ship

Commit, push, and open a PR to staging in one shot — runs the cleanup pass and, when migrations changed, the db-migrate safety review first

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/ship/SKILL.md

Quality

Content

77%Weight 40%Scale 1-5

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

The content is highly actionable and the workflow is exceptionally clear with strong validation feedback loops, but it is dense/verbose in places and inlines substantial reference-style detail that would benefit from being split into bundled files.

Suggestions

Move the long Phase A/B generator commentary and the migration-specific warnings into reference files (e.g. references/pre-ship-checks.md) and link to them, keeping SKILL.md a lean overview.

Tighten the explanatory prose around the sync-check and generator sections to reduce token load while keeping the executable commands.

Add a brief 'See also' navigation block pointing to any split-out reference files once created, so the one-level-deep references are clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but several sections are quite dense and explanatory (the Phase A/B commentary, the migration and generator warnings), which could be tightened; it is on the verbose side for a skill body.	3 / 5
Actionability	It provides fully executable, copy-paste-ready bash snippets (the parallel generate loop, lint/audit block, PR verification) plus concrete commands with explicit exit-code gating that cover the common cases end to end.	5 / 5
Workflow Clarity	The nine-step ship flow is clearly sequenced with explicit validation checkpoints (sync-check re-verification, post-rebase log re-check, generator/audit failure gating, final PR content comparison) and detailed feedback loops for the destructive history-rewrite case.	5 / 5
Progressive Disclosure	There is good section structure, but no bundle files exist and the entire procedure — including long inline bash blocks and detailed generator-specific warnings that clearly belong in reference material — is inlined in SKILL.md rather than split into one-level-deep references.	3 / 5
	Total	16 / 20 Passed

Description

56%Weight 40%Scale 1-5

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 clearly states what the skill does with concrete actions and preconditions, but lacks an explicit 'Use when...' trigger clause, which caps completeness, and frames triggers in the skill's voice rather than the user's natural phrasing.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to ship code to staging — committing, pushing, and opening a PR in one step.'

Surface the /ship invocation trigger and natural user phrases ('ship it', 'open a PR to staging') so trigger-term quality matches how users actually ask.

Keep the concrete precondition detail but trim slightly so the description reads as a trigger hook rather than a full procedure summary.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Commit, push, and open a PR') plus specific preconditions ('runs the cleanup pass and, when migrations changed, the db-migrate safety review first'), with minor gaps in describing the full scope of what the skill does.	4 / 5
Completeness	It gives a clear 'what' (commit, push, open PR to staging) but there is no explicit 'Use when...' or equivalent trigger guidance stating when Claude should invoke the skill; the 'when' is only weakly implied by the command name.	3 / 5
Trigger Term Quality	It contains relevant terms ('commit', 'push', 'PR', 'staging', 'migrations') but is framed as the skill's behavior rather than as natural phrases a user would say when they need it, and lacks common synonyms or the /ship invocation trigger.	3 / 5
Distinctiveness Conflict Risk	It targets a fairly specific niche ('one shot' ship-to-staging flow with cleanup and migration gating) that is mostly distinct from generic commit/PR skills, with only minor overlap risk.	4 / 5
	Total	14 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: simstudioai/sim
Path: .agents/skills/ship/SKILL.md
Commit: 7945b29

Reviewed: 3 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.