gh-pr-inline

Post inline comments on GitHub PRs and respond to review feedback via gh api

1.29x

Quality

75%

Does it follow best practices?

Impact

96%

1.29x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./dot_config/opencode/skill/gh-pr-inline/SKILL.md

Evaluation results

92%

37%

Code Review: Authentication Service PR

Posting inline PR review comments via gh api

Criteria

Without context

With context

Uses gh api not gh pr review

100%

Uses --input - heredoc

100%

Correct reviews endpoint

100%

REQUEST_CHANGES event

100%

No top-level body

100%

Correct comment structure

50%

100%

All three files targeted

100%

Verification documented

100%

Correct repo in endpoint

100%

Shows comments before posting

Delete mechanism noted

50%

100%

22%

Handle Review Feedback on Feature Branch PR

Responding to PR review thread feedback

Criteria

Without context

With context

GraphQL listing query

100%

GraphQL query fields

100%

resolveReviewThread mutation

100%

PRRT_ thread ID format

25%

100%

REST reply endpoint

100%

Numeric comment ID for reply

50%

100%

No reply for resolved items

100%

Resolve vs reply decision

100%

Correct PR number used

100%

Reply body included

100%

97%

Review a Data Pipeline Refactor PR

Multi-line comments and line number correctness

Criteria

Without context

With context

start_line for block comment

100%

Single-line no start_line

100%

HEAD commit line reference

64%

100%

Diff off-by-one warning

40%

70%

DELETE for misplaced comments

100%

Uses gh api not gh pr review

100%

Uses --input - heredoc

100%

Correct file paths

100%

Correct line numbers used

100%

Repository: athal7/dotfiles
Commit: 07d79b6

Evaluated: 26 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Code Review: Authentication Service PR Handle Review Feedback on Feature Branch PR Review a Data Pipeline Refactor PR

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.