CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-and-ship

Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A tight, well-structured skill body: lean prose, concrete commands, a clearly sequenced workflow with an explicit fix-and-retest loop, and clean section organization that needs no external files. Its only weakness is that the commit/PR steps rely on high-level direction rather than executable commands.

Suggestions

Add the specific commands for the shipping steps, e.g. `gh pr create --title ... --body ...` and a short commit message format example.

Make the PR-readiness checkpoint explicit in the workflow (e.g., step 7: run `gh pr checks` and only report done when checks pass) instead of leaving it only in Guardrails.

Optionally note how to handle push failures or hook rejections to close the remaining validation gap.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence ("Run targeted tests for changed behavior. If no focused tests exist, decide whether to add them or document the gap.") with no concept over-explained and every section earning its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

Concrete, executable commands are provided ("git diff origin/main...HEAD", "gh pr checks --json name,bucket,state,workflow,link") but steps 5-6 ("Commit selective files with a concise message", "Push branch and open or update a PR") lack the specific commands such as an example commit message or `gh pr create`, fitting 'mostly executable guidance; minor gaps'.

4 / 5

Workflow Clarity

The six-step sequence is clear and includes an explicit feedback loop ("Fix critical issues before finalizing and re-run affected tests"), but some checkpoints are implicit (e.g., no explicit verification step after opening the PR despite the `gh pr checks` guardrail), matching the 'clear sequence with most checkpoints; minor validation gaps' anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines, has no external references (no references/, scripts/, or assets/ bundle files exist), and is organized into clean, well-signaled sections (Trigger, Workflow, Suggested Checks, Guardrails, Output), meeting the simple-skill exception for a top score on organization alone.

5 / 5

Total

18

/

20

Passed

Description

66%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 strong, lean description with multiple specific actions and natural trigger keywords, held back only by the complete absence of a 'Use when...' clause, which caps completeness at 3 and weakens its trigger guidance.

Suggestions

Add an explicit trigger clause such as 'Use when the user asks to review changes before merging, ship a branch, or open/update a PR.'

Include one or two natural synonyms (e.g., 'pull request', 'ship', 'push') to broaden trigger coverage.

Optionally mention fixing found issues in the capability list to round out coverage of the workflow the body actually performs.

DimensionReasoningScore

Specificity

Lists several specific concrete actions ("Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR") with only minor coverage gaps, matching the 'several specific actions' anchor rather than the 1-2 actions of the level below.

4 / 5

Completeness

The 'what' is clear and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the judging guidelines cap at 3; the description exceeds the vague-'what' anchor at 2 but cannot reach 4 without any 'when' content.

3 / 5

Trigger Term Quality

Natural terms users would say are present ("review", "branch", "bugs", "test coverage", "commit", "PR"), but a few natural synonyms are missing ("pull request" spelled out, "ship", "push"), matching the 'good keyword coverage, a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

The branch-review/commit/PR framing carves a mostly distinct niche, though "review...for bugs" risks minor overlap with generic code-review skills, fitting the 'mostly distinct; minor overlap risk' anchor.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

cursor/plugins

Path

cursor-team-kit/skills/review-and-ship/SKILL.md

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.