Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 32221–32250 of 35202 skills

dev-systematic-debuggingkevinnft/ai-agent-skills4-phase root cause debugging: understand bugs before fixing.Stars: 15Updated Claude CodeCodexUnverifiedInstall
dev-tddkevinnft/ai-agent-skillsTDD: enforce RED-GREEN-REFACTOR, tests before code.Stars: 15Updated Claude CodeCodexUnverifiedInstall
user-ryzen-preferenceskevinnft/ai-agent-skillsUser ryzen's workflow preferences, communication style, and anti-patterns to avoidStars: 15Updated Claude CodeCodexUnverifiedInstall
dev-writing-planskevinnft/ai-agent-skillsWrite implementation plans: bite-sized tasks, paths, code.Stars: 15Updated Claude CodeCodexUnverifiedInstall
brainstormingkevinnft/ai-agent-skillsYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.Stars: 15Updated Claude CodeCodexUnverifiedInstall
dispatching-parallel-agentskevinnft/ai-agent-skillsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 15Updated Claude CodeCodexUnverifiedInstall
executing-planskevinnft/ai-agent-skillsUse when you have a written implementation plan to execute in a separate session with review checkpointsStars: 15Updated Claude CodeCodexUnverifiedInstall
finishing-a-development-branchkevinnft/ai-agent-skillsUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanupStars: 15Updated Claude CodeCodexUnverifiedInstall
receiving-code-reviewkevinnft/ai-agent-skillsUse 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 implementationStars: 15Updated Claude CodeCodexUnverifiedInstall
superpowers-requesting-code-reviewkevinnft/ai-agent-skillsUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 15Updated Claude CodeCodexUnverifiedInstall
superpowers-subagent-driven-developmentkevinnft/ai-agent-skillsUse when executing implementation plans with independent tasks in the current sessionStars: 15Updated Claude CodeCodexUnverifiedInstall
superpowers-systematic-debuggingkevinnft/ai-agent-skillsUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 15Updated Claude CodeCodexUnverifiedInstall
superpowers-tddkevinnft/ai-agent-skillsUse when implementing any feature or bugfix, before writing implementation codeStars: 15Updated Claude CodeCodexUnverifiedInstall
using-git-worktreeskevinnft/ai-agent-skillsUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 15Updated Claude CodeCodexUnverifiedInstall
using-superpowerskevinnft/ai-agent-skillsUse when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questionsStars: 15Updated Claude CodeCodexUnverifiedInstall
verification-before-completionkevinnft/ai-agent-skillsUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 15Updated Claude CodeCodexUnverifiedInstall
superpowers-writing-planskevinnft/ai-agent-skillsUse when you have a spec or requirements for a multi-step task, before touching codeStars: 15Updated Claude CodeCodexUnverifiedInstall
writing-skillskevinnft/ai-agent-skillsUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 15Updated Claude CodeCodexUnverifiedInstall
yuanbaokevinnft/ai-agent-skillsYuanbao (元宝) groups: @mention users, query info/members.Stars: 15Updated Claude CodeCodexUnverifiedInstall
plugin-fast-adapttaxueseek/plugin-fast-adaptDSH 插件升级适配与代码审查主入口。查 DeepSeek 官方最新版本与升级指南,扫描插件破坏性变更;支持四条车道(适配升级/造插件/启动排障/代码审查与防御性架构审核)及 DSH 原生插件与子 Agent 隔离委派协议,输出 P0/P1 紧凑报告。触发词:适配 DSH 插件、升级插件、插件不兼容、dsh 升级后报错、代码审查、代码审核、code review、生命周期检查、单例泄漏、Peer污染、紧凑报告、批量巡检。Stars: 15Updated Claude CodeCodexUnverifiedInstall
dsh-plugin-adapttaxueseek/plugin-fast-adaptplugin-fast-adapt 的升级适配车道。查 DeepSeek 官方最新版本,取该版本官方 upgrade-guide,扫描插件代码匹配破坏性变更锚点,报出踩了哪几条并给官方修法;seams 查包名或 API 符号在指南与本机宿主里的双源结论;改完秒验并做四维性能架构体检;官方指南覆盖不到的老版本转七阶段迁移 SOP。宿主环境本身有问题(覆盖层残留、悬空软链、插件装了没生效)不走这里,转 dsh-plugin-diagnose。触发词:适配 DSH 插件、升级插件、插件不兼容、dsh 升级后报错、插件用了废弃 API、接缝查询、这个 API 还在不在、扫描窗口、破坏性变更、老版本 DSH 适配、历史走廊迁移、插件性能审计、peer 修补。Stars: 15Updated Claude CodeCodexUnverifiedInstall
dsh-plugin-diagnosetaxueseek/plugin-fast-adaptDSH 插件装了没生效、客户端卡 loading、宿主起不来的排障车道。log-doctor 解析 ~/.dsh/logs 的 startup 日志(StartupError、端口占用、未声明 inject、客户端入口死链)给根因与下一步动作;env-doctor 巡检 profiles 覆盖层旧包残留、共享 node_modules 农场悬空软链、两层 patch、宿主半与客户端半双面启用就绪度;env-heal 清理覆盖层默认 dry-run。触发词:插件装了没生效、插件不激活、客户端卡 loading、entry did not activate、web boot 失败、注入死链、宿主启动失败、StartupError、EADDRINUSE、日志诊断、覆盖层旧包、悬空软链、共享农场、环境体检、Silent Pending。Stars: 15Updated Claude CodeCodexUnverifiedInstall
