An efficient, fully executable skill body with excellent organization and no padding. Its one real weakness is the absence of verification steps around batch labeling, which both the judging guidelines and scoring notes flag as a required feedback loop.

Suggestions

Add a verification step after batch labeling, e.g. 'Verify applied labels: gh issue view 33524 --repo storybookjs/storybook --json labels --jq ".[].name"', and note that gh label create fails if the label already exists so the create step should tolerate that.

Include an explicit feedback loop for batch operations: run the chained commands, check each succeeded, and re-run only the failures rather than assuming success.

State what to do when a label does not exist (create it first via the shown gh label create command) so the add-label steps have a complete, ordered workflow.

Dimension	Reasoning	Score
Conciseness	The ~50-line body is lean with zero concept padding — every section (tracking label, severity definitions, applicability table, batch example) earns its place and assumes Claude's competence with gh. Not below 5 because no trimming is obviously possible without losing information.	5 / 5
Actionability	All guidance is copy-paste-ready executable gh CLI commands with concrete parameters (repo, color code, real issue numbers 33524/33527/33526 in the batch example) plus explicit severity definitions. There are no gaps between the commands shown and the common cases.	5 / 5
Workflow Clarity	The content is clearly organized, but the rubric caps workflow clarity at 3 for batch operations lacking validation/verification steps, and the 'Batch labeling' section (chained gh issue edit commands) includes no step to verify labels were applied. This cap takes precedence over the simple-skill exception, so it cannot score 4-5 despite otherwise clear sequencing.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed — the well-organized sections (tracking, severity, applicability, batching) satisfy the simple-skill exception for a top progressive-disclosure score.	5 / 5
	Total	18 / 20 Passed

Description

73%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 solid description with a clear what, an explicit use-when clause, and a distinct niche. Its main gaps are moderate action coverage and missing natural synonyms (triage, severity, bug reports) that would strengthen triggering.

Suggestions

List the concrete label actions in the description (e.g., 'Apply upgrade tracking labels (upgrade:<version>) and severity labels (sev:S1-S4)') to raise specificity from one action to several.

Add natural trigger synonyms such as 'triage', 'severity', or 'bug reports' to the use-when clause: 'Use when triaging or organizing QA findings, bug reports, or release-upgrade issues.'

Mention the batch-labeling capability in the description so users searching for bulk labeling find this skill.

Dimension	Reasoning	Score
Specificity	"Label GitHub issues and PRs found during QA testing" names the domain plus one concrete action, matching the anchor for 1-2 concrete actions without comprehensive coverage. A 4 would require several specific actions listed (e.g., severity labels, tracking labels), which appear only in the body, not the description.	3 / 5
Completeness	Both "what" ("Label GitHub issues and PRs found during QA testing") and "when" ("Use when organizing QA findings with proper labels") are explicitly present. Not 5 because the single when-clause lacks the multiple concrete trigger phrases and synonyms of the top anchor; not 3 because the trigger guidance is explicit rather than weakly implied.	4 / 5
Trigger Term Quality	Natural terms like "GitHub issues", "PRs", "QA testing", "QA findings", and "labels" give good keyword coverage a user would plausibly say. Not 5 because common variations such as "triage", "severity", or "bug reports" are missing.	4 / 5
Distinctiveness Conflict Risk	The combination of GitHub labeling, QA testing, and release-upgrade tracking is a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 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: storybookjs/storybook
Path: .agents/skills/github-qa-labels/SKILL.md
Commit: dc9b30e

Reviewed: 3 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.