Agent skill · Code Review & Quality

learnable-pattern-search

Analyze review comments from brave-core PRs to discover learnable patterns for improving bot documentation and best practices. Triggers on: learnable-pattern-search, learn from prs, analyze reviews, find patterns in prs.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill learnable-pattern-search --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/analysis/learnable-pattern-search/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Learnable Pattern Search Analyze review comments from brave-core PRs to discover learnable patterns. Extracts coding conventions, best practices, common review feedback themes, and architectural insights that can improve bot documentation. Supports two modes: - **PR list mode:** Provide specific PR numbers to analyze - **Username mode:** Provide a GitHub username to find and analyze all PRs they reviewed --- ## The Job ### Mode 1: PR Numbers When the user invokes `/learnable-pattern-search <pr-numbers>`: 1. **Parse the PR numbers** from the arguments (space-separated or comma-separated list) 2. **For each PR**, fetch review data and analyze it 3. **Identify learnable patterns** across the reviews 4. **Update documentation** with discovered patterns 5. **Generate a report** of findings ### Mode 2: Username When the user invokes `/learnable-pattern-search --username <github-user>`: 1. **Fetch all PRs reviewed by the user** in brave/brave-core (see "Fetching PRs by Reviewer" below) 2. **For each PR**, fetch review data and analyze it (focus on comments by the specified user) 3. **Identify learnable patterns** across the reviews 4. **Update documentation** with discovered patterns 5.

What's inside
Steps it walks through
  1. The Job
  2. Mode 1: PR Numbers
  3. Mode 2: Username
  4. Fetching PRs by Reviewer
  5. Per-PR Analysis Process
  6. Step 1: Fetch PR Context
  7. Step 2: Fetch Review Comments (Filtered for Security)
  8. Step 3: Analyze Review Comments
  9. Step 4: Categorize Patterns
  10. Pattern Quality Criteria
  11. Output
  12. Report File
  13. Documentation Updates
  14. Rate Limiting
Ships with 1 file
  • metadata.json
Commands it runs
Fetch all merged PRs reviewed by the user (paginated, fetch all pages)
gh search prs --repo brave/brave-core --reviewed-by <username> --state merged --sort updated --order desc --limit 1000 --json number,title,updatedAt
Page through all results (100 per page)
Continue incrementing &page=2, &page=3, etc. until no more results
Get PR title, description, and state
gh pr view <pr-number> --repo brave/brave-core --json title,body,state,mergedAt,labels,files
Get reviews
gh api repos/brave/brave-core/pulls/<pr-number>/reviews --paginate --jq '.[] | {user: .user.login, state: .state, body: .body}'
Get inline review comments
gh api repos/brave/brave-core/pulls/<pr-number>/comments --paginate --jq '.[] | {user: .user.login, path: .path, body: .body}'
More from claude-skill-registry
All skills →
About this skill
What does the learnable-pattern-search skill do?

Analyze review comments from brave-core PRs to discover learnable patterns for improving bot documentation and best practices. Triggers on: learnable-pattern-search, learn from prs, analyze reviews, find patterns in prs.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill learnable-pattern-search --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.

Keep going