All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,957
- 665
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 11,017–11,040 of 15,957 skills
- Cortex EnginePersistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.Votes: 0GitHub stars: 2
- Company ValuesHelp define company values and culture for a minimalist business. Use when someone is setting up their company culture, preparing to hire, or wanting to codify what their company stands for.Votes: 0GitHub stars: 2
- Clever CompactYour OpenClaw agent forgets everything between sessions — after /new, after compaction, after overnight. Clever Compact fixes all three: injects your last state on session start, flushes before every compact, and keeps memory stable across context resets. Native plugin. Zero per-turn overhead. Install in 4 steps, runs automatically.Votes: 0GitHub stars: 2
- Clear PromptA skill that transforms vague prompts into precise, actionable instructions using 5 core principles.Votes: 0GitHub stars: 2
- Clawmind VfmClawMind — 自我进化 AI Agent 引擎，健康度驱动 + VFM 提案评分 + 经验记忆。依赖 OpenClaw 工作空间。当需要自我进化、自主驱动、健康度追踪、VFM 决策、经验存取时触发。Votes: 0GitHub stars: 2
- Claude DelegateDelegate various coding tasks to Claude Code. Use this skill when you need assistance with code generation, bug fixing, feature implementation, code review, refactoring, or file exploration. It streamlines calling Claude Code for non-interactive execution, handling parameters like `--print --permission-mode bypassPermissions`. Triggers on phrases like 'write code for', 'fix this bug in', 'implement feature', 'review this pr', 'refactor', 'explore files for', 'debug', 'code task for claude'.Votes: 0GitHub stars: 2
- Cjl Autoresearch CcImprove skills, prompts, articles, workflows, and systems via iterative mutation-testing.Votes: 0GitHub stars: 2
- Boss Report> "Boss, every task has a response." 📊 **Description**: Generates comprehensive work summaries (daily, weekly, monthly) for your boss/manager. Outputs to long-term memory and exports as HTML/PDF reports. **Triggers**: User says "boss report", "report to boss", "work summary", "daily report", "weekly report", "monthly report", or "/boss-report" ---Votes: 0GitHub stars: 2
- Automation Dedup GuardWorkBuddy 自动化任务去重守护。当用户的自动化任务出现重复时自动检测并清理。触发场景：自动化任务重复、任务列表膨胀、需要清理重复任务。支持 Windows/macOS/Linux，纯 Python 标准库，零依赖。Votes: 0GitHub stars: 2
- Art Tutor艺术学习私人助教。依据用户的学习目标、水平和偏好，从本地艺术知识库中精准推荐学习资源、规划学习路径，并解答技法疑问。当用户说"学画画"、"想学水彩"、"零基础学素描"、"帮我制定学习计划"、"推荐一些艺术书籍"等任何艺术学习相关需求时，触发本技能。Votes: 0GitHub stars: 2
- Arbitrage FinderReference tool for blockchain and crypto — covers intro, quickstart, patterns and more. Quick lookup for Arbitrage Finder concepts, best practices, and imple...Votes: 0GitHub stars: 2
- Apex Stack Claude CodeThe complete autonomous agent stack for Claude Code — APEX cognitive framework, MEMORIA persistent memory, and ARCHITECT goal execution engine — bundled into a single Claude Code skill. Drop it into your CLAUDE.md and instantly upgrade every Claude Code session: better thinking, persistent context, autonomous task execution. Built by contrario. Zero config. Works on every project.Votes: 0GitHub stars: 2
- Amazon Review使用 Reveyes API 批量抓取亚马逊商品评论，支持 20 个站点。 输出评论列表、星级分布统计和差评摘要。 Use when: 用户提到抓评论、查差评、分析竞品口碑、给出 ASIN 编号需要评论数据。 NOT for: 分析已经抓好的本地评论文件，或查询亚马逊商品价格/销量。Votes: 0GitHub stars: 2
- Amazon Review Reveyes使用 Reveyes API 批量抓取亚马逊商品评论，支持 20 个站点。 输出评论列表、星级分布统计和差评摘要。 Use when: 用户提到抓评论、查差评、分析竞品口碑、给出 ASIN 编号需要评论数据。 NOT for: 分析已经抓好的本地评论文件，或查询亚马逊商品价格/销量。Votes: 0GitHub stars: 2
- Album Pipeline> 专辑制作流水线总入口。从概念设计到发布物料打包，6 个 Phase 完整流程。 ---Votes: 0GitHub stars: 2
- Ai Code Quality EconomicsUnderstand the economic incentives driving AI code quality. Learn why good code will prevail over "slop" due to token efficiency, maintainability costs, and market competition in AI-assisted development.Votes: 0GitHub stars: 2
- Agent Templates SystemOpenClaw Agent Templates system reference and workflow guide. Use when creating, editing, reviewing, debugging, or extending the built-in Agent Templates feature; when working with template-backed agent creation; or when packaging/documenting the Agent Templates UI, gateway handlers, SQLite storage, workspace file seeding, identity defaults, or create-from-template flow.Votes: 0GitHub stars: 2
- Agent Git OracleAdvanced repository analysis and refactoring guide. Identifies technical debt and architectural anti-patterns using AI reasoning.Votes: 0GitHub stars: 2
- Afrexai Ai Coding Toolkit> The complete methodology for 10X productivity with AI-assisted development. Covers Cursor, Windsurf, Cline, Aider, Claude Code, GitHub Copilot, and more — tool-agnostic principles that work everywhere.Votes: 0GitHub stars: 2
- Aesthetic Scorer给你的照片打分、评价反馈、给出改进建议或美学分析 / Aesthetic photo scorer with detailed analysisVotes: 0GitHub stars: 2
- Adk Skill Patterns5 proven agent skill design patterns (Tool Wrapper, Generator, Reviewer, Inversion, Pipeline) from Google's ADK. Build reliable, composable skills with templates, decision trees, and composition guides. Stop cramming logic into prompts—use structured patterns instead.Votes: 0GitHub stars: 2
- 10x Talent School专为追求倍速增长的初建学校设计的教师选、育、用、留四环节体系。基于科德高中融合部真实管理经验，结合十部AI Agent架构，将人才管理从校长个人经验升级为可继承、可协同、可沉淀的组织能力。Votes: 0GitHub stars: 2
- RefineryConvergence loop that iteratively improves work until quality thresholds are met. Scores, diagnoses specific weaknesses, rewrites, re-scores, and repeats until all dimensions reach 8/10 or diminishing returns are detected. Use when you want to refine or iterate on work, after the analyst gives a REVISE verdict, or when output quality is below your bar. Part of the architect-system loop. Outputs to system/refinery-log.md.Votes: 0GitHub stars: 4
- AnalystSenior engineering analyst for code review, plan review, and automation review. Four-lens review covering architecture, code quality, reliability, and performance, each scored 1-10. Delivers APPROVE, REVISE, or REJECT verdicts. Use when you need a code review, plan review, quality check, or want to verify work before shipping. Part of the architect-system loop. Reads from system/blueprints/ and source code. Outputs to system/reviews/.Votes: 0GitHub stars: 4