CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

79

1.40x
Quality

70%

Does it follow best practices?

Impact

94%

1.40x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/issues/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

The body is highly actionable with executable gh commands, but suffers from repetition, lacks validation feedback loops for its batch/destructive operations, and keeps all material inline in a long file rather than splitting advanced material into references.

Suggestions

De-duplicate the repeated CVE-2025-55183 search example and consolidate Best Practices into the Workflows to tighten conciseness.

Add verification checkpoints to batch and destructive operations (e.g., confirm `gh issue close` succeeded, check each `gh issue create` exit status in the loop) to lift workflow clarity above 3.

Move the full security-issue template and batch/API patterns into a `references/` file referenced once from the body to improve progressive disclosure and cut duplication.

DimensionReasoningScore

Conciseness

Mostly concrete commands with no concept-over-explanation, but heavy repetition (the CVE-2025-55183 search appears across Searching, Workflow 1, Integration, and Common Patterns; Best Practices rehashes the Workflows) means it could be tightened; not 2 because content is still predominantly actionable rather than padded prose.

3 / 5

Actionability

Fully executable, copy-paste-ready `gh` commands throughout with concrete flags, JSON/--jq parsing, and a full security-issue template covering the common cases.

5 / 5

Workflow Clarity

Workflows are sequenced but the Batch Operations loop and the destructive `gh issue close` lack verification/validation checkpoints, so the rubric's destructive/batch cap holds at 3; not 4 because validation is absent rather than a minor gap.

3 / 5

Progressive Disclosure

No bundle files exist and the 295-line body inlines content that could be split (the security template is duplicated, batch/API patterns inline) with no reference signaling; structure via headers is present but not enough for 4 given the length.

3 / 5

Total

14

/

20

Passed

Description

75%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.

The description is specific and well-differentiated, clearly naming its actions and scoping itself away from a sibling skill, but it lacks an explicit 'Use when...' trigger phrase, capping completeness.

Suggestions

Add an explicit trigger clause such as 'Use when searching, viewing, or updating existing GitHub issues — especially CVE/security-vulnerability tracking' to lift completeness above 3.

Include a few natural synonyms users might say (e.g., 'issue tracker', 'bug tracking') to broaden trigger-term coverage toward 5.

DimensionReasoningScore

Specificity

Quotes 'Search, list, view, and update existing GitHub issues' — four concrete, distinct actions matching the comprehensive-coverage anchor; not 4 because coverage of core issue operations is complete.

5 / 5

Completeness

Clear 'what' is stated but the 'when' is only weakly implied via 'Primary use case is...' with no explicit 'Use when...' trigger clause, capping at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Natural terms present ('GitHub issues', 'CVE tracking', 'security vulnerability issue management') but missing common synonyms users might say ('bug tracker', 'issue tracker'); good but not comprehensive like the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Clear niche (CVE/security issue management for the ark-security-patcher agent) plus explicit disambiguation ('use the issue-creation skill instead') yields minimal conflict risk.

5 / 5

Total

17

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mckinsey/agents-at-scale-ark
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.