triage-issue

Assess, validate, and route community-filed issues for human disposition and roadmap placement. Takes a specific issue number or processes a confirmed batch of issues labeled state:triage-needed. Investigates reported behavior, separates objective findings from product decisions, and prepares validated issues for a human yes/no decision. Trigger keywords - triage issue, triage, assess issue, review incoming issue, triage issues.

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 thorough, highly actionable triage workflow with strong sequencing and validation checkpoints. Its main weakness is repetition of the human-only constraints across multiple sections, which inflates length without adding clarity.

Suggestions

Consolidate the human-only disposition rules into the 'Critical' section and reference it once from Step 7 rather than restating the full list in multiple places.

Consider extracting the classification table or the triage-comment template into a reference file to shorten the main body and improve progressive disclosure.

Trim redundant restatements of the 'no priority labels / sequencing comes from roadmap association' point to a single authoritative mention.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient domain-specific policy, but the human-only disposition constraints (never apply state:accepted, never close a validated issue, no priority labels) are restated across the 'Critical' section, Step 7, and the relationship section, which could be tightened.	3 / 5
Actionability	Guidance is fully executable: copy-paste gh CLI commands, a concrete classification table with per-row agent actions, a complete comment template, and a detailed sub-agent prompt for diagnosis.	5 / 5
Workflow Clarity	Steps 1–7 are clearly sequenced with explicit validation checkpoints — a confirmation gate before batch commenting, a prior-triage check, and a completeness check — plus feedback loops (request retest, request missing info) that satisfy the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Sections are well organized and external skill references (debug-openshell-cluster, debug-inference, openshell-cli) are clearly signaled at one level deep, but no bundle files exist and some inline material (the classification table, comment template) could optionally be split out.	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 description that clearly communicates purpose, concrete actions, and trigger conditions in third person. The only minor weakness is mild redundancy among the trigger keywords.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Assess, validate, and route', 'Investigates reported behavior, separates objective findings from product decisions', and 'prepares validated issues for a human yes/no decision' — giving comprehensive coverage rather than vague abstractions.	5 / 5
Completeness	It explicitly states both what the skill does (assess/validate/route issues) and when to use it via an explicit 'Trigger keywords - ...' clause, satisfying the what-and-when requirement with concrete triggers.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('triage issue', 'assess issue', 'review incoming issue'), but 'triage'/'triage issue'/'triage issues' are near-duplicates and a few common synonyms are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The skill occupies a clear niche — triaging community-filed issues tied to the 'state:triage-needed' label — with distinct triggers and minimal overlap risk against other 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: NVIDIA/OpenShell
Path: .agents/skills/triage-issue/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.