Loading…
Showing 5761–5790 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| tech-leadakunzai/agent-skillsLead implementation as a tech lead: slice the work, brief subagent implementers in isolated git worktrees, and accept the result in the primary session. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-audio-checkchenyuxiaojin/xiaochen-skills陈与小金的「成片音频体检 + 修法」。视频导出后、发布前,用 ffmpeg 把成片量一遍:响度(LUFS)、 真峰值 / 削波、左右声道平衡、BGM 与人声比例、片中静音、视频 / 音频码率,可选与母带对齐检查; 给出一张放行表 + 结论(可发 / 不可发)+ 对应病因和达芬奇修法(菜单级步骤),不可发时可用 ffmpeg 应急修音轨或重混人声+BGM(自动闪避)。铁律:数字说话,不凭听感、不凭字幕判断;修完必须复测。 触发方式:音频体检、查一下音频、检查码率和音频、这版能发吗、声音有没有问题、人声太小、BGM 太大、 声音偏一边、破音、混音、人声规避 / 闪避、视频导出了看看、/cyxj-audio-check。 凡是"成片导出了准备发"的场景都应先过本 skill,再走 cyxj-release-kit 出物料。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-data-reviewchenyuxiaojin/xiaochen-skills陈与小金的「抖音平台数据复盘诊断」。读小陈导出的抖音数据,跑一套证据驱动的诊断, 回答一个问题:靠收藏把长视频持续推、再转化涨粉——这条路,数据里跑没跑通。 赛道:非程序员用 Claude Code/Codex 做一切的知识视频。KPI 链 = 收藏 → 涨粉。 铁律:盘点没和用户确认前,禁止出任何诊断结论。每条结论必标【事实】【推断】【未知】,数据里没有的不许编。 触发方式:/cyxj-data-review、复盘我的数据、诊断我的平台数据、数据复盘、看看我最近数据、我的抖音数据怎么样、这条视频数据怎么样。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-obsidian-buildchenyuxiaojin/xiaochen-skills基于 Karpathy LLM Wiki 方法论,将 Obsidian 库编译成三层知识架构。 支持 Ingest(摄入)、Query(查询)、Lint(检查)三大操作。 触发词:整理 Obsidian、编译知识库、摄入笔记、查知识库、健康度检查。 当用户提到 Obsidian 整理、笔记关联、知识管理、Wiki 维护时,使用此 skill。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-roundtablechenyuxiaojin/xiaochen-skills圆桌会议 skill。当你想不明白一件事时,召集 6 个独立 subagent(当前最强对话模型档) 扮演 6 个有立场的角色(苏格拉底/严苛同行/带偏见投资人/历史学家/5 年后后悔的你/同盟者), 从 6 个不会互相迁就的视角同时给出意见。主位坐你,AI 不替你拍板。 会议结束自动落地到 Obsidian 决策记录。 触发方式:/圆桌、"开个圆桌"、"开圆桌"、"圆桌一下"。 Roundtable consilium. Convenes 6 independent top-tier-model subagents with adversarial perspectives to help you decide. You sit at the head. AI does not decide for you. Trigger: /roundtable, "open the roundtable", "/圆桌" | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-subfixchenyuxiaojin/xiaochen-skills达芬奇字幕修正工具:SRT 清理、Sonnet 语义初修、Opus 审查把关。 触发词:/字幕修正、修正字幕、字幕错别字、SRT 修正、达芬奇字幕。 当用户提供 SRT 文件路径需要修正时使用此 skill。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-contentchenyuxiaojin/xiaochen-skills陈与小金的「知识视频内容诊断」。把一个已定选题,诊断成观众看完想收藏的 3 分钟以上知识视频。 不是短视频带货,是 3 分钟+ 知识口播/演示。 触发方式:/cyxj-content、内容诊断、这条视频内容怎么做、帮我看看这条稿、视频内容怎么做更好。 不做已发布视频的数据复盘(那是 cyxj-data-review 的活)。 边界:本 skill 专供陈与小金账号(3 分钟+ 知识视频);超出该范围的诊断请求按普通对话处理。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-hookchenyuxiaojin/xiaochen-skills陈与小金的「知识视频开头/钩子」优化。诊断 3 分钟以上知识视频的开头问题,并生成优化方案。 不是 15 秒短视频带货,是 3 分钟+ 知识口播——钩子负责留人,但完播靠整条价值密度;开头不是骗点击,是「承诺一个值得看完的获得感」。 触发方式:/cyxj-hook、优化我的视频开头、知识视频开头怎么写、帮我看开头、开头钩子。 边界:本 skill 专供陈与小金账号(3 分钟+ 知识视频);超出该范围的开头优化请求按普通对话处理。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-youtube-topicschenyuxiaojin/xiaochen-skillsYouTube 选题发现 + 判断。搜索 "Claude Code" 相关最近 48 小时新视频, 去重、按话题聚类、做硬信号 + 字幕内容分析,输出带 verdict(值得做/观望/跟风/跳过)+ 理由 + 差异化切口建议的选题报告。写入 Obsidian 选题库。 触发方式:「YouTube 选题」「找 YouTube 选题」「YouTube 最近有什么」「帮我找找最近的新选题」「跑一下选题发现」「有什么新视频」 边界:只做 YouTube 新视频的选题发现与判断;泛选题、短视频 IP 人群选题、文案式出选题不归本 skill。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| cyxj-yt-creatorchenyuxiaojin/xiaochen-skillsApify 博主用法研究。用 Apify 搜索 YouTube 上某个工具/话题的博主视频, 抓取重点视频字幕,按发布日期整理 YouTube 链接、频道、播放量、时长和字幕观察, 结合陈与小金的「非程序员,用 Claude Code 做一切」定位,写入 Obsidian 待发布稿。 触发方式:「查博主怎么用」「用 Apify 搜 YouTube」「写到待发布」「研究这个工具的 YouTube 视频」「抓字幕分析博主用法」。 | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| bmad-cis-agent-brainstorming-coacharmelhbobdad/oh-my-skillsElite brainstorming specialist for facilitated ideation sessions. Use when the user asks to talk to Carson or requests the Brainstorming Specialist. