Name: arn-code-pick-issue
Rating: 72 (1 reviews)
Author: AppsVortex

arn-code-pick-issue

This skill should be used when the user says "pick issue", "work on issue", "arness code pick", "arness code pick issue", "arn-code-pick-issue", "grab issue", "pick from backlog", "what should I work on", "show issues", "find issue", "browse issues", "next issue", "select issue", "choose issue", "what's unblocked", "work on next feature", "pick from feature tracker", or wants to browse issues filtered by Arness labels, select one, and route it to the appropriate Arness pipeline skill for implementation. Supports local-first dependency resolution from a greenfield feature backlog when available. Requires an issue tracker (GitHub or Jira) to be configured for remote issue browsing. Do NOT use this for creating new issues — use /arn-code-create-issue for that.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-3

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

A well-structured, highly actionable multi-platform workflow with clear sequencing, validation checkpoints, and appropriate use of a one-level reference. The main opportunity is reducing repetition across the GitHub/Jira parallel branches.

Suggestions

Factor the shared GitHub/Jira steps and repeated user-facing messages (e.g. the "no results" suggestion) into a single parameterized block to cut duplicated tokens.

The Error Handling section duplicates several messages already stated inline in Steps 1–6; consolidate to a single source to tighten the body further.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural instruction with no concept-explaining fluff, but the parallel GitHub/Jira branches and duplicated messages (e.g. the "no results / suggest /arn-code-create-issue" line repeated at Step 3 for both trackers) could be tightened; not a 3 due to this repetition.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: concrete `gh issue list`/`gh issue view` commands, a JQL query template, exact label names, and explicit JSON field lists.	3 / 3
Workflow Clarity	A clearly sequenced Steps 1–7 flow with explicit validation checkpoints (git/gh auth/MCP prerequisites in Step 1, the Step 6.5 freshness gate) and a thorough Error Handling section covering recovery for each failure mode.	3 / 3
Progressive Disclosure	The greenfield detection/resolution detail is offloaded to a real one-level reference (references/greenfield-backlog-resolution.md, verified present) and clearly signaled via a blockquote in Step 1b, keeping the main body an overview.	3 / 3
	Total	11 / 12 Passed

Description

92%Weight 40%Scale 1-3

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, explicit description that covers what, when, and concrete actions with broad natural trigger terms. Its only weakness is a set of generic unqualified issue phrases that raise overlap risk with sibling issue skills.

Suggestions

Qualify the generic triggers (e.g. "show Arness issues", "find Arness-labeled issue") so they cannot fire for non-Arness issue-management contexts.

Consider trimming the longest trigger enumeration slightly; the most distinctive phrases ("arness code pick", "pick from feature tracker", "what's unblocked") already carry the signal.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "browse issues filtered by Arness labels, select one, and route it to the appropriate Arness pipeline skill for implementation" and "local-first dependency resolution from a greenfield feature backlog" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (browse/select/route issues, dependency resolution) and when ("This skill should be used when the user says...") with additional negative guidance pointing to /arn-code-create-issue.	3 / 3
Trigger Term Quality	Extensive natural trigger coverage ("pick issue", "what should I work on", "what's unblocked", "grab issue", "next issue", "pick from backlog") spanning common phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The Arness niche and negative guidance are distinctive, but a cluster of unqualified generic triggers ("show issues", "find issue", "browse issues", "next issue", "select issue") could overlap with other issue-management skills; not a clear 3 because conflict risk is moderate.	2 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-code/skills/arn-code-pick-issue/SKILL.md
Commit: 7f87870

Reviewed: 14 days 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.