slate-ar-ship

Slate v2 one-command ship/readiness mini-skill. Runs finalization preview, picks the review shape, runs pre-commit gates/autoreview, pauses for commit approval, then commits/finalizes after confirmation.

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/slate-ar-ship/SKILL.md

Quality

Content

73%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 body is a well-sequenced procedural skill with strong validation checkpoints and feedback loops around its destructive operations, and it names concrete commands and flags throughout. Its main weakness is repetition of the same safety constraints across multiple sections, which adds tokens without adding clarity.

Suggestions

Consolidate the repeated no-mutation-without-explicit-approval and no-review-branch rules into a single authoritative section and reference it, reducing token cost.

Tighten abstract steps like "run the narrowest relevant slate-ar-gate proof" with a concrete example of which gate maps to which change type.

Consider splitting the long Review And Commit rules into a referenced file so SKILL.md reads as a leaner overview with one-level-deep detail.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational prose that assumes Claude knows git, but the no-mutation-without-approval and no-review-branch rules are repeated across Contract, Current Tree, Pre-Commit, and Review And Commit sections and could be tightened.	3 / 5
Actionability	Names concrete sub-commands and flags (slate-ar-finalize, finalize-current-tree --exclude-session-artifacts, slate-ar-gate, autoreview, finalize-autoresearch.mjs <plan>) with clear ordering, though some steps like "run the narrowest relevant gate" stay abstract, keeping it just below fully copy-paste ready.	4 / 5
Workflow Clarity	Both the 8-step default flow and 7-step pre-commit path are explicitly sequenced with validation checkpoints (proof gates, autoreview, fix P0/P1 then rerun, READY TO COMMIT pause) and feedback loops for the destructive commit/push/PR operations.	5 / 5
Progressive Disclosure	Well-organized into clear sections (Contract, Current Tree, Pre-Commit Review, Review And Commit, Handoff) with no nested or buried references and no bundle files to split out, but it is a single inline monolith with no overview-pointing-to-details pattern to earn a 5.	4 / 5
	Total	16 / 20 Passed

Description

58%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 gives a concrete, sequenced picture of what the skill does but omits any explicit "when to use it" trigger guidance and relies heavily on Slate-internal jargon. It is distinguishable within its niche yet carries minor overlap with sibling slate-ar skills.

Suggestions

Add an explicit "Use when..." clause with natural trigger phrases (e.g., ship, ready to ship, commit my AR work, is this shippable) to lift completeness above 3.

Reduce internal jargon (autoreview, AR, finalization, gates) in favor of terms a user would actually say, improving trigger-term quality.

Add a distinguishing phrase that separates this ship/readiness entry point from slate-ar and slate-ar-finalize to lower overlap risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Runs finalization preview, picks the review shape, runs pre-commit gates/autoreview, pauses for commit approval, then commits/finalizes" — but "picks the review shape" is slightly abstract, so it stops short of comprehensive (5).	4 / 5
Completeness	Clearly answers "what" with a sequenced action list, but provides no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Contains some natural terms ("ship", "readiness", "commit") but leans on Slate-internal jargon ("autoreview", "AR", "finalization", "gates") and misses common synonyms or variations a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	"Slate v2 one-command ship/readiness mini-skill" carves a clear niche, but it overlaps with closely related slate-ar / slate-ar-finalize skills, leaving minor conflict risk rather than a fully distinct trigger.	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
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: udecode/plate
Path: .agents/skills/slate-ar-ship/SKILL.md
Commit: d76efae

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.