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| bmad-cis-agent-creative-problem-solverarmelhbobdad/oh-my-skillsMaster problem solver for systematic problem-solving methodologies. Use when the user asks to talk to Dr. Quinn or requests the Master Problem Solver. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| bmad-cis-agent-innovation-strategistarmelhbobdad/oh-my-skillsDisruptive innovation oracle for business model innovation and strategic disruption. Use when the user asks to talk to Victor or requests the Disruptive Innovation Oracle. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| bmad-cis-agent-storytellerarmelhbobdad/oh-my-skillsMaster storyteller for compelling narratives using proven frameworks. Use when the user asks to talk to Sophia or requests the Master Storyteller. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| chengzicv-case-factorychengzicv/chengzicv-career-skills为指定岗位与职级生成独立披露的虚拟简历及岗位入门。虚拟简历的写法、结构、个人优势、篇幅、标点和事实纪律全部沿用 chengzicv-resume;本 Skill 只负责虚拟案例设定、岗位研究、岗位入门与批次生产。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| chengzicv-job-greetingchengzicv/chengzicv-career-skills为 BOSS 直聘、猎聘、拉勾、脉脉等招聘平台生成初次打招呼、回复推进、岗位澄清、已读不回跟进和被拒反馈询问,也可基于已确认履历生成候选人专属投递侧指南。正式邮件求职信不使用本 Skill。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| herdrmodem-dev/ossrulesControl Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires HERDR_ENV=1. | Stars: 66 | Updated | Claude CodeCodex | Verified | Install |
| recursive-modetry-works/role-modelRepository workflow orchestration skill for staged implementation, locked artifacts, late-phase receipts, and durable memory maintenance. Use when executing recursive-mode runs, resuming a run, locking a phase, or verifying locks. | Stars: 119 | Updated | Claude CodeCodex | Unverified | Install |
| agent-evaloberconcejo/VS-CODEHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| codex-issue-wavesddnetters/homelab-agent-skillsRun a batch of GitHub issues through codex exec in isolated git worktrees as parallel autonomous PRs, then manage the review and correction waves until merge. Use when the user gives a list of issue numbers (≥ 2) and asks to "spawn codex" / "dispatch codex" / "have codex work on" / "manage the PRs" / "process feedback" / "get them merged" for those issues, or when the user asks for multi-issue parallel delegation to codex. Not for single-issue wave-driven delegation (use codex-task-waves), single-issue one-shot dispatch (use invoking-codex-exec), or implementation without delegation (use /pr or direct implementation). | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| codex-task-wavesddnetters/homelab-agent-skillsUse when the user says "have codex fix this" / "have codex implement this" / "let codex handle this" / "give this to codex" / "delegate this to codex" for a single task with context already in scope (a Jira ticket, GitHub issue, file diff, bug, or described change). Plans the work, splits it into reviewable waves, dispatches codex per wave with review and correction between waves before opening a PR. Not for multi-issue parallel batches (use codex-issue-waves) or one-shot codex runs without planning (use invoking-codex-exec). | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| invoking-codex-execddnetters/homelab-agent-skillsUse when delegating a single coding task to `codex exec` ("hand off to codex", "run codex on this", "dispatch codex on this ticket", any one-shot invocation). Covers flags, sandbox traps, monitoring, and recovery. Not for multi-issue parallel batches — use codex-issue-waves for those. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| creating-orchestration-packsjaktestowac/awesome-copilot-for-testersCreates agent orchestration packs: cooperating `.agent.md` files with an orchestrator, subagents, matched handoffs, minimal tool grants, and a shared handoff packet contract. Use when one agent role is too broad for a job, when a workflow needs explore, plan, implement, review, and verify as separate roles, or when a pack fails the orchestration lint because a handoff target does not resolve. | Stars: 122 | Updated | Claude CodeCodex | Verified | Install |
| creating-pluginsjaktestowac/awesome-copilot-for-testersPackages repository skills as installable Copilot plugins: marketplace registration, `plugin.json` manifests, generated skill copies, and the sync check CI enforces. Use when bundling one or more skills for installation, when adding a plugin to the marketplace, or when `npm run lint` reports that a plugin copy has drifted from its source skill. | Stars: 122 | Updated | Claude CodeCodex | Verified | Install |
| matlab-analyze-reliabilityzrwangems/dsh-zrwang-pluginUse this skill when fitting accelerated life models, computing mean time to failure (MTTF), B10 life and similar quantities, fitting life distributions like Weibull for reliability analysis, comparing distribution fits, computing confidence intervals on reliability quantities with bootstrapping, performing lifetime prediction, computing failure rates, plotting Kaplan-Meier curves, computing survival functions, or doing reliability analysis. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| roadrunner-corezrwangems/dsh-zrwang-pluginFoundation skill for all RoadRunner workflows: MATLAB path setup, connection, project/scene/scenario lifecycle, world settings, handle management, status, and close. Use when connecting to RoadRunner, managing projects/scenes/scenarios, setting world origin, checking status, closing RoadRunner, or when any downstream RoadRunner skill needs initialization. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| harness-toolsleek/agent-skillsThe tool each agent harness (Claude Code, Codex, Grok, agy) uses to start, follow up with, or stop a sub-agent, and to ask the user a structured question. Use when a skill names one of these moves and points here, or when you are not sure which tool your harness has for it. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| implement-specleek/agent-skillsBuild a whole spec fast: parallel implementer subagents work the ticket frontier, each in its own worktree, merging onto one integration branch; then one review, one verification pass, and one PR or a stack of PRs. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| panelleek/agent-skillsConvene a panel of agent CLIs (grok, claude, codex, agy) on a prompt or a code review, then report one consensus grouped by how much they agree. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| resolve-review-commentsleek/agent-skillsFix or rebut every review comment on a pull request, human or AI-review bot (Codex, Copilot, Gemini), then reply and resolve each thread. Use when the user wants a PR's review comments addressed, answered, or cleared. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |