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.
80
71%
Does it follow best practices?
Impact
94%
1.40xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/issues/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly specifies concrete actions (search, list, view, update), a well-defined domain (GitHub issues, CVE tracking, security vulnerabilities), and explicit routing guidance including a boundary clause distinguishing it from the issue-creation skill. The description is concise, uses third person voice, and provides enough context for accurate skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Search, list, view, and update existing GitHub issues.' Also specifies the primary domain: 'CVE tracking and security vulnerability issue management.' | 3 / 3 |
Completeness | Clearly answers 'what' (search, list, view, update GitHub issues for CVE/security tracking) and 'when' (used by ark-security-patcher agent, for existing issues). Also provides explicit negative boundary ('For drafting NEW issues... use the issue-creation skill instead'), which serves as a strong trigger/routing guide. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'GitHub issues', 'CVE tracking', 'security vulnerability', 'issue management', 'search', 'list', 'view', 'update'. These cover the domain well and match natural user language. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear boundaries. Explicitly differentiates from the 'issue-creation' skill by specifying this is for existing issues, not new ones. The CVE/security vulnerability niche and the named agent context further reduce conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable `gh` CLI commands covering the full range of issue operations, which is its primary strength. However, it is severely bloated with repetition (the repo flag appears ~30 times, templates are duplicated, workflows are restated in multiple sections) and includes unnecessary explanations of basic concepts like rate limiting and permission errors. The content would benefit greatly from consolidation, deduplication, and splitting advanced content into referenced files.
Suggestions
Define the repo as a variable or state it once at the top (e.g., 'All commands below assume `--repo mckinsey/agents-at-scale-ark`') to eliminate ~30 repetitions.
Remove the 'Creating Issues' section and security issue template since the description says to use the 'issue-creation' skill for new issues — or at minimum, add only a brief cross-reference.
Remove the Error Handling section entirely — Claude knows what 'permission denied' and 'not found' mean and how to handle rate limits.
Extract the security issue template and batch operations into separate referenced files to improve progressive disclosure and reduce the main file length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The `--repo mckinsey/agents-at-scale-ark` flag is repeated in every single command (~30 times) when it could be stated once. The 'Integration with Security Workflow' section largely duplicates 'Common Workflows'. The issue template appears twice. Many sections restate things Claude already knows (what rate limiting is, what 'permission denied' means). The skill is ~200 lines when it could be ~60. | 1 / 3 |
Actionability | All commands are concrete, executable `gh` CLI invocations with real flags and options. The bash scripts with JSON parsing (`--jq`) are copy-paste ready. Templates include complete heredoc syntax. Every operation has a specific, runnable example. | 3 / 3 |
Workflow Clarity | Workflows are listed and sequenced (search → check → create/link), but there are no explicit validation checkpoints. The batch operations section has no verification step after creating multiple issues. The 'check for existing CVE issues' workflow says 'If not found, you may want to create one' which is vague rather than prescriptive. | 2 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files. Everything is inline — the security issue template, error handling, batch operations, and integration details could all be split out. The description mentions an 'issue-creation' skill but the content itself includes a full issue creation section, creating confusion about boundaries. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- mckinsey/agents-at-scale-ark
- Commit
f4bfd2d
- Reviewed
Table of Contents
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.