quality	Explicit 'Trigger keywords - launch gator, start gator, run gator, gator sandbox, supervised gator, gator logs, restart gator' gives good coverage of natural phrases an operator would say.	3 / 3
Distinctiveness Conflict Risk	The gator-on-OpenShell niche is sharply scoped with distinct triggers, making it unlikely to fire for unrelated skills.	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
relative_links	Relative link issues: 9 missing	Warning
referenced_paths_exist	Referenced path issues: 15 missing, 15 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/OpenShell
Path: .agents/skills/launch-openshell-gator/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.