gator-gate

Validate and monitor OpenShell GitHub issues and PRs using the gator:* state machine. Use when asked to triage issues/PRs for project validity, gate PRs, run gator, validate submissions, or monitor PRs toward merge readiness.

Quality

86%

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

81%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 gating workflow with explicit validation feedback loops and a properly signaled one-level reference. Its main weakness is conciseness: the body is very long with repetitive restatements of the same disposition rules, and much of that inline policy could be split into reference files.

Suggestions

Consolidate the repeated one-disposition-per-head-SHA rule into a single authoritative statement and reference it from other sections instead of restating it multiple times.

Move the large Comment Templates block and the reviewer-quality telemetry details into a separate reference file (e.g. references/comment-templates.md) and link to it from the main body to reduce the monolithic wall of text.

Tighten the Pragmatic review calibration and Convergence checkpoint sections by merging overlapping guidance on when to introduce unchanged-code findings, which currently appears in several places.

Dimension	Reasoning	Score
Conciseness	The ~1290-line body is largely policy-dense rather than concept-padded, but it repeatedly restates the same rules (e.g., the one-disposition-per-head-SHA rule across the Comment Marker, Human Comment Disposition, and Review Loop sections), so it could be tightened, matching the score-3 anchor rather than the leaner 4.	3 / 5
Actionability	Concrete executable `gh api`/`jq` commands, exact REST review request shapes, comment templates, and stable `GATOR-<sha>-<ordinal>` finding-ID formats provide copy-paste-ready guidance across common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	A clearly sequenced Step 1-12 workflow over a defined state machine with explicit validation checkpoints (ledger `jq -e` validation, `validate-review-findings`, write-guard exits 21/22) and transient-failure feedback loops for destructive/batch GitHub mutations matches the score-5 anchor.	5 / 5
Progressive Disclosure	The single external reference `references/review-findings-schema.md` is real, one level deep, and clearly signaled, but the SKILL.md body is a monolithic wall of text with heavy inline content (comment templates, telemetry rules) that could be split into separate files, matching the score-4 anchor rather than the cleanly split 5.	4 / 5
	Total	17 / 20 Passed

Description

92%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 third-person description that clearly states both capability and trigger conditions with concrete actions and a distinct niche. The only minor gap is slightly less comprehensive synonym/extension coverage in trigger terms.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions in third person ("Validate and monitor...issues and PRs", "triage", "gate PRs", "run gator", "validate submissions", "monitor PRs toward merge readiness") with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	It explicitly answers both what ("Validate and monitor OpenShell GitHub issues and PRs using the gator:* state machine") and when ("Use when asked to triage issues/PRs...gate PRs, run gator, validate submissions, or monitor PRs...") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases like "triage issues/PRs", "gate PRs", "run gator", "validate submissions", and "monitor PRs toward merge readiness" give good keyword coverage, though a few common synonyms or extensions are missing, matching the score-4 anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	The gator state-machine niche with OpenShell-specific triage/gate triggers is clearly distinct with minimal conflict risk against other skills, matching the score-5 anchor.	5 / 5
	Total	19 / 20 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 (1294 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing, 2 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/OpenShell
Path: scripts/agents/gator/skills/gator-gate/SKILL.md
Commit: 69a05eb

Reviewed: 1 day 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.