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

78%

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

85%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.

An exceptionally actionable, well-sequenced shipping runbook with strong validation and error-recovery loops throughout — every command is executable and every gate is explicit. The weaknesses are density (justification prose that could be trimmed) and the absence of any reference files, leaving policy material inline that would benefit from progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious, repo-specific knowledge ("the stash list is shared across every worktree of the repo", "a bare `wait` swallows child exit codes") and explains nothing Claude already knows, but the volume of inline justification prose in steps 2 and 6 (e.g. the umbrella-generator rationale) could be trimmed. Not 5 because several passages of rationale could be tightened without losing clarity; not 3 because nothing is generic padding.	4 / 5
Actionability	Fully executable throughout: copy-paste bash blocks with explicit exit-code gating (the generator loop with /tmp/ship-gen-results, the lint/audit gates), exact grep scrub patterns, the exact `gh pr create --base staging` command, and a complete PR body template. Guidance covers common cases with concrete commands rather than pseudocode.	5 / 5
Workflow Clarity	Nine clearly sequenced steps with explicit validation checkpoints and feedback loops: the sync check re-verifies the commit list after rebase, "A failing test aborts ship", generator/audit failures abort with "do not ship", and the final content check instructs redoing step 2's fix and force-pushing on mismatch. Destructive history-rewrite operations include verify-then-recover loops, so the destructive-operation cap does not apply.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are all absent) and all ~184 lines are inline; content such as the "What to Omit" scrubbing policy (~40 lines of leak-prevention rules and grep patterns) and the PR/commit templates would fit naturally in reference files. Section headers give decent in-file structure, matching anchor 3 rather than 2, but nothing is offloaded to one-level-deep references, so it does not reach 4.	3 / 5
	Total	17 / 20 Passed

Description

71%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.

A specific, action-dense description that clearly states what the command does, including its conditional safety gates. Its main weakness is the absence of explicit "when to use" trigger guidance, which caps completeness and slightly narrows its discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to ship, commit and push, or open a PR to staging" — this would raise completeness from 3 to 4-5.

Include natural synonyms such as "pull request" or "publish" alongside "PR" to broaden trigger-term coverage.

Optionally note the gate conditions as triggers ("when migrations changed") so the migration-safety behavior also serves as a trigger cue.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Commit, push, and open a PR to staging", "runs the cleanup pass", "the db-migrate safety review" — with a conditional gate, giving comprehensive coverage of the skill's actions. It exceeds anchor 4 because the action list has no coverage gaps, each being a specific executable capability rather than a domain label.	5 / 5
Completeness	The "what" is clearly and concretely stated, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines. It is not 2 because the "what" is specific and multi-action rather than vague.	3 / 5
Trigger Term Quality	Natural terms users would say — "commit", "push", "PR", "staging" — are present and appropriate for a ship/PR workflow. Not anchor 5 because common synonyms like "pull request", "publish", or "submit a PR" are missing, though the coverage that exists is solid.	4 / 5
Distinctiveness Conflict Risk	The niche (staging PR pipeline with cleanup and migration gates) is distinct from general git helpers, so conflict risk is minor. Not anchor 5 because a generic request like "commit this" or "open a PR" could plausibly trigger it over a narrower commit-message skill.	4 / 5
	Total	16 / 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: 2 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: 8725250

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.