Curated skills, patterns, and playbooks for Claude Code, reviewed by admins.
You are a security reviewer specializing in TypeScript and Node.js.
You are a performance reviewer specializing in TypeScript and Node.js.
You are a holistic reviewer.
You are a conventions reviewer.
You are a code quality reviewer.
Authors: [Author Names and Affiliations] Date: [Date] Review Type: [Narrative Systematic Scoping Meta-Analysis Umbrella Review] Review Protocol: [PROSPERO ID if registered, or sta…
模式：PR 审查，代码分析 重点：质量、安全性、可维护性
Mod: PR incelemesi, kod analizi Odak: Kalite, güvenlik, sürdürülebilirlik
モード: PRレビュー、コード分析 フォーカス: 品質、セキュリティ、保守性
Mode: PR review, code analysis Focus: Quality, security, maintainability
Perform an automated code review with categorized findings and severity ratings.
Perform a thorough code review of the current uncommitted changes or a specified file directory.
No new additions to the ConfigYaml schema should be made for features that are experimental.
You are reviewing code for correctness, security, and maintainability.
Isolated reviewers see the diff and the design docs but have zero visibility into which tasks are done versus pending.
Review the README and category files for quality and organization.
Copy this checklist and check off items as you complete them:
Read SKILL.md §Mandatory ordering — methodology before evidence before executing this file.
Run a comprehensive multi-perspective review of a pull request.
Comprehensive pull request review using all specialized agents.
Perform a comprehensive code review using subagents for key areas:
Perform a thorough code review of a pull request with actionable feedback.
Run a comprehensive pull request review using multiple specialized agents, each focusing on a different aspect of code quality.
$ARGUMENTS: The PR number or URL to review
$ARGUMENTS: The PR number to review
Use this exact format when presenting synthesized review findings in Interactive mode.
Use this exact format when presenting synthesized review findings.
Use this context when conducting code reviews or quality assessments.
Repeat the following cycle on the current branch's changes against main (max 3 iterations):
Review uncommitted local changes using all specialized agents with code improvement suggestions.
$ARGUMENTS: The issue number to review
Review the frontend site to ensure new repos are properly displayed and categories are well-organized.
Date: 2026-04-07 Skill: kk:review-design (standard mode) Model: claude-opus-4-6 (1M context) Methodology: skill-creator eval framework — 3 test cases, each run with-skill and with…
Use this checklist to self-review a workflow skill before submission.
| Category | Key Questions | |----------|---------------| | Design | Does it fit existing patterns?
Use only relevant sections for the current pull request.
Revenue estimation is critical for deciding whether an opportunity is worth pursuing.
Retrosynthesis is the process of planning synthetic routes from target molecules back to commercially available starting materials.
Epic completion, reporting, and system description update after all tickets are executed.
Verify all tickets are complete, generate a comprehensive completion report, close the epic in Jira, and perform a holistic system description review.
| Technique | Impact | Complexity | When to Use | |-----------|--------|------------|-------------| | Hybrid Search | High | Medium | Always for production | | Reranking | High |…
Working with GitHub repositories, pull requests, issues, releases, or raw file URLs.
Codex is powered by OpenAI models with their own knowledge cutoffs and limitations.
VitePress documentation site with 14 languages.
Cross-browser extension (Chrome Firefox Edge) using WXT framework with Manifest V3.
You are an expert code analyst specializing in repository exploration using Repomix CLI.
You write commits that carry development reasoning in the body — the intent, decisions, constraints, and learnings that the diff alone cannot show.
@praha byethrow is a lightweight, tree-shakable Result type library for handling fallible operations in JavaScript and TypeScript.
A persistent memory space for storing knowledge that survives across conversations.
Pack entire codebases into a single, AI-friendly file for analysis.
Use this skill to operate Ralph loops from the outside.
Use this skill to operate the full Ralph hat lifecycle for user-authored hat collections.
This skill tests directory-based skill discovery ( SKILL.md pattern).
This skill validates Terminal User Interface (TUI) applications by capturing their output and using LLM-as-judge for semantic validation.
Debug TUI rendering bugs by launching ralph in a tmux split pane and capturing live output.
Use tmux to drive interactive terminal sessions, including TUI workflows like ralph-tui.
One skill for all TDD workflows.
Run the ralph.reviewer.yml orchestration loop against a pull request.
A spec-driven development workflow: PRD → Epic → GitHub Issues → Parallel Agents → Shipped Code.
Bump version and trigger release for ralph-orchestrator.
Create polished terminal demos for PRs using asciinema recordings converted to GIF.
Use Playwriter to run Playwright Page scripts against your local Chrome session.
Transform a rough idea into a detailed design with an implementation plan.
This skill finds and displays all code tasks (.code-task.md files) in the repository, showing their frontmatter status and metadata.
Systematically test all hat collection presets using shell scripts.
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow.
Create and edit valid Obsidian Flavored Markdown.
This skill provides comprehensive validation, linting, and testing capabilities for Terragrunt configurations.
Use the obsidian CLI to interact with a running Obsidian instance.
Create the file: Create a .base file in the vault with valid YAML content 2.
A canvas file (.canvas) contains two top-level arrays following the JSON Canvas Spec 1.0:
Use Defuddle CLI to extract clean readable content from web pages.
The n8n-cli command-line tool manages an n8n instance via its REST API.
Specs live in .claude specs .
Configure commonly used MCP servers for n8n engineers.
Given a Linear ticket context ($ARGUMENTS), systematically reproduce the bug with a failing regression test.
Add OAuth2 (Authorization Code 3LO) support to an existing n8n node.
Fetch the transcript from a Loom video using Loom's GraphQL API.
Generate production-ready Terragrunt configurations following current best practices, naming conventions, and security standards.
Analyze project memory files (CLAUDE.md, AGENTS.md) for optimization.
Start work on Linear issue $ARGUMENTS
Skills are markdown (plus optional scripts) that teach the agent a focused workflow.
Creates GitHub PRs with titles that pass n8n's check-pr-title CI validation.
Create a Linear ticket or GitHub issue for: $ARGUMENTS
Guide for adding new ESLint rules to packages @n8n eslint-plugin-community-nodes .
📚 Full Documentation: - General: AGENTS.md - Architecture, commands, workflows - Frontend: packages frontend AGENTS.md - CSS variables, timing
You are a Senior Content Designer specializing in SaaS tools.
Remove the edit restriction set by freeze, allowing edits to all directories.
bash UPD=$( .claude skills gstack bin gstack-update-check 2> dev null || .claude skills gstack bin gstack-update-check 2> dev null || true) [ -n "$UPD" ] && echo "$UPD" || true mk…
Comprehensive toolkit for validating, linting, and testing Terraform configurations with automated workflows for syntax validation, security scanning, and intelligent documentatio…
