understand-pr

Guided interactive PR review — understand the history and context before forming opinions

Quality

63%

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 ./.mastracode/skills/understand-pr/SKILL.md

Quality

Content

77%

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 highly actionable, well-sequenced interactive workflow with concrete commands and explicit validation checkpoints throughout. Its main weaknesses are some tightening opportunities in prose and the absence of any progressive disclosure via reference files despite the length.

Suggestions

Trim repeated guidance like 'Tailor the options to what's actually relevant' and the rationale sentences in the People section to improve token efficiency.

Consider moving the comment-posting REST API snippets and the people/linkage methodology into a reference file (e.g. references/posting.md) to improve progressive disclosure for a 269-line skill.

Consolidate the near-identical A/B/C/D option blocks where the pattern is already established to reduce repetition.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and actionable and avoids explaining concepts Claude already knows, but repeated exhortations ('tailor the options', 'do not use generic options') and rationale prose ('This tells you how much context each person has...') could be tightened.	2 / 3
Actionability	Nearly every instruction ships a concrete, executable command — 'gh pr view --json ...', 'git log --oneline -20 -- <file>', and a copy-paste-ready REST API block for posting comments — matching 'Fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	A clear Setup → Phase 1–7 sequence with explicit validation gates (lettered options that pause for confirmation, 'Only proceed ... after the user confirms') and feedback loops (opinion exchange, iterate-until-happy comment drafting, patch-on-wrong-body recovery) matches anchor 3.	3 / 3
Progressive Disclosure	Sections are well organized into clear phases, but the skill is a 269-line monolithic file with no bundle/reference files; content such as the posting scripts and people-analysis methodology that could live in separate reference files is inline, matching 'content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys the skill's purpose and distinctive 'understand-first' angle concisely, but it lacks an explicit 'Use when...' trigger clause and broader natural keyword coverage. It is solid but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing a pull request or when the user asks to understand a PR before commenting on it.'

Include natural keyword variations such as 'pull request', 'code review', and 'review a PR' so users' phrasings match the description.

Optionally surface one or two concrete phases (e.g. 'check CI and changesets, walk the diff, draft a review comment') to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('PR review') and a couple of actions ('understand the history and context before forming opinions'), but does not enumerate the concrete phases (goal, quality gate, walkthrough) — closer to 'Names domain and some actions, but not comprehensive' than to a multi-action list.	2 / 3
Completeness	It states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 with 'when' only implied.	2 / 3
Trigger Term Quality	'PR review' and 'history and context' are natural terms, but common variations a user would say ('pull request', 'review a pull request', 'code review') are missing, matching 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The 'understand before forming opinions' framing is a fairly distinct niche, but 'PR review' is a common domain that could overlap with other review skills, matching 'Somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: mastra-ai/mastra
Path: .mastracode/skills/understand-pr/SKILL.md
Commit: 3b78ed9

Reviewed: about 23 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.