ship

Commit and push all local current-branch work, open a ready PR, babysit it, merge when clean, then create a fresh branch

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

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

The body is a strong, actionable, well-sequenced workflow with explicit validation gates and feedback loops, delegating monitoring detail to sibling skills rather than duplicating it. Its main weakness is redundancy: the shipping invariant and production-verification guidance are restated across the invariant section, step 9, and the Important section.

Suggestions

Consolidate the 'commit all non-gitignored local changes including other agents' work' rule so it is stated once authoritatively (e.g., in the invariant) and referenced rather than repeated in steps 2, 4, and Important.

Merge the production deploy/publish verification guidance in the invariant section with step 9 to remove the near-duplicate treatment of the same retrigger-vs-fix-and-ship logic.

Trim the Important bullets that restate babysit/new-branch delegation already covered in steps 7 and 10 to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational guidance with no explaining of concepts Claude already knows, but the 'Non-Negotiable Shipping Invariant', step 9, and the 'Important' section each restate the 'commit all non-gitignored local changes including other agents' work' and production-verification points, so it could be tightened rather than earning the lean-every-token-earns-its-place anchor at 3.	2 / 3
Actionability	Provides fully executable, specific commands — `git status --short`, `git diff --stat`, `git push -u origin <branch>`, `gh pr merge <number> --squash --admin`, `/babysit-pr <number>`, `/new-branch`, `pnpm run prep` — copy-paste ready, matching the executable anchor rather than the pseudocode/abstract anchors at 1–2.	3 / 3
Workflow Clarity	An explicit 11-step sequence with validation checkpoints (merge gates holding for 10 consecutive minutes, clean tree, green CI, addressed comments) and clear feedback loops (retrigger transient failures vs fix-and-ship code failures), matching the clear-sequence-with-validation anchor rather than the implicit-checkpoint anchors at 1–2.	3 / 3
Progressive Disclosure	No bundle files exist; the skill is self-contained and well-sectioned (Steps, Important) and delegates detail to sibling skills (/babysit-pr, /new-branch) as source-of-truth rather than nesting references, so per the simple-skills scoring note a well-organized single file scores 3 rather than the monolithic or poorly-signaled anchors at 1–2.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, action-driven, and uses natural trigger terms with a clear distinct niche, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Add a 'Use when...' clause stating the trigger (e.g., 'Use when the user asks to ship, commit and push, or open and merge a PR for the current branch') to lift completeness to 3.

Clarify the colloquial 'babysit it' with a brief gloss (e.g., 'monitor CI/review until mergeable') so the trigger reads naturally to users unfamiliar with the /babysit-pr skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Commit and push", "open a ready PR", "babysit it", "merge when clean", "create a fresh branch" — matching the 'lists multiple specific concrete actions' anchor, not the partial domain-only anchor at 2.	3 / 3
Completeness	Clearly answers what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 instead of reaching the explicit-both-what-and-when anchor at 3.	2 / 3
Trigger Term Quality	Uses natural terms a user would actually say — "commit and push", "open a PR", "merge", "branch" — giving good coverage rather than the thin single-keyword anchor at 2.	3 / 3
Distinctiveness Conflict Risk	Describes a distinct end-to-end ship-workflow niche unlikely to fire for unrelated skills, matching the clear-niche anchor rather than the generic or still-overlapping anchors at 1–2.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/ship/SKILL.md
Commit: e9a2f0e

Reviewed: 4 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.