maintainer-issue-pr-management

Manages GitHub issue and pull-request lifecycle including creation, updates, triage labelling, and closeout metadata using canonical templates and repository taxonomy. Use when a maintainer asks to create, update, close, or triage GitHub issues or PRs, or when issue creation requires codebase analysis for scope, labels, or acceptance criteria.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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 tight, actionable skill body with concrete commands, explicit guards for destructive operations, and clean navigation to canonical repo files. The main improvement area is folding validation into the workflow as inline checkpoints rather than relying on separate guard/checklist sections.

Suggestions

Embed an explicit 'validate against current templates/taxonomy before drafting' checkpoint inside Workflow step 2 or 3, with a retry-on-mismatch loop, instead of relying only on the separate Stop Conditions and Acceptance sections.

De-duplicate the guidance shared between Stop Conditions, Gotchas, and the Workflow steps (e.g., 'inspect current state first' appears in all three) to reclaim tokens.

Consider moving the long Conditional Surfaces list into a referenced file so the SKILL.md overview stays leaner while preserving the full surface taxonomy one level deep.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no padding explaining GitHub or issues — but Stop Conditions, Gotchas, and Workflow steps overlap somewhat and could be tightened.	4 / 5
Actionability	Provides copy-paste-ready commands (`make agent-report ENV=cpu\|amd CHANGED_FILES="..."`, `git commit -s`) plus specific label-transition rules and concrete file references, covering the common cases.	5 / 5
Workflow Clarity	A clear five-step sequence is reinforced by Stop Conditions guards (including an explicit destructive-delete guard) and an Acceptance checklist, but validation is distributed across sections rather than embedded as inline validate→fix→retry loops within the workflow.	4 / 5
Progressive Disclosure	Well-organized into clear sections with a 'Must Read' block that signals one-level-deep repo references (CONTRIBUTING.md, PR template, maintainer-policy.yaml, .prowlabels.yaml); the skill stays an overview and does not inline the templates or taxonomy.	5 / 5
	Total	18 / 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, well-scoped description that pairs a concrete capability statement with explicit maintainer-facing triggers. The only soft spot is the second trigger clause, which leans toward internal process language rather than natural user phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete lifecycle actions — 'creation, updates, triage labelling, and closeout metadata' — giving comprehensive coverage rather than a vague domain label.	5 / 5
Completeness	Explicitly answers both 'what' (manages the issue/PR lifecycle using canonical templates and taxonomy) and 'when' ('Use when a maintainer asks to create, update, close, or triage...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'create, update, close, or triage GitHub issues or PRs' are natural user phrases with good synonym coverage, but the secondary trigger about 'codebase analysis for scope, labels, or acceptance criteria' reads as internal mechanism rather than something a user would naturally say.	4 / 5
Distinctiveness Conflict Risk	Targets a clear maintainer niche with distinct, specific triggers ('maintainer asks to create, update, close, or triage GitHub issues or PRs'), giving minimal overlap with 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 suspicious	Warning

	Total	14 / 16 Passed

Repository: vllm-project/semantic-router
Path: tools/agent/skills/maintainer/issue-pr-management/SKILL.md
Commit: d8b03e3

Reviewed: ~1 hour 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.