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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./scripts/agents/gator/skills/gator-gate/SKILL.md

Quality

Content

66%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.

The body is highly actionable and workflow-clear with strong validation and feedback loops, but it is a verbose monolith that inlines separable material (templates, schemas, state machine) instead of splitting it into one-level-deep reference files.

Suggestions

Move the Comment Templates section (12+ templates) and the review-findings evidence contract into separate reference files under references/, keeping only a concise summary and clearly signaled links in SKILL.md.

De-duplicate the one-disposition-per-head-SHA and 48-business-hour TTL rules by stating each once and cross-referencing from later sections instead of restating.

Split the State Machine and Labels definitions into a references/state-machine.md file to reduce the main body to an overview with well-signaled one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The ~1300-line body restates the same-SHA one-disposition rule and the 48-business-hour TTL rules across many sections (Comment Marker, Human Comment Disposition, Reviewer-quality telemetry, Step 8), giving noticeably verbose, padded prose even for a complex state machine.	2 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: concrete `gh api`/bash snippets, JSON review-request shapes, label-create commands, and exact `OPENSHELL_AGENT_RESULT` sentinel strings covering the common operations.	5 / 5
Workflow Clarity	Clear sequenced workflow (state machine plus numbered Steps 1–12) with explicit validation checkpoints (`validate-review-findings`, jq ledger validation, write-guard exits 21/22) and feedback loops (transient_failure -> retry, validate -> fix -> retry) for destructive GitHub writes.	5 / 5
Progressive Disclosure	A monolithic ~1300-line SKILL.md inlines content that clearly belongs in separate reference files — 12+ comment templates, the review-findings contract, the state machine, and label definitions — with only one real bundled reference (`references/review-findings-schema.md`) and external scripts referenced but not bundled.	2 / 5
	Total	14 / 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 description that clearly states both capability and trigger conditions with concrete, domain-specific actions. Minor improvement is possible around trigger-term synonyms, but it answers what and when distinctly.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — 'Validate and monitor', 'triage issues/PRs', 'gate PRs', 'run gator', 'validate submissions', 'monitor PRs toward merge readiness' — giving comprehensive coverage of the workflow.	5 / 5
Completeness	Explicitly answers 'what' ('Validate and monitor OpenShell GitHub issues and PRs using the gator:* state machine') and 'when' via a concrete 'Use when asked to triage... gate PRs... monitor PRs toward merge readiness' trigger clause.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('triage', 'gate PRs', 'validate submissions', 'monitor PRs', 'merge readiness'), but the terms lean project-specific ('gator', 'gate') and lack common synonyms or variations a user might say.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche — OpenShell GitHub issue/PR gating via the gator:* state machine — with distinct triggers that would not fire for unrelated skills.	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 (1301 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: 292559c

Reviewed: 5 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.