agentsclimarketplace

Context & AI engineering

25,772 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Skill seekers doc to skill

    findscripter/everything-skills/04-ai/skill-seekers-doc-to-skill Skill

    no license11★ repo

    当需要把文档网站、GitHub 仓库、PDF 或视频批量转成可用的 AI 技能(SKILL.md + references)时使用;用 skill-seekers 完成抓取→增强→打包→上传/安装到 Claude 或各 Agent 全流程;不适用于手写单条精炼技能、或源缺乏结构化文档时。触发词:文档转技能、爬文档建技能、skill-seekers、批量生成技能

  • Ai answer engine seo

    findscripter/everything-skills/05-business/ai-answer-engine-seo Skill

    no license11★ repo

    当你希望内容被 ChatGPT / Perplexity / Google AI Overviews / Claude / Gemini / Copilot 等 AI 搜索"引用"而非只在蓝链里"排名"时使用;做 AI 可见性审计、按"结构·权威·可发现"三支柱改写内容并产出 robots.txt 修复、可提取内容块、Schema 与引用监控方案;不适用于传统排名 SEO 审计(用 seo-audit)或从零写内容(用 seo-content-writer)。触发词:AI SEO、GEO、AEO、生成式搜索、被ChatGPT引用、AI Overviews、Perplexity引用、LLM 可见性、答案引擎优化

  • Ai search seo

    findscripter/everything-skills/05-business/ai-search-seo Skill

    no license11★ repo

    当需要让内容被 AI 搜索与大模型引用(AI Overviews、ChatGPT、Perplexity、Claude、Gemini、Copilot)时使用;做 AI 可见性审计、按结构/权威/存在三支柱重写内容并产出可抽取的答案块、Schema 与 robots.txt 放行清单;不适用于纯传统排名 SEO 或不在乎 AI 引用的场景;触发词:AI SEO、AEO、GEO、AI 引用、LLM 可见性、AI Overviews

  • Fx carry trade eval

    findscripter/everything-skills/05-business/fx-carry-trade-eval Skill

    no license11★ repo

    当评估外汇套息(carry)机会、需把即期/远期/利差/波动率曲面/历史价位串成风险调整结论时使用;做组合 MCP 取价、算各期限年化 carry 与 carry-to-vol 比率、出 carry profile 表与带头寸建议的交易推荐;不适用于无 FX 行情/曲面 MCP 工具的离线场景、单纯现货方向投机、或期权波动率本身的交易;触发词:套息交易、carry trade、carry-to-vol、远期点、利差、波动率曲面、货币对

  • Design dev handoff

    findscripter/everything-skills/06-creative/design-dev-handoff Skill

    no license11★ repo

    当设计稿定稿、要交给工程实现时使用;产出覆盖布局/设计令牌/组件 props/交互状态/响应式断点/边界情况/动效的开发交付规格文档;不适用于尚在探索的概念稿或纯视觉评审;触发词:设计交付、handoff、Figma 转开发

  • Google stitch ui prompting

    findscripter/everything-skills/06-creative/google-stitch-ui-prompting Skill

    no license11★ repo

    当用 Google Stitch(Gemini 驱动的 Labs UI 生成器)由文字/草图生成 Web 或移动端界面时使用;做提示词工程,产出具体、含视觉风格与功能要求的可执行提示词及迭代/导出方案;不适用于手写生产代码、做交互动效实现或替代真人评审。触发词:Stitch、UI 提示词、文字转界面、界面生成、导出 Figma/HTML。

  • Agent workflow builder

    findscripter/everything-skills/07-productivity/agent-workflow-builder Skill

    no license11★ repo

    当需要为 Claude Code 的 Workflow 工具编写确定性、可恢复的多智能体编排脚本(.claude/workflows/ 下的 .js 文件),把任务扇出给全新上下文子智能体时使用;做需求 intake、拓扑选型并产出可运行的工作流脚本(扇出/流水线/循环/评审团);不适用于单智能体单任务(用 Agent)或需模型动态决定步骤的可复用流程(用 Skill)。触发词:工作流编排、workflow、多智能体、子智能体编排、fan-out、pipeline、judge-panel、agent fan-out、orchestrate sub-agents

