pr-review-triage

Triage open pull requests for CI status, review comments, and merge readiness. Use in PR babysitter loops. Respects project review norms and required checks.

Quality

80%

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

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 triage skill with a concrete output template and explicit validation/escalation rules. The main gap is the absence of concrete data-retrieval commands that would make it fully self-executing.

Suggestions

Add a short 'Retrieving state' snippet with the actual commands (e.g. `gh pr view`, `gh pr checks`, `gh pr review`) so the skill is fully executable without relying on inference.

Make the per-PR sequence explicit as a short numbered list (gather → classify → validate ready-to-merge → decide action) to surface the validation checkpoints already embedded in the rules.

Optionally fold the escalation thresholds (>4 days idle, high-risk labels) into the action-decision step so the validation loop is visually explicit.

Dimension	Reasoning	Score
Conciseness	Lean and efficient ~40-line body with no padding and no explanation of concepts Claude already knows; every line is an output field or a decision rule. Not below 5 because there is no over-explanation to trim.	5 / 5
Actionability	Provides a copy-paste output template with enumerated allowed values and concrete decision rules. Not a 5 because the data-gathering mechanics (e.g. gh pr view/checks commands) are implied rather than given; not a 3 because the guidance is concrete and specific, not pseudocode.	4 / 5
Workflow Clarity	The template fields imply a clear per-PR sequence (checks → required-check policy → reviews → mergeability → blocking comments → ready-to-merge → action) and the 'Ready to merge' rule is an explicit validation checklist with escalation feedback loops. Not a 5 because steps are not framed as an explicit numbered sequence with explicit checkpoints; not a 3 because validation is genuinely present, so the batch-operation cap does not apply.	4 / 5
Progressive Disclosure	Under 50 lines, self-contained, no bundle files in references/scripts/assets, and well-organized into 'Per-PR Output' and 'Rules' sections. Per the simple-skill scoring note, this earns a 5 with just well-organized sections and no external references needed.	5 / 5
	Total	18 / 20 Passed

Description

75%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 concise, specific description that answers both what and when with a clear niche. It would reach the top band with broader natural trigger phrasing and more comprehensive capability enumeration.

Suggestions

Broaden the 'when' clause with concrete user-facing triggers, e.g. 'Use when the user asks about PR status, check failures, or merge readiness' alongside the babysitter-loop context.

Add common synonyms to the keyword set such as 'mergeable', 'checks passing', or 'code review' to improve trigger term coverage.

Consider naming the merge-readiness sub-capabilities (approvals, conflicts, blocking comments) to round out specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ('CI status, review comments, and merge readiness'), with only minor gaps in coverage. Not a 3 because three distinct triage areas exceed '1-2 concrete actions'; not a 5 because it is essentially one action verb (triage) applied to targets rather than a comprehensive list of distinct operations.	4 / 5
Completeness	Clearly answers 'what' (triage PRs for CI/reviews/merge readiness) and provides an explicit 'when' ('Use in PR babysitter loops'). Not a 5 because the 'when' is a single narrow context rather than a set of concrete trigger phrases users would say; not a 3 because both what and when are explicitly present.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('pull requests', 'PR', 'CI status', 'review comments', 'merge readiness', 'required checks'). Not a 5 because synonyms like 'mergeable', 'checks passing', or 'code review' are absent; not a 3 because the terms present are the ones users would naturally say.	4 / 5
Distinctiveness Conflict Risk	Clear PR-triage niche with the babysitter-loop framing making it mostly distinct from a generic code-review skill. Not a 5 because some overlap risk with broader PR-review skills remains; not a 3 because the trigger context is specific enough to avoid broad overlap.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: cobusgreyling/loop-engineering
Path: starters/pr-babysitter/.claude/skills/pr-review-triage/SKILL.md
Commit: 804a4e9

Reviewed: about 13 hours 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.