CtrlK
BlogDocsLog inGet started
Tessl Logo

arn-code-ship

This skill should be used when the user says "ship it", "arness code ship", "create PR", "open pull request", "push and PR", "commit and push", "wrap up", "ship the feature", "ship the fix", "ready to ship", "push changes", "finalize", "finish up", or wants to commit, push, and optionally open a pull request. Guides through branching, staging, committing with meaningful messages, pushing, and PR creation. Works standalone or as the final Arness pipeline step. Do NOT use this for reviewing PRs — use /arn-code-review-pr for that.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 highly actionable, well-sequenced shipping workflow with strong validation gates, though its length and inline detail push conciseness and content-splitting below the top level. The two reference files are real and properly one level deep.

Suggestions

Move the lint/format gate and sketch-cleanup procedures into reference files (as done for feature-tracker-update.md) to trim the body and improve progressive disclosure.

De-duplicate the CHANGE_RECORD enrichment description across the GitHub and Bitbucket PR sections by extracting it once and referencing it.

Tighten the sketch-cleanup section's per-status option lists, which restate Delete/Keep repeatedly.

DimensionReasoningScore

Conciseness

Procedural and dense, but the ~260-line body repeats itself (CHANGE_RECORD enrichment explained twice, GitHub/Bitbucket paths re-stated) and the sketch-cleanup section is verbose, so it is mostly efficient but could be tightened.

2 / 3

Actionability

Concrete executable commands throughout ("git branch --show-current", "gh pr create --title \"...\" --body \"...\"", "bkt pr create ...") plus specific numeric thresholds ("N <= 20 → suggest Fix now"), making guidance copy-paste ready.

3 / 3

Workflow Clarity

A clearly numbered 6-step workflow with explicit validation checkpoints (lint/format gate, auth-status checks) and a dedicated error-handling section giving feedback loops for risky operations like push rejection.

3 / 3

Progressive Disclosure

Two real one-level-deep references are clearly signaled ("> Read .../feature-tracker-update.md" and the platform-labels.md path), but the bulk of detailed logic (lint gate, sketch cleanup) is inline rather than split out, leaving structure good but not cleanly separated.

2 / 3

Total

10

/

12

Passed

Description

100%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.

The description is concrete, trigger-rich, and explicitly bounds both when to use the skill and when not to. It clearly exceeds the level-2 anchors on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "branching, staging, committing with meaningful messages, pushing, and PR creation" — matching the multi-action anchor rather than a single-domain description.

3 / 3

Completeness

Explicitly answers both what ("Guides through branching, staging, committing...") and when via the "This skill should be used when..." clause, satisfying the explicit-trigger requirement.

3 / 3

Trigger Term Quality

Strong coverage of natural phrasings users would actually say ("ship it", "create PR", "open pull request", "push and PR", "commit and push", "wrap up", "finalize", "finish up").

3 / 3

Distinctiveness Conflict Risk

Distinct niche triggers plus an explicit exclusion — "Do NOT use this for reviewing PRs — use /arn-code-review-pr for that" — sharply reduces conflict risk.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
AppsVortex/arness
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.