arn-shipping
This skill should be used when the user says "shipping", "arness shipping", "ship it", "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", "done", "arn-shipping", or wants to commit, push, and optionally create a pull request. Handles branching, staging, committing, pushing, and PR creation as a single guided flow. Chains from arn-implementing at completion.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
92%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 description that excels at listing explicit trigger terms and concrete actions. The 'what' and 'when' are both clearly addressed. The main weakness is that some trigger terms ('done', 'finalize', 'finish up') are overly generic and could cause false matches with unrelated skills, creating conflict risk.
Suggestions
Consider removing or qualifying overly generic trigger terms like 'done', 'finalize', and 'finish up' to reduce conflict risk with other skills — e.g., specify 'done with code changes' instead of just 'done'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: branching, staging, committing, pushing, and PR creation. Also mentions it operates as 'a single guided flow' and chains from another skill. | 3 / 3 |
Completeness | Clearly answers both 'what' (handles branching, staging, committing, pushing, and PR creation as a single guided flow) and 'when' (explicit trigger terms and use cases listed at the beginning). The 'when' guidance is very explicit. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say, including variations like 'ship it', 'ship', 'create PR', 'open pull request', 'push and PR', 'commit and push', 'wrap up', 'finalize', 'finish up', 'done', and 'ready to ship'. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | While the shipping/PR-specific terms are distinctive, some trigger terms like 'done', 'finalize', 'finish up', and 'wrap up' are very generic and could easily conflict with other skills that handle task completion in different contexts. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured thin orchestration skill with clear workflow sequencing and appropriate delegation to sub-skills. Its main weakness is some unnecessary meta-commentary about its own design philosophy ('thin orchestration wrapper', 'MUST NOT duplicate') that consumes tokens without adding actionable value. The error handling section partially restates what the invoked skill already handles, which is slightly redundant.
Suggestions
Remove design-philosophy statements like 'This is a thin orchestration wrapper' and 'It MUST NOT duplicate arn-code-ship logic' — these are author notes, not instructions Claude needs to follow the workflow.
Trim the error handling section to only cover errors this skill must handle directly (config missing, ship fails), removing the 'Nothing to ship' case since you already note arn-code-ship handles it internally.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary meta-commentary (e.g., 'This is a first-citizen entry point', 'This skill is a thin orchestration wrapper', 'It MUST NOT duplicate arn-code-ship logic'). These are design notes for the skill author, not actionable instructions for Claude. The error handling section also restates things the invoked skill already handles. | 2 / 3 |
Actionability | The skill provides a clear sequence of actions (read config, invoke ship skill, present handoff message), but the actual work is entirely delegated to other skills. The concrete guidance is limited to invoking another skill and displaying progress text. There's no executable code beyond ASCII art progress indicators. | 2 / 3 |
Workflow Clarity | For a thin orchestration wrapper, the workflow is clearly sequenced: Step 0 (config), Step 1 (invoke ship), Step 2 (completion handoff). Error handling covers the relevant failure modes with clear actions (retry or abort). The simplicity of the task matches the simplicity of the workflow. | 3 / 3 |
Progressive Disclosure | The skill appropriately delegates to referenced skills (arn-code-ship, arn-code-ensure-config) rather than inlining their logic. References are one level deep and clearly signaled with specific file paths and skill invocation syntax. The structure is well-organized for a wrapper skill. | 3 / 3 |
Total | 10 / 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
b9084b6
- 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.