paw-review-baseline
Analyzes the codebase at the PR's base commit to establish baseline understanding for review comparison.
npx skills add majiayu000/claude-skill-registry --skill paw-review-baseline --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Baseline Research Activity Skill Analyze the codebase **at the base commit** (before PR changes) to document how the system worked, what patterns existed, and what context informs understanding of the changes. > **Reference**: Follow Core Review Principles from `paw-review-workflow` skill. ## CRITICAL: Baseline Only **Your only job is to document the pre-change codebase as it existed.** - DO NOT analyze the PR changes or compare before/after - DO NOT suggest improvements or identify issues - DO NOT critique the implementation - ONLY describe what existed before: behavior, patterns, conventions, integration points ## Responsibilities - Checkout base commit safely (with state restoration) - Research how affected modules functioned before changes - Document integration points and dependencies - Identify patterns and conventions in affected areas - Create CodeResearch.md with baseline understanding ## Non-Responsibilities - PR change analysis or before/after comparison (understanding skill) - Quality evaluation or recommendations (evaluation skills) - Workflow orchestration (handled by workflow skill) ## Prerequisites - ReviewContext.md must exist with base commit SHA - ResearchQuest
- CRITICAL: Baseline Only
- Responsibilities
- Non-Responsibilities
- Prerequisites
- Multi-Repository Mode
- Detection
- Per-Repository Processing
- Cross-Repository Pattern Identification
- Error Handling
- Execution Steps
- Step 1: Sync Remote State
- Step 2: Checkout Base Commit
- Step 3: Read Research Questions
- Step 4: Analyze Pre-Change Codebase
What does the paw-review-baseline skill do?
Analyzes the codebase at the PR's base commit to establish baseline understanding for review comparison.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill paw-review-baseline --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.