  • Board prep orchestrator

    findscripter/everything-skills/07-productivity/board-prep-orchestrator Skill

    no license11★ repo

    当要为一次高风险董事会/投资人更新/融资路演系统性筹备,需把"备数字、备问题、备叙事、备演练、备到人"串成一条可执行流水线时使用;产出脱稿数字清单、对抗问题库、五段叙事框架、模拟董事会脚本、逐董事画像与会前48h/会中/会后清单;不适用于内部团队周会、友好型进度同步、纯财务建模或汇报材料排版。触发词:董事会筹备、会前编排、投资人更新、融资路演、模拟董事会、董事画像

  • Chief of staff orchestrator

    findscripter/everything-skills/07-productivity/chief-of-staff-orchestrator Skill

    no license11★ repo

    当创始人/负责人抛出需多专业角色判断的问题或重大决策时使用;做问题复杂度评分、路由到合适的 C 级角色或召开"董事会"、综合各方意见并记录决策;不适用于单一明确领域的小问题或无需多角色的直接执行;触发词:幕僚长、多角色编排、路由分发、董事会评议、决策综合、决策日志

  • Kanban agent pipeline orchestrator

    findscripter/everything-skills/07-productivity/kanban-agent-pipeline-orchestrator Skill

    no license11★ repo

    当想把现有看板(Asana/Linear/GitHub Projects)当成分布式状态机、编排多个 Claude Code worker 跑完「构建→评审→测试→集成」全自动开发流水线时使用;做的事是把 SPEC 拆成带依赖的看板任务、按传递优先级派单、用确定性门禁(tsc/eslint/test)+对抗式评审把关、逐任务记成本、无守护进程崩溃可恢复;不适用于单 worker 小改动、无看板/PM 工具、或不接受 AI 自动改主干的场景;触发词:看板编排、kanban orchestration、自动开发流水线、SDLC orchestrate、多 worker 派单、对抗式评审 adversarial review

  • Multi agent orchestrator

    findscripter/everything-skills/07-productivity/multi-agent-orchestrator Skill

    no license11★ repo

    当有 3 个以上专职 AI Agent 需协同完成复杂任务,且出现重复劳动、冲突改文件或质量参差时使用;做的事是搭建单一编排器(任务拆解→去重→路由→质量门禁→心跳监控)并产出任务登记表、委派指令与验收证据;不适用于单 Agent 简单任务或无需协同的场景;触发词:多智能体编排、multi-agent orchestration、任务路由 task routing、Agent 去重 anti-duplication、质量门禁 quality gate、心跳监控 heartbeat

  • Oncall handoff writer

    findscripter/everything-skills/07-productivity/oncall-handoff-writer Skill

    no license11★ repo

    当 On-Call/值班轮换交接、需让接班工程师获得完整态势感知时使用;做按固定模板产出含活跃事故/在查问题/近期变更/已知问题/升级路径的值班交接文档(含事中交接 IC 移交与异步快速交接);不适用于事后复盘报告、对外状态页公告、事故根因分析本身;触发词:值班交接、On-Call 交接、轮班交接、shift handoff、on-call handoff、交接文档、值班轮换、事中交接、incident handoff、watch list、升级路径、escalation

  • Agent plugin audit

    findscripter/everything-skills/08-security/agent-plugin-audit Skill

    no license11★ repo

    当要把一个技能/插件/Agent/命令合入或发布前做一次性全量闸门时使用;做结构+质量+脚本+安全+市场合规+生态集成+代码评审的 8 阶段审计并产出 PASS/带警告 PASS/FAIL 的闸门报告(自动修非关键项);不适用于运行时沙箱、单纯安全扫描(用 agent-skill-security-scanner)、CVE 实时联网核验;触发词:审计这个插件、发布前闸门、plugin audit、技能合规检查、上架前检查、8 阶段审计、quality gate

  • Agent skill security scanner v2

    findscripter/everything-skills/08-security/agent-skill-security-scanner-v2 Skill

    no license11★ repo

    当准备采用/安装第三方 Agent 技能、需在信任前评估其安全性时使用;做静态扫描+人工研判,产出含发现项/置信度/风险等级与采用建议的安全审查报告;不适用于自身代码漏洞审计或运行时沙箱防护。触发词:技能安全扫描、提示注入检测、采用前审查

