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.

78

1.40x
Quality

68%

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

57%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.

Highly actionable — every operation is backed by executable gh commands — but the body is roughly twice as long as it needs to be, with duplicated integration and template content and no external references. The batch-creation workflow also lacks validation, capping workflow clarity.

Suggestions

Deduplicate: merge the 'Integration with Security Workflow' section into the 'When to use this skill' note, and keep the issue body template in one place (Workflow 3's heredoc or the 'Issue Formatting' section, not both).

Add validation to the batch issue-creation loop — check each `gh issue create` exit status (or verify with `gh issue view` / a follow-up search) before proceeding, which would also lift the workflow_clarity cap.

Move the issue body template and the bulk gh command reference into a references/ file (e.g., references/templates.md and references/commands.md), keeping SKILL.md to the workflows and key examples to cut its length by roughly half.

DimensionReasoningScore

Conciseness

The ark-security-patcher integration is explained twice (the note under "When to use this skill" and the "Integration with Security Workflow" section repeat the same three points and commands), the security-issue body template appears nearly verbatim in both Workflow 3 and "Issue Formatting", "Common Patterns" re-runs searches already shown, and standard `gh` CLI syntax Claude already knows is spelled out — noticeably verbose with several padded sections.

2 / 5

Actionability

Every section provides copy-paste-ready executable `gh` commands, including filtered searches, `--json`/`--jq` parsing, a complete bash if/else workflow, and full issue-creation commands with heredoc bodies — specific examples cover the common cases.

5 / 5

Workflow Clarity

Workflows 1–3 are clearly sequenced and an error-handling section addresses not-found, permission, and rate-limit failures, but there are no explicit validation checkpoints inside the workflows, and the batch creation loop ("for cve in CVE-2025-001 CVE-2025-002; do gh issue create …") performs no success/failure verification — per the judging guideline, batch operations without validation cap this dimension at 3.

3 / 5

Progressive Disclosure

The skill is a single ~300-line file with no references/, scripts/, or assets/ directories. Section headers keep it navigable, but content that clearly belongs in a separate file (the issue body template, the bulk command reference) is inlined and even duplicated, fitting the 'some structure but content that should be separate is inline' anchor. The under-50-line exception does not apply.

3 / 5

Total

13

/

20

Passed

Description

78%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 description: concrete actions, a clear primary use case, and an explicit boundary against a sibling skill. The main gap is the absence of a natural "Use when…" trigger phrase with user-facing synonyms.

DimensionReasoningScore

Specificity

"Search, list, view, and update existing GitHub issues" names four concrete actions plus the domain, matching the 'several specific actions; minor gaps' anchor. It stops short of anchor 5 because create, close, and comment — actions the skill actually supports — are absent from the what-clause.

4 / 5

Completeness

The 'what' is explicit (search, list, view, update existing GitHub issues) and 'when' is given via "Primary use case is CVE tracking and security vulnerability issue management", which is explicit enough to avoid the missing-trigger cap. It falls below anchor 5 because there is no "Use when the user…" phrasing with concrete trigger conditions.

4 / 5

Trigger Term Quality

"GitHub issues", "CVE tracking", and "security vulnerability issue management" are natural phrases users would say, giving good keyword coverage. Not anchor 5 because common synonyms like "bug", "triage", "close issue", or "reopen" are missing.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (existing GitHub issues on the Ark repo, CVE tracking, the ark-security-patcher agent) and explicitly draws a boundary with "For drafting NEW issues with research and task breakdowns, use the "issue-creation" skill instead" — 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.

Validation — 16 / 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.