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.
84
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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 skill description that excels across all dimensions. It provides an extensive list of natural trigger phrases, clearly describes the concrete actions performed, explicitly states when to use it and when not to, and distinguishes itself from related skills. The only minor note is that the long list of trigger phrases makes it slightly verbose, but this serves the functional purpose of ensuring correct skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: branching, staging, committing with meaningful messages, pushing, and PR creation. Also clarifies it works standalone or as a pipeline step. | 3 / 3 |
Completeness | Clearly answers both 'what' (guides through branching, staging, committing, pushing, PR creation) and 'when' (explicit list of trigger phrases plus a general description of when to use it). Also includes a negative boundary ('Do NOT use this for reviewing PRs'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'ship it', 'create PR', 'open pull request', 'push and PR', 'commit and push', 'wrap up', 'ship the feature', 'finalize', 'finish up', 'push changes', and more. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct with clear boundaries — explicitly differentiates from the PR review skill (/arn-code-review-pr) and focuses specifically on the shipping/commit/push/PR creation workflow. The trigger terms are specific to this action domain. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent workflow clarity, providing specific commands, clear sequencing, and robust error handling throughout the shipping process. However, it is significantly over-verbose — the lint gate sub-step alone is nearly as long as many complete skills, and the sketch cleanup and dual-platform PR logic add substantial bulk that should be offloaded to reference files. The content would benefit greatly from aggressive decomposition into referenced sub-documents.
Suggestions
Extract the Lint and Format Gate (Step 3, sub-step 3) into a separate reference file like `references/lint-gate.md` and summarize it in 3-4 lines in the main skill.
Move the Sketch Cleanup section (Step 5b) into `references/sketch-cleanup.md` — it's a conditional side-flow that doesn't need to be inline.
Consolidate the GitHub and Bitbucket PR creation paths into a shared description with platform-specific commands in a reference file, reducing duplication of the body generation logic.
Trim the error handling section by removing entries Claude can infer (e.g., 'Git not available — inform user, exit' and 'No changes to ship — inform user, exit' are already covered in Step 1).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines with extensive detail on lint gate sub-options, sketch cleanup paradigm-conditional logic, feature tracker integration, and exhaustive error handling. Much of this could be condensed or moved to reference files. Claude doesn't need this level of hand-holding for git operations, option menu formatting, or conditional branching logic. | 1 / 3 |
Actionability | The skill provides specific, executable git commands throughout (e.g., `git branch --show-current`, `git push -u origin <branch-name>`, `gh pr create --title "..." --body "..."`), concrete CLI invocations for both GitHub and Bitbucket platforms, and clear decision trees with exact user-facing prompts. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 6 numbered steps with explicit validation checkpoints: checking git state before proceeding, lint gate with 3-option resolution, sensitive file warnings, push rejection handling with rebase suggestion, and user confirmation at multiple points. Feedback loops are present for error recovery (lint fix → re-run, push rejected → pull rebase). | 3 / 3 |
Progressive Disclosure | The skill references external files like `feature-tracker-update.md` and `platform-labels.md` appropriately, and Step 6 correctly defers to a reference file. However, the main SKILL.md itself is monolithic — the lint gate logic (sub-step 3), sketch cleanup (Step 5b), and Bitbucket vs GitHub PR paths could all be split into reference files rather than inlined at full detail. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
1fe948f
- 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.