skills/pr-info/SKILL.md
Fetch PR details from GitHub (reviews, inline comments, conversations, diff). Use when user asks to view a PR, check PR comments, review PR feedback, or when any workflow needs to read PR data. Provides reliable repo-aware commands. Do NOT use for creating PRs (use create-pr skill instead).
npx skillsauth add nicolas-codemate/claudecodeconfig pr-infoInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Fetches comprehensive PR information from GitHub, handling repo detection and all comment sources automatically.
<context> Direct `gh` commands often fail because: - Claude hardcodes wrong `owner/repo` in API paths (404 errors) - `--jq` returns exit code 1 on empty results - Inline review comments require a separate API endpoint from PR reviews - Three distinct comment sources must be combined for a complete pictureThis skill solves all of these by using a tested wrapper script. </context>
<instructions>Run the helper script from the project directory:
# Basic: overview + reviews + all comments
~/.claude/scripts/gh-pr-info.sh <PR_NUMBER>
# With diff included
~/.claude/scripts/gh-pr-info.sh <PR_NUMBER> --diff
# From a different repo path
~/.claude/scripts/gh-pr-info.sh <PR_NUMBER> --repo-path /path/to/repo
The script auto-detects owner/repo from the current git context. No need to
hardcode repository paths.
If you need to run individual commands, always detect the repo first:
# Step 1: detect repo (MANDATORY before any gh api call)
REPO=$(gh repo view --json nameWithOwner -q .nameWithOwner)
# Step 2: use $REPO in API paths
gh api "repos/$REPO/pulls/<N>/reviews" --paginate
gh api "repos/$REPO/pulls/<N>/comments" --paginate # inline comments
gh api "repos/$REPO/issues/<N>/comments" --paginate # conversation comments
| Endpoint | What it contains |
|----------|-----------------|
| pulls/<N>/reviews | Review verdicts (APPROVED, CHANGES_REQUESTED, COMMENTED) with optional body |
| pulls/<N>/comments | Inline comments on specific code lines (path + line number) |
| issues/<N>/comments | General conversation comments on the PR discussion tab |
development
Method to diagnose and raise the Lighthouse performance score of a public page (landing, marketing, home). Use when asked to improve Lighthouse/PageSpeed scores, when auditing the first uncached paint of a public page, or when a landing embedded in a SPA must reach a top score. Do NOT use for in-app screen performance (data loading, rendering). For a brand-new landing, the first recommendation is static HTML with no framework runtime — most of this skill exists for when that is not an option.
tools
Audits a project's Claude Code setup against real usage — mines the project's conversations (worktrees included), confronts the project's skills/agents/CLAUDE.md with best practices, and proposes adjustments or new skills/agents/rules. Use when the user asks to audit the project config, analyze project conversations, or find automation opportunities for the current project. Do NOT use for the global ~/.claude configuration (use /audit-config instead).
development
Coaching workflow orchestrator. Guides the developer through implementation without writing code.
development
Disciplined methodology for code architecture refactoring. Use when the user asks to refactor architecture, decouple code, restructure a family of classes, redesign an interface, or rename/reorganize a set of related components. Forces a big-picture analysis before any code is written. Do NOT use for simple bug fixes, feature additions, or single-file refactoring.