  • Agent skill security scanner

    findscripter/everything-skills/08-security/agent-skill-security-scanner Skill

    no license11★ repo

    当要安装或评估来自不可信来源的第三方 Agent 技能(本地目录或 git 仓库)时使用;做静态安全审计并产出 PASS/WARN/FAIL 裁决、按严重级分组的发现项与修复建议;不适用于运行时动态沙箱、CVE 实时联网核验、逻辑炸弹/延时载荷检测;触发词:审计这个技能、技能安全扫描、这个技能安全吗、安装前安全检查、技能漏洞扫描、prompt injection 检测、供应链审计、audit this skill、is this skill safe、scan skill for security

  • Agentic actions auditor

    findscripter/everything-skills/08-security/agentic-actions-auditor Skill

    no license11★ repo

    当审计调用 AI 编码 Agent(Claude Code Action、Gemini CLI、OpenAI Codex、GitHub AI Inference)的 GitHub Actions 工作流是否存在提示注入与攻击者可控输入风险时使用;做静态发现工作流、识别 AI 步骤、跨文件解析、捕获安全上下文、按 9 类攻击向量检测并产出分级发现报告;不适用于非 GitHub CI(Jenkins/GitLab/CircleCI)、无 AI Agent 的普通工作流、运行时注入实测或自动修改文件;触发词:agentic actions、AI Agent 工作流安全、提示注入审计、prompt injection、pull_request_target、Claude Code Action、env 中间变量、沙箱配置审计

  • Ai system security audit

    findscripter/everything-skills/08-security/ai-system-security-audit Skill

    no license11★ repo

    当评估 LLM/分类器/嵌入模型或 Agent 系统的注入、越狱、模型反演、数据投毒、工具滥用风险时使用;做静态签名扫描、按访问级别打分、映射 MITRE ATLAS 技术并输出护栏方案与报告;不适用于通用 Web/API 应用渗透或基础设施异常检测(见 code-reviewer/dependency-auditor)。触发词:AI 安全、prompt injection、提示注入、jailbreak、越狱、model inversion、模型反演、data poisoning、数据投毒、agent tool abuse、工具滥用、MITRE ATLAS、LLM 红队

  • Memory forensics

    findscripter/everything-skills/08-security/memory-forensics Skill

    no license11★ repo

    当对内存镜像(RAM dump)做事件响应或恶意软件分析、需追查注入/隐藏进程/凭据/Rootkit 时使用;做内存采集→Volatility 3 分析→提取进程、网络、注册表、文件、YARA 命中等取证产物;不适用于纯磁盘/网络流量取证、活体系统在线排查或非内存证据;触发词:内存取证、memory dump、Volatility、malfind、内存镜像

  • Multi framework compliance orchestrator

    findscripter/everything-skills/08-security/multi-framework-compliance-orchestrator Skill

    no license11★ repo

    当同时搭建多框架合规项目、规划年度审计日历或冲刺认证 stage 1 时使用;做四件事并产出结果——选框架(选择器)、算重叠(跨框架映射+证据复用)、模拟审计(从205场景库抽)、整合统一证据清单;不适用于单框架技术落地/控制项配置或日常证据维护;触发词:多框架合规、跨框架映射、证据复用、模拟审计、认证就绪

  • Security antipattern hook

    findscripter/everything-skills/08-security/security-antipattern-hook Skill

    no license11★ repo

    当 AI Agent 在写代码/改文件(涉及鉴权、支付、用户输入、IaC)时使用;提供一个 PreToolUse 钩子,在 Edit/Write/MultiEdit 落盘前用子串匹配拦截 12 类安全反模式(命令注入、XSS、SQL 注入、不安全反序列化、eval/new Function 代码注入、GitHub Actions 工作流注入)并产出告警;不适用于 AST 级精确扫描或 CI 阶段的 SAST(用 semgrep/CodeQL)。触发词:安全钩子、拦截不安全代码、security hook、block unsafe code、command injection、SQL injection、eval/pickle/os.system

