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

73%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.

The skill is a strongly actionable, well-sequenced interactive workflow with explicit validation checkpoints between phases. Its main weakness is conciseness — repeated option blocks and a few restating sentences inflate the length without adding guidance value.

Suggestions

Define the A/B/C/D option pattern once and shorten the repeated blocks, or omit the literal text and describe the option convention in one line.

Trim restating sentences (e.g. 'This is critical context for the PR Goal — the linked issues often explain why this PR exists better than the PR description itself.') that re-emphasize what the preceding instruction already says.

Consider moving the comment-posting REST API bash into a scripts/ helper to reduce inline length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but repeated A/B/C/D option blocks and restating sentences ('This is critical context for the PR Goal — ...') add padding that could be tightened; not a 4.	3 / 5
Actionability	Nearly every step ships a concrete, copy-paste-ready command (gh pr view, gh pr diff, gh pr checks, git log/blame, REST API posting bash), but a few phases (Opinion Exchange, Understanding Check) lean on abstract judgment guidance, leaving minor gaps versus a 5.	4 / 5
Workflow Clarity	Seven phases are explicitly sequenced with hard validation checkpoints ('Only proceed to the quality gate after the user confirms understanding', 'Do not move to Phase 4 until...'), a pass/fail Quality Gate feedback loop, and an Understanding Check — matching the explicit-validation anchor.	5 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-sectioned document with clear phase headers. Structure is good, though the ~260-line length and inlined posting/comment bash blocks could arguably be split into scripts, keeping it just below a 5.	4 / 5
	Total	16 / 20 Passed

Description

53%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.

The description conveys a clear purpose and a distinct niche, but it lacks an explicit 'when to use' trigger clause and only names high-level actions. Adding a 'Use when...' clause with concrete actions and trigger synonyms would lift all three 3-scored dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when reviewing a pull request — especially large, unfamiliar, or cross-team PRs — before approving or commenting.'

Replace abstract phrasing with concrete actions: 'examines git history, CI status, linked issues, and test quality before forming opinions.'

Include natural synonyms users say ('pull request', 'code review', 'review this PR') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('PR review') and a couple of actions ('understand the history and context', 'forming opinions'), but these are high-level rather than the several concrete actions (examine git history, run CI checks, read linked issues) that would warrant a 4.	3 / 5
Completeness	The 'what' is clear ('Guided interactive PR review — understand the history and context before forming opinions') but there is no 'Use when...' clause or equivalent trigger guidance, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	'PR review' is a natural term a user would say, but common synonyms like 'pull request', 'code review', or 'review this PR' are missing, placing it at 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	'PR review' is a clear, distinct niche with minimal conflict risk; only minor overlap with a generic code-review skill keeps it just below a 5.	4 / 5
	Total	13 / 20 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: d6ce34a

Reviewed: about 17 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.