dsh-plugin-reviewtaxueseek/plugin-fast-adaptDSH 插件代码审查与防御性架构审核车道。基于 Git 范围或工作区源码,检查 Cordis 生命周期泄漏、未逆向注销、单例状态漂移、已废弃模板变量(如 {{cwd}})、Vendored Peer 依赖污染、准入账本覆盖,按 P0/P1/P2/P3 输出精炼结构化报告;提供子 Agent 隔离委派协议(Sub-agent Dispatch Pattern),在后台沙箱运行紧凑分析并回传精炼结果,防止主会话上下文污染。触发词:代码审查、代码审核、code review、插件体检、防御性审查、生命周期检查、单例泄漏、Peer污染、子Agent审查、紧凑报告。Stars: 15Updated Claude CodeCodexUnverifiedInstall
ab-testingopensite-ai/opensite-skillsWhen the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.Stars: 15Updated Claude CodeCodexUnverifiedInstall
accessibility-auditopensite-ai/opensite-skillsRun a comprehensive WCAG accessibility audit covering perceivable, operable, understandable, and robust principles. Use this skill whenever the user wants to audit accessibility, review WCAG compliance, fix accessibility issues, prepare for accessibility certification, address an accessibility lawsuit risk, or systematically improve a site's accessibility. Triggers on accessibility audit, WCAG audit, a11y audit, accessibility compliance, ADA compliance, screen reader test, keyboard navigation, accessibility report, fix accessibility, axe scan. Also triggers when accessibility issues have been reported and need systematic remediation.Stars: 15Updated Claude CodeCodexUnverifiedInstall
agent-file-engineopensite-ai/opensite-skillsRepository-specific AGENTS.md authoring and maintenance workflow. Use when creating, refreshing, or expanding AGENTS.md coverage for a codebase, including deciding whether nested AGENTS.md files are needed for subsystems with distinct rules, workflows, or AI-sensitive constraints.Stars: 15Updated Claude CodeCodexUnverifiedInstall
ai-research-workflowopensite-ai/opensite-skillsDeep research and AI workflow orchestration patterns for Octane. Use when working on brand guide generation, market analysis, competitive analysis, content brief, or any multi-step AI research pipeline. Covers the WorkflowBuilder/WorkflowStep orchestration system, Anthropic dual-model routing (Opus for research, Sonnet for generation), and the ai_tasks persistence pattern.Stars: 15Updated Claude CodeCodexUnverifiedInstall
ai-retrieval-patternsopensite-ai/opensite-skillsRetrieval architecture for AI applications — choosing and combining vector RAG, PageIndex (vectorless PDF tree-search), and precision embedding models. Covers the decision framework for matching retrieval strategy to document type and query characteristics, Milvus collection design, hybrid two-stage pipelines, the EmbeddingProvider abstraction, and the routing layer that ties it all together. Use when building semantic search, RAG pipelines, document Q&A, or any system where retrieval strategy and embedding model choice affect answer quality.Stars: 15Updated Claude CodeCodexUnverifiedInstall
amazon-bedrockopensite-ai/opensite-skillsBuilds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Applies when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing Bedrock models (Claude, Llama, Nova, Titan). Also for prompt caching, quota and throttling diagnosis, cost tracking, migrating between Claude model generations, chunking strategies, and Bedrock model selection. Covers AgentCore Payments (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, paid endpoints, agent payments). NOT for custom model training, Rekognition, or Comprehend. For SageMaker model discovery, customization, or endpoints, use aws-ai-ml.Stars: 15Updated Claude CodeCodexUnverifiedInstall
analyticsopensite-ai/opensite-skillsWhen the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this," "track conversions," "Mixpanel," "Segment," "are my events firing," or "analytics isn't working." Use this whenever someone asks how to know if something is working or wants to measure marketing results. For choosing attribution models, comparing multi-touch/MMM/incrementality, or reconciling conflicting numbers across tools, see attribution. For A/B test measurement, see ab-testing.Stars: 15Updated Claude CodeCodexUnverifiedInstall