  • Varlock env secrets guard

    findscripter/everything-skills/08-security/varlock-env-secrets-guard Skill

    no license11★ repo

    当在 AI Agent/Claude 会话、终端、日志或 git 提交中处理含密钥的环境变量、想让敏感值默认脱敏不外泄时使用;做法是用 varlock 在 .env.schema 中以 @sensitive/@type/@required 声明并校验 env,用 varlock run 注入运行时、用其自动脱敏的 redacted 输出替代明文 echo,产出可校验、可加密提交且日志安全的 env 工作流;不适用于生产级集中密钥库/HA/动态短期凭据基建(见 secrets-management)。触发词:varlock、env 脱敏、密钥不进日志、.env.schema、会话密钥泄露

  • Bulk rnaseq orchestrator

    findscripter/everything-skills/09-verticals/bulk-rnaseq-orchestrator Skill

    no license11★ repo

    当你手握 bulk RNA-seq 原始 FASTQ 或定量输出、要走「可复现可辩护」的完整差异表达研究时使用;做实验设计/QC 把关→比对定量(nf-core/rnaseq 或 STAR/Salmon 两条路)→基因级计数矩阵→分发给差异表达/富集/作图的流程编排,产出计数矩阵+元数据模板+各阶段交接;不适用于单细胞(用 single-cell-rnaseq-analysis)、只做 DE 统计(用 pydeseq2)或只做富集;触发词:RNA-seq、bulk、FASTQ to DESeq2、nf-core/rnaseq、STAR、Salmon、计数矩阵、链特异性、QC、流程编排

  • Defi natural language agent

    findscripter/everything-skills/09-verticals/defi-natural-language-agent Skill

    no license11★ repo

    当用户想用自然语言在 EVM 链上做 DeFi 操作(查价/换币/质押/桥接)并签名上链时使用;驱动 Aomi CLI 把提示转成钱包待签交易,先 list+模拟再经显式批准签名;不适用于无网络后端、非本人账户或绕过防盗保护。触发词:DeFi 代理、链上交易、自然语言换币、Aomi、钱包签名、跨链桥

  • Amazon alexa skill builder

    findscripter/everything-skills/10-platform/amazon-alexa-skill-builder Skill

    no license11★ repo

    当需要用 ASK CLI + AWS Lambda 开发 Amazon Alexa 语音技能、并以 Claude 作为对话大脑(含 DynamoDB 记忆、Polly 语音、APL 屏显、Smart Home 控制)时使用;做交互模型/Lambda 处理器/部署脚本的搭建与产出;不适用于纯网页/移动 App 或非 Alexa 平台语音助手;触发词:Alexa、ASK CLI、语音技能、Smart Home

  • Claude code settings auditor

    findscripter/everything-skills/10-platform/claude-code-settings-auditor Skill

    no license11★ repo

    当为某仓库初始化或审计 Claude Code 的 .claude/settings.json 权限时使用;做检测技术栈/构建工具/monorepo 结构并产出仅含只读命令的 permissions allow 推荐清单(及按需的 .mcp.json 建议);不适用于会改状态的安装/构建/部署命令、自定义脚本或绝对路径授权;触发词:settings.json、claude 权限审计、只读 allow 清单、权限基线、mcp 配置

  • Exa semantic search

    findscripter/everything-skills/10-platform/exa-semantic-search Skill

    no license11★ repo

    当需要基于语义/向量做网页检索、找相似内容或按类别(公司/人物/论文等)做结构化调研时使用;做 Exa API 语义搜索并产出带正文摘要的结果集;不适用于精确关键词匹配、站内全文检索或纯本地数据查询;触发词:语义搜索、相似内容、Exa

  • Imessage claude bridge

    findscripter/everything-skills/10-platform/imessage-claude-bridge Skill

    no license11★ repo

    当想用手机 iMessage/短信远程驱动笔记本上的 Claude Code 会话(发文字/语音/图片、跑代码、cd 切目录)时使用;做部署 njerschow/textme 本地守护进程、配置 Sendblue 凭证与手机号白名单、验证非白名单拦截后再持久化,产出可远控的「手机→Claude」入站通道;不适用于仅需「任务完成后发短信通知我」的纯出站场景(那是 sendblue-notify,无需守护进程)。触发词:text claude、手机控制 claude、远程驱动 claude、imessage 控制电脑、textme、sendblue 入站

