pr-review-triage

Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./starters/pr-babysitter-opencode/skills/pr-review-triage/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and well-organized for a simple monitoring skill, with a concrete output template, but it stops short of giving executable retrieval commands and leaves the loop/validation mechanics implicit.

Suggestions

Add the specific gh/MCP commands to fetch CI status, reviews, and mergeability per PR so the guidance is copy-paste ready.

Spell out the loop mechanics — how often to re-check, what triggers re-evaluation, and how 'Suggested loop action' values map to next steps.

Add an explicit validation checkpoint (e.g., confirm required-check policy is 'known' before assessing 'Ready to merge') to make the decision gate a clear validation step.

Dimension	Reasoning	Score
Conciseness	The body is lean — a short Inputs list, a compact per-PR output template, top-3 actions, and precise Rules — with no padding or explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	The per-PR template with explicit enum values (e.g., 'Checks: passing \| failing \| pending \| absent/unknown') is concrete, but the actual retrieval commands for each datum are absent (only 'gh pr list or GitHub MCP' is named), leaving key execution details missing rather than copy-paste ready.	2 / 3
Workflow Clarity	A per-PR assessment sequence and a 'Ready to merge' decision gate are present, but validation checkpoints and the loop mechanics (cadence, re-evaluation triggers, escalation flow) are implicit rather than explicit, fitting 'sequence present but checkpoints missing or implicit'.	2 / 3
Progressive Disclosure	At under 50 lines with no need for external references, the body is well-organized into clearly signaled sections (Inputs, Per-PR Output, Rules), which per the scoring notes earns a 3 for a simple, single-purpose skill.	3 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is specific and well-niched, clearly conveying what the skill does, but it omits any explicit 'Use when...' trigger guidance, which caps completeness and leaves trigger-term coverage short of full.

Suggestions

Add an explicit trigger clause, e.g., 'Use when monitoring open pull requests, triaging stale PRs, or surfacing CI/review blockers.'

Include the spelled-out term 'pull requests' alongside 'PRs' to broaden natural trigger coverage.

Name the common variations users might say ('stale PRs', 'blocked PRs', 'CI failures') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist' — matching the score-3 anchor of several specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' but never says when to use it; per the judging guidelines, a missing 'Use when...' clause or equivalent trigger guidance caps completeness at 2.	2 / 3
Trigger Term Quality	Keywords like 'open PRs', 'CI status', 'merge conflicts', and 'review comments' are natural, but common variations (e.g., 'pull requests') are missing and there is no explicit trigger phrasing, so it sits at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The PR-monitoring/triage niche ('watch open PRs', 'staleness', 'merge conflicts', 'unanswered review comments', 'prioritized watchlist') is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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-opencode/skills/pr-review-triage/SKILL.md
Commit: ffa5bf8

Reviewed: 9 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.