Code Review
Automated code review and analysis
intervals-time-entry
by olivoil
Fill Intervals Online time entries from daily notes with GitHub and Outlook calendar correlation. Use when asked to fill time entries, timesheets, or submit hours to Intervals. Requires chrome-devtools MCP with browser open to Intervals.
create-plan
by Cygnusfear
Create comprehensive implementation plan as a ticket based on analysis or report. Use when user asks to create a plan, plan implementation, design a solution, or structure work for a feature/refactor/fix.
analyse-issue
by tenfyzhong
Analyze GitHub issues by link or issue number. Use when a user says "analyse issue"/"analyze issue" or provides a GitHub issue URL/number and asks to fetch the issue content, verify it matches the current repo, and inspect local code to confirm the problem.
review
by VitaDynamics
Perform exhaustive code reviews using multi-agent analysis across 13+ specialized reviewer agents
refactor-dependency
by ShotaIuchi
Dependency mapping and analysis for refactoring. Apply when mapping import chains, call graphs, coupling relationships, circular dependencies, and hidden connections in target code.
verification-rules
by DUTSTECH
4-layer verification system for task completion. Use when verifying that a task has been fully completed before marking it done.
CSV Data Summarizer
by yousufjoyian
Claude agent skills and workspace configuration
code-audit
by pietz
Structural health assessment for codebases. Use when the user asks to audit code quality, assess code health, review a codebase, find technical debt, clean up code structure, or identify refactoring opportunities. Also use when asked to do a "code audit", "codebase review", "quality assessment", or "tech debt analysis". Provides parallel multi-lens analysis via sub-agents with specialized checklists for code health, cross-module coherence, refactoring detection, and security.
javascript-code-review
by TriNgo0108
Master JavaScript code review patterns including modern syntax, async/await, equality operators, memory leaks, and DOM manipulation. Use PROACTIVELY when reviewing JavaScript PRs.
code-review-checklist
by htooayelwinict
Review code changes for correctness, security, performance, and maintainability. Use for PR reviews, code audits, pre-merge checks, or quality validation of Laravel + React + Python code. EXCLUSIVE to reviewer agent.
pd
by kunhai-88
"通过对话式交互生成产品需求文档（PRD）。创建包含用户故事、质量门禁和验收标准的结构化 PRD。当用户希望创建 PRD、规划功能、编写需求、写规格说明，或提到「pd」「产品设计」「需求」「用户故事」时使用。"
auditing-bdd-tests
by viktor-silakov
Analyzes BDD (Gherkin) + Playwright test solutions. Produces aspect scoring (0/5/10), A–F grade, issues by severity, and Markdown + HTML report formats for deep test-solution analysis.
sif-learning-app
by rod-americo
Use when working on the Sif repository, especially for modular curriculum content, exercise metrics, the global review deck, and SQLite-backed study persistence.
gh-save
by AutoFor
feature ブランチの途中経過をコミット・プッシュし、Issue タイトル・本文と Draft PR 本文を現在の進捗で更新する。
plan-refiner
by dreambound
Generate and iteratively refine implementation plans from an initial spec/prompt. Takes a specification as input, generates an initial plan, then refines it through parallel multi-reviewer passes (minimum 3) with fresh agent context. User can continue beyond 3 passes until satisfied. Use when turning requirements into polished implementation plans.
istqb-foundation
by Hiccup-za
Comprehensive guide to ISTQB Foundation Level knowledge areas for QA testing. This skill provides detailed guidance on testing fundamentals, test techniques, test management, and static testing following the ISTQB Certified Tester Foundation Level (CTFL) syllabus. Use this when establishing standardized testing practices, designing test cases, selecting test techniques, or aligning team terminology with industry standards. Triggers on: establishing QA baselines, designing test cases, selecting test techniques, planning test activities, conducting reviews, managing test processes, or when standardized testing terminology and practices are needed.
Wireshark Network Traffic Analysis
by jcastillotx
This skill should be used when the user asks to "analyze network traffic with Wireshark", "capture packets for troubleshooting", "filter PCAP files", "follow TCP/UDP streams", "detect network anomalies", "investigate suspicious traffic", or "perform protocol analysis". It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark.
refactor-impact
by ShotaIuchi
Blast radius and risk assessment for refactoring. Apply when analyzing affected consumers, change propagation, risk levels, and areas requiring extra caution during refactoring.
design
by ddaanet
Triage complexity and design implementation approach. Triggers on /design, architecture or implementation planning requests, or tasks needing complexity assessment. Triages simple/moderate/complex, produces design documents for complex jobs, routes moderate to /runbook.
receiving-code-review
by Cygnusfear
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
refactor
by mguinada
"TDD-based code simplification that preserves behavior through tests. Use Red-Green-Refactor cycles to simplify code one test-verified change at a time. DISTINCT FROM: General code review or AI rewriting—this skill requires existing tests and only proceeds when tests confirm behavior is preserved. PROACTIVE: Auto-invoke when test-covered code has complexity (functions >50 lines, high cyclomatic complexity, duplication) and user wants to simplify it safely. Trigger phrases: 'clean up code', 'make code simpler', 'reduce complexity', 'refactoring help'. NOT FOR: Adding features or fixing bugs—use /tdd skill instead."
codesop
by veniai
Project workbench and workflow router for AI-assisted coding across Claude Code, Codex, and OpenCode. Restores context from AGENTS.md and PRD.md, summarizes current state, recommends the next skill, and explains what not to do yet. Proactively invoke this skill (do NOT answer directly) when the user: - asks what to do next, what skill to use, or wants a status/progress summary - says "continue", returns to a project after a gap, or looks confused about what step comes next - explicitly mentions codesop, /codesop, workflow, project status, or next step - wants help deciding whether to plan, debug, implement, review, or ship - describes a new feature, bug, refactoring, or small change without specifying a workflow Do not trigger when the user is explicitly invoking a mechanical subcommand like /codesop init or /codesop update. (codesop)
Solaudit - Smart Contract Security Scanner
by NguyenMinhGitHub
Solidity smart contract security auditor. Detect reentrancy, overflow, access control issues. 50+ vulnerability patterns. CI/CD ready. Free CLI tool.
limitation-of-liability-general
by scholarly360
Analyze, draft, and review Limitation of Liability clauses for General contracts. Use when the user mentions limitation of liability, liability cap, damages cap, or asks to review, redline, or generate this clause type. Returns structured risk assessment, plain-language summary, and suggested alternative language.