  • Mcp builder

    findscripter/everything-skills/10-platform/mcp-builder Skill

    no license11★ repo

    当需要为外部 API/服务构建 MCP(Model Context Protocol)服务器、设计供 LLM 调用的工具并产出可评测的服务器时使用;做 MCP 服务器的研究/实现/测试/评估全流程产出(工具 schema、分页、错误处理、评估 XML);不适用于编写普通 REST API、调用现成 MCP 客户端或仅集成单个 Anthropic SDK 功能;触发词:MCP、MCP 服务器、Model Context Protocol、FastMCP、TypeScript SDK、工具暴露给 LLM、build mcp server、registerTool。

  • N8n mcp tools expert

    findscripter/everything-skills/10-platform/n8n-mcp-tools-expert Skill

    no license11★ repo

    当用 n8n-mcp MCP 工具集搜节点、校验配置、套模板或增删改工作流时使用;做工具选型、参数格式与迭代流程指引,产出可落地的搜索→校验→建流→激活闭环;不适用于在 n8n UI 手工拖拽或不走 MCP 的场景;触发词:n8n-mcp、search_nodes、validate_node、n8n_update_partial_workflow、nodeType

  • Vexor vector cli setup

    findscripter/everything-skills/10-platform/vexor-vector-cli-setup Skill

    no license11★ repo

    当需要按语义(而非关键词/正则)在文件与代码库中检索内容、或为 Claude/Codex 智能体接入语义文件搜索能力时使用;用 vexor CLI 安装、配置嵌入与重排提供方、建立可复用索引并执行语义搜索,产出带相似度分数的结果与 agent skill 集成;不适用于纯字面/正则匹配(用 grep/ripgrep)、无嵌入 API Key 或本地模型时;触发词:语义搜索文件、vexor、向量检索代码、embedding 文件搜索、自然语言找文件

  • Zoom mcp connectors

    findscripter/everything-skills/10-platform/zoom-mcp-connectors Skill

    no license11★ repo

    当通过 MCP 工具访问 Zoom 会议、录制、会议资产或转录时使用;规划工具面/鉴权并排障 401/-32001/-32602/404,产出可执行调用方案;不适用于会议增删改(走 REST)、白板(走 whiteboard)。触发词:zoom mcp、search_meetings、ai companion transcript

  • Zoom virtual agent builder

    findscripter/everything-skills/10-platform/zoom-virtual-agent-builder Skill

    no license11★ repo

    当把 Zoom Virtual Agent(虚拟客服坐席)嵌入网站、Android WebView 或 iOS WKWebView,做活动/入口聊天嵌入、原生桥接、转人工与知识库同步时使用;做一套含「就绪门控(zoomCampaignSdk:ready / waitForReady)、Campaign 优先嵌入、native 桥接 exitHandler/commonHandler/support_handoff、外链策略、KB 自定义 API 同步」的可落地集成;不适用于 Contact Center 客户端面板、纯后端 OAuth/REST 自动化或非 Zoom 客服平台;触发词:zoom virtual agent、zva、虚拟客服、zoomCampaignSdk、zcc-sdk、campaign embed、entry id、support_handoff、知识库同步、webview 客服。

  • Agent open questions

    bostonaholic/team/skills/agent-open-questions Skill

    11★ repo

    Drive a feature from idea to PR with a team of Claude Code agents.

  • Nested agents

    bostonaholic/team/skills/nested-agents Skill

    11★ repo

    Guardrails for spawning nested sub-agents from inside a Team pipeline agent (Claude Code >= 2.1.172) — loaded by researcher, implementer, code-reviewer, and security-reviewer. Nested dispatch is a context-economy optimization, never a dependency.

  • Qrspi workflow

    bostonaholic/team/skills/qrspi-workflow Skill

    11★ repo

    Worktree-Question-Research-Design-Structure-Plan-Implement-PR phase discipline with gate enforcement — loaded by orchestrator to govern pipeline phase transitions, artifact conventions, and anti-patterns

  • Team worktree

    bostonaholic/team/skills/team-worktree Skill

    11★ repo

    Prepare one or more isolated git worktrees — one per repository the topic touches. Router action — no agent. Trigger on "set up the worktree", "isolate this work", or "/team-worktree".

  • Worktree isolation

    bostonaholic/team/skills/worktree-isolation Skill

    11★ repo

    Worktree isolation methodology — loaded by the router to run the entire Team pipeline in one or more isolated git worktrees, enabling parallel /team runs and features that span multiple repositories

  • Golang how to

    alexastrum/skl/.agents/skills/golang-how-to Skill

    11★ repo

    Golang skills orchestrator — always active on any Golang coding, review, debug, or setup task. Reads the task context and loads the most relevant skills from samber/cc-skills-golang, often multiple at once: writing a gRPC service loads golang-grpc + golang-testing + golang-error-handling; debugging a panic loads golang-troubleshooting + golang-safety; auditing security loads golang-security + golang-lint + golang-safety. Also: disambiguates competing clusters when two skills seem to overlap (performance vs benchmark vs troubleshooting, samber/lo vs mo vs ro, DI cluster, safety vs security), and configures CLAUDE.md or AGENTS.md to force-trigger skills in a project (/golang-how-to configure).

  • Skill creator

    0GiS0/ghcp-agent-skills/personal-skills/skill-creator Skill

    no license11★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

  • Delivery orchestrator

    jpantsjoha/ai-native-developer-experience/.agents/skills/delivery-orchestrator Skill

    11★ repo

    Decompose an epic into atomic parallelizable tasks and route each task to the right skill. Use this as a meta-router when you have more than one skill available and need to decide which applies. Trigger at the start of any multi-track epic or when the skill count in your harness exceeds ~12.

  • Mcp server scaffold

    jpantsjoha/ai-native-developer-experience/.agents/skills/mcp-server-scaffold Skill

    11★ repo

    Scaffold and govern an MCP server as a bounded tool seam. Defines which tools the agent may call, enforces the principle that agents call tools and tools call infrastructure. Trigger when adding or reviewing an MCP server in an agent system.

  • Speccrew feature designer orchestration

    charlesmu99/speccrew/.speccrew/skills/speccrew-feature-designer-orchestration Skill

    11★ repo

    Feature Designer 的核心编排技能,负责加载功能清单、协调功能分析、功能规格设计与 API 契约生成。处理单个功能(直接调用)和多个功能(Worker 分发)两种工作流路径。

  • Speccrew product manager orchestration

    charlesmu99/speccrew/.speccrew/skills/speccrew-product-manager-orchestration Skill

    11★ repo

    Product Manager core orchestration skill (pure routing layer v2.0), responsible for workflow resume routing and dispatch-to-worker scheduling for each Phase Skill. All business logic is executed by independent Phase Skills.

  • Speccrew system deployer orchestration

    charlesmu99/speccrew/.speccrew/skills/speccrew-system-deployer-orchestration Skill

    11★ repo

    System Deployer 的编排调度技能,负责执行部署工作流:阶段门禁验证、IDE目录检测、准备阶段、技能调度(构建→迁移→启动→冒烟测试)、部署总结确认。

  • Speccrew system designer orchestration

    charlesmu99/speccrew/.speccrew/skills/speccrew-system-designer-orchestration Skill

    11★ repo

    System Designer orchestration skill. Manages the complete system design workflow from stage gate checking through platform dispatch to joint confirmation. Coordinates framework evaluation, design overview generation, and parallel platform-specific design tasks across web, mobile, desktop platforms.

