Name: ark-issues
Rating: 82 (1 reviews)
Author: mckinsey

ark-issues

Search, list, view, and update existing GitHub issues. Primary use case is CVE tracking and security vulnerability issue management. Used by the ark-security-patcher agent. For drafting NEW issues with research and task breakdowns, use the "issue-creation" skill instead.

1.40x

Quality

—

Does it follow best practices?

Impact

94%

1.40x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete, executable gh commands and useful templates, but it is verbose and repetitive, lacks verification checkpoints around its batch and destructive operations, and is a monolithic wall of text rather than an overview pointing to one-level-deep references.

Suggestions

Add validation/verification steps to destructive and batch workflows (e.g., confirm `gh issue create` succeeded and capture the new issue number before linking a PR; verify an issue exists before closing it).

De-duplicate repeated commands and factor out the constant `--repo mckinsey/agents-at-scale-ark` into a one-time note to reduce token cost.

Extract the issue-creation body template and full workflow scripts into a reference file, keeping SKILL.md as a concise overview with clearly signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete commands but is padded with repetition — the same `gh search issues` / repo-target examples recur across "GitHub CLI Commands", "Common Workflows", and "Integration with Security Workflow", and the repo slug is restated in nearly every command — so it could be tightened significantly.	2 / 3
Actionability	Commands are fully executable and copy-paste ready (e.g., `gh issue view 123 --repo ... --json number,title,body,state,labels`), with specific flags and a complete issue-creation body template, matching the score-3 anchor.	3 / 3
Workflow Clarity	Workflows are sequenced, but batch/destructive operations (the "Create multiple issues from a list" loop, `gh issue close`) lack any verification step confirming the action succeeded, which the guidelines say caps workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist and the ~300-line SKILL.md is a single monolithic document with inline content (templates, full workflows, error handling) that could be split into references, so organization is present but not appropriately separated.	2 / 3
	Total	9 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and well-differentiated, with strong natural trigger terms and an explicit disambiguation against the issue-creation skill. Its main weakness is the absence of an explicit "Use when..." trigger clause, leaving the invocation condition implied rather than stated.

Suggestions

Add an explicit "Use when..." clause naming the user-facing triggers (e.g., searching or updating existing GitHub issues, CVE/vulnerability issue tracking).

Lead with the trigger guidance so the primary use case reads as an invocation condition rather than a background fact.

Dimension	Reasoning	Score
Specificity	"Search, list, view, and update existing GitHub issues" lists multiple concrete actions, matching the score-3 anchor that rewards enumerating specific actions rather than vague language.	3 / 3
Completeness	The "what" is explicit and the "when" is only conveyed via "Primary use case is CVE tracking" and "Used by the ark-security-patcher agent"; there is no explicit "Use when..." trigger clause, which the guidelines say caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms a user would say are well covered — "GitHub issues", "CVE tracking", "security vulnerability issue management" — giving good coverage of common phrasings rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly scoped to existing-issue management for CVE tracking, and it explicitly redirects NEW-issue drafting to the "issue-creation" skill, making overlap with sibling skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mckinsey/agents-at-scale-ark
Commit: b0cc1b7

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.