babysit-pr

Use whenever an open PR needs shepherding to a merge — watching CI, weighing the agentic reviews, resolving merge conflicts, and merging once everything is green. Assumes the PR already exists (code is written, pushed, and `gh pr create` has run); this skill starts from there. Used by the `build-feature` skill's last step, and by any agent (e.g. a dedicated babysitter) whose job is watching a PR through to landing.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

96%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, command-driven workflow with explicit validation checkpoints and error-recovery branches, assuming Claude's competence throughout. Only minor: everything is inlined with no progressive reference structure, though none is strictly needed at this size.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — no padding, no re-explanation of git/GitHub concepts Claude already knows; every sentence earns its place, matching the score-5 anchor.	5 / 5
Actionability	Fully executable: copy-paste-ready `gh pr checks --watch`, `gh pr view --json mergeStateStatus`, rebase, and `gh pr merge --squash --delete-branch` commands with concrete failure-mode branches.	5 / 5
Workflow Clarity	Clear three-step sequence (watch → close the loop → merge) with explicit validation (re-check `mergeStateStatus`, re-run `npm run check`) and feedback loops (DIRTY → rebase → re-run → force-push → re-check), matching the score-5 anchor.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with no nested references and no separate bundle files to navigate, but the body inlines all detail rather than pointing one level deep to references, sitting just below the score-5 'overview pointing to detailed materials' anchor.	4 / 5
	Total	19 / 20 Passed

Description

92%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, third-person description that explicitly pairs a concrete 'what' with an explicit 'Use whenever...' 'when', and scopes itself to an already-open PR. Slightly below top on trigger-term breadth but otherwise exemplary.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete shepherding actions — watching CI, weighing agentic reviews, resolving merge conflicts, merging — matching the comprehensive-coverage anchor rather than the score-4 'minor gaps' anchor.	5 / 5
Completeness	Explicitly answers both what ('shepherding to a merge — watching CI... resolving merge conflicts... merging') and when ('Use whenever an open PR needs shepherding') with concrete triggers, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Natural phrases like 'open PR', 'watching CI', 'merge conflicts', and 'merging' appear, but it lacks the most generic shorthand a user might say ('shepherd/land a PR') as a standalone keyword, sitting just below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — post-creation PR landing via gh — with distinct triggers and an explicit precondition (PR already pushed), making conflict with other skills minimal.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: drufball/skylark
Path: plugins/skylark-builder/skills/babysit-pr/SKILL.md
Commit: b5a3eaf

Reviewed: 6 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.