  • Speccrew system developer orchestration

    charlesmu99/speccrew/.speccrew/skills/speccrew-system-developer-orchestration Skill

    11★ repo

    System Developer 的核心编排技能,负责读取系统设计蓝图、协调跨平台开发任务分发、加载技术知识、验证环境就绪、分发各平台开发技能、执行集成检查、交付开发完成报告。支持 web、mobile、desktop 和 backend 平台。

  • Speccrew test manager orchestration

    charlesmu99/speccrew/.speccrew/skills/speccrew-test-manager-orchestration Skill

    11★ repo

    Test Manager 的编排调度技能,负责执行三阶段测试工作流:测试用例设计 → 测试代码生成 → 测试执行与报告。支持单平台直接调用和多平台 Worker 并行调度。

  • Skill creator

    Flexonze/claude-init/.claude/skills/skill-creator Skill

    10★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

    The same file is in 66 other repositories

  • Obsidian mcp

    r007b34r/opencode-obsidian-knowledge-workflow/skills/obsidian-mcp Skill

    10★ repo

    Vault operation safety layer for all Obsidian MCP operations. Load when any vault read/write/search/tag/edit/verify is needed. Do NOT use alone for workflow decisions; combine with companion skill.

  • Design refiner

    JHostalek/dotclaude/skills/design-refiner Skill

    10★ repo

    Use when the user wants a UI/UX/frontend *build request* rewritten into an expert design brief before an LLM builds from it. Rewrites the prompt, never executes it; sharpens vague gestures into named techniques, makes implicit constraints explicit, and surfaces absent load-bearing dimensions as author-facing fill slots — never fabricating specifics. Do NOT trigger for design exploration or alternative directions (use design), page/flow usability review (use ux), person-to-person voice rewrites (use writing-identity), or LLM prompt engineering (use prompt). Triggers - "refine this design prompt", "make this UI prompt better", "turn this into a design brief", or "/design-refiner" with a prompt or path.

  • Prompt

    JHostalek/dotclaude/skills/prompt Skill

    10★ repo

    Use when the user asks to create, refine, evaluate, or optimize an LLM system prompt.

  • Learning memory

    yugash007/edu-agent-skills/skills/memory/learning-memory Skill

    10★ repo

    Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.

  • Tt hook scripter

    sergebulaev/tiktok-skills/.codex-marketplace/tiktok-skills/skills/tt-hook-scripter Skill

    10★ repo

    Script the first 1-3 second TikTok hook: the spoken line, the on-screen text, and the opening visual firing at once so the viewer cannot swipe. Picks a 2026 hook formula (cold-open result, pattern interrupt, number reveal, open-loop question, relatable call-out, story) by goal of completion, saves, comments, or shares. The single biggest retention lever on TikTok. Use to script a hook from a video idea. Not for the caption (use tt-caption-writer) or scrubbing a script (use tt-humanizer).

  • Tt hook scripter

    sergebulaev/tiktok-skills/skills/tt-hook-scripter Skill

    10★ repo

    Script the first 1-3 second TikTok hook: the spoken line, the on-screen text, and the opening visual firing at once so the viewer cannot swipe. Picks a 2026 hook formula (cold-open result, pattern interrupt, number reveal, open-loop question, relatable call-out, story) by goal of completion, saves, comments, or shares. The single biggest retention lever on TikTok. Use to script a hook from a video idea. Not for the caption (use tt-caption-writer) or scrubbing a script (use tt-humanizer).

  • Hive workers skill

    smith-horn/product-builder-starter/skills/hive-workers-skill Skill

    no license10★ repo

    Execute tasks using hive mind orchestration with parallel agents, automatic code review, and documentation updates. Use for feature execution, epic completion, or complex multi-task work.

  • Worktree manager

    smith-horn/product-builder-starter/skills/worktree-manager Skill

    no license10★ repo

    Manage git worktrees for parallel development with conflict prevention and wave-aware execution strategy. Use when creating feature branches, starting parallel work sessions, merging worktree PRs, or coordinating multiple Claude sessions.

  • Setup personal

    exasol-labs/exasol-agent-skills/plugins/exasol/skills/setup-personal Skill

    10★ repo

    Exasol skills for AI agents. Optimized for Claude Code and OpenAI Codex 🤖

  • Context engineering

    FluxonLab/Skillry/community/addyosmani-agent-skills/skills/context-engineering Skill

    no license10★ repo

    Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

  • Ai prompt engineering safety review

    FluxonLab/Skillry/community/github-awesome-copilot/skills/ai-prompt-engineering-safety-review Skill

    no license10★ repo

    Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.

  • Copilot sdk

    FluxonLab/Skillry/community/github-awesome-copilot/skills/copilot-sdk Skill

    no license10★ repo

    Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.