Code Review
Automated code review and analysis
zdev
by 5hanth
Manage isolated dev environments with git worktrees, auto ports, and preview URLs
manuscript-writing
by YSLAB-ai
Use when revising or reviewing scientific, technical, or academic manuscripts, proposals, abstracts, reports, or related writing for precision, concision, logical cohesion, citation support, evidence alignment, and objective scholarly tone.
react-coding-standards
by Lichens-Innovation
"Enforces internal React and TypeScript coding standards using avoid/prefer rules. Use when reviewing or refactoring React/TS code, applying company standards, or when the user asks to align code with coding standards."
security-review
by htooayelwinict
Audit code for security vulnerabilities using OWASP Top 10 guidelines. Use for security audits, pre-deployment checks, authentication reviews, or when checking for XSS, SQL injection, CSRF, or authorization issues. EXCLUSIVE to security-expert agent.
code-review
by SPUERSAIYAN
Review code changes, shell commands, tool calls, file operations, test results, and implementation decisions produced by any AI IDE or coding assistant, then generate a standalone HTML report from a static template. Use when the user asks to audit, review, summarize, inspect, document, or deliver a report about what an AI coding tool changed, executed, verified, failed to verify, or is uncertain about.
gh-address-comments
by aleister1102
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
screenshot-to-website
by gemini960114
Build a fully working replica of a website from a screenshot, matching design and functionality exactly.
tpr-framework
by evan-zhang
TPR（Think / Probe / Review）统一工作方法。 用于把复杂问题从模糊需求转化为可验证、可执行、可复盘的结果。 当遇到以下场景时激活： - 需要结构化分析复杂问题 - 启动项目、起草方案、审查方案 - 用户提到 TPR / 三层架构 / GRV / Battle / DISCOVERY - 需要做决策前的系统性思考
security-agent-efficiency
by aleister1102
Use when running a full security audit of an arbitrary source code repository. Orchestrates a 9-phase workflow combining advisory intelligence, patch bypass analysis, knowledge base construction, SAST, spec gap analysis, deep bug hunting, false positive elimination, and variant analysis. Triggers on "audit this repo", "run a full security audit", "find vulnerabilities in this codebase", "check for security issues", "is this secure?", "run the security agents", or any request combining advisory regression, SAST, and manual review.
skeleton-dev
by finnan444
Build UI with Skeleton UI v4 (any framework). Use when creating, editing, or reviewing any component that uses Skeleton UI — buttons, modals, tabs, navigation, forms, cards, avatars, etc. Also use when questions involve Skeleton presets, color pairings, composed component patterns, or theming. Supports Svelte, React, and framework-agnostic usage.
plan
by biruk741
Plan a complex coding task with adversarial review. Explores the codebase, asks clarifying questions, drafts a plan, then iterates with Codex for adversarial review against 10 quality criteria. Falls back to Claude-only if Codex unavailable. Does NOT create files — use /parallelize after.
memory-lucia
by wen521
Memory Lucia - Local SQLite-based memory system for OpenClaw agents. Features: (1) Priority analysis and tracking, (2) Learning progress with milestones, (3) Decision recording with review scheduling, (4) Skill evolution monitoring, (5) Local text search across all memory tables, (6) Automatic database backups. All data stored locally in SQLite database. No external API calls.
KnowledgeLM NSE
by eggmasonvalue
AI agent skill to download NSE listed company filings and upload them to notebookLM
remote-desktop-audio-config
by yousufjoyian
Diagnose and fix audio device detection and routing on NixOS xRDP remote desktop sessions. Handles PulseAudio hardware detection, xRDP audio redirection, and USB audio devices.
clawlist
by arisylafeta
"MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations."
marketplace-earning
by coopergwrenn
Earn money autonomously via Clawlancer bounties and digital product creation on external marketplaces. Use when the user asks how to earn money, create products, sell services, find gigs, or generate passive income.
laravel-debugging
by MamounHisham1
Debugs Laravel applications with Xdebug integration. Activates when setting breakpoints, stepping through code, inspecting variables, analyzing dd() output, debugging routes, controllers, queues, or Eloquent queries; or when user mentions debug, breakpoint, step into, inspect variables, Xdebug, or troubleshooting errors.
unit-test
by kyzooghost
Guidelines for writing and reviewing unit tests. Covers AAA pattern, test naming, determinism, mocking strategies, and reviewer responsibilities. Use when creating or updating .test. files, reviewing test PRs, or refactoring tests to improve clarity and coverage.
review
by pmco23
Use after /design to adversarially review the design document. Dispatches strategic-critic (Opus) and code-critic (Sonnet) in parallel — Opus for strategic critique grounded in Context7, Sonnet for code-grounded critique against the existing codebase. Lead deduplicates, runs cost/benefit analysis, loops until all MUST FIX findings resolve. Writes .pipeline/design.approved on loop exit.
getting-started
by pproenca
This skill is loaded automatically at session start via SessionStart hook. Establishes protocols for finding and using skills, checking skills before tasks, brainstorming before coding, and creating tasks for checklists.
Agent Design 2
by hhopkins95
This skill should be used when the user asks to "configure agent profile", "add skills to agent", "set up MCP servers", "configure agent tools", "write system prompt", "create agent workflow", "define agent commands", "add subagents", or needs to define what capabilities an agent has and how to orchestrate complex workflows in the runtime.
elm-performance-review
by bromanko
This skill should be used when the user asks to "review performance", "optimize Elm", "Elm performance", "performance audit", "find bottlenecks", "improve efficiency", or wants analysis of Elm code performance focusing on virtual DOM efficiency, rendering patterns, and data structure choices.
jpralph-iterate
by juanpare
"Execute a single Ralph iteration - implement one user story autonomously. Use for manual mode where you want maximum control and fresh context per story. Triggers on: ralph iterate, execute one story, run single iteration, manual ralph."
address-github-comments
by ncdevshiv
"Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI."