AGENT SKILLS · MISSION KIT
Useful agent skills ranked by real adoption
Browse verified skills from public repositories. Compare what each skill does, package contents, install activity, and source evidence before adding it to your agent.
- CATALOG SCOPE
- VERIFIED
- skills
- 22,822
- repositories
- 3519
- last synced
- Nov 2, 2026
vincenzoimpmanage-submission
Use when submitting a paper, recording decisions and reviews, drafting rebuttals and response letters, applying revisions, or preparing the camera-ready version.
- 1h installs
- 1
- GitHub stars
- 3
- Updated
- Aug 25
vincenzoimppackage-artifacts
Use when packaging the artifacts of a paper for submission — assembling everything promised in the manuscript plus the venue's badge and artifact-evaluation requirements.
- 1h installs
- 1
- GitHub stars
- 3
- Updated
- Aug 25
vincenzoimpwrite-paper
Use when starting or writing a paper for a venue — venue selection, framing, contribution selection, and the full manuscript on the venue template.
- 1h installs
- 1
- GitHub stars
- 3
- Updated
- Aug 25
vincenzoimpwrite-survey
Use when writing the project survey from the digested SOTA or updating it after the SOTA changed — grouping design, gaps and research directions, and coverage maintenance.
- 1h installs
- 1
- GitHub stars
- 3
- Updated
- Aug 25
qianwen-aiyunqi-agent-discovery
- 云栖大会（Yunqi）发现与规划 Skill。查询议程与展览信息，根据 Agent 目标推荐、比较会议和展商/展台，基于会刊回答大会主旨、亮点、展馆等介绍性问题，基于参会指南回答交通、住宿、餐饮、门票等参会服务问题。 适用于「查询大会议程」「查询展览信息」「推荐会议」「比较展商/展台」「规划参会路线」「大会亮点」「大会介绍」「交通/住宿/餐饮」「门票/签到」等场景。 数据源为 qianwen CLI 的 yunqi 子命令（接口获取优先，静态会刊与参会指南作为补充），公开只读，不产生任何写操作。
- 1h installs
- 1
- GitHub stars
- 2
- Updated
- Sep 17
apidojo-ioanalyzing-competitor-twitter-profile-content
Extracts and analyzes tweet history from competitor or brand Twitter profiles using apidojo's Twitter Profile Scraper on Apify. Triggers when the user asks to: get all tweets from a competitor's Twitter account, analyze what a company posts on Twitter, audit a brand's tweet history, track what topics a competitor covers on X, compare Twitter content strategy between brands, extract posts from a company's Twitter timeline, or monitor a competitor's messaging and announcements on Twitter. Returns
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- May 13
happyplumaudit-loop
当用户说「审计循环」「循环审计」「audit loop」「温链复审」「审查修复循环」，或要求「审查→修复→再审查直到子代理审计通过」的迭代验证流程时必须加载。编排只读审查子代理对指定对象（提交区间、文件、实现或计划）做循环审计：审查→修复→温链续审→再修复，直至审查子代理明确无误通过。用户点名了子代理（如 oracle、metis、momus 等）就直接用；只说「进行审计循环」未点名时先从最近对话推断并向用户确认；绝不把负责执行 task 的子代理当作审计者。
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
happyplumdeep-thinking
当用户使用 ult、启用 ulw，或明确要求"深度思考""帮忙思考""帮我思考""超级思考""深度分析"时加载。默认常驻普通模式；本 skill 仅在上述触发条件满足时激活，覆盖简洁优先原则。
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
happyplumlinearize-commits
线性化整理 git 提交历史——合并细碎的修正提交、控制颗粒度以支持按提交粒度回退、保留原始开发者的作者归属、不跳过项目 git hooks、把每条提交信息规范为 type(scope): 中文描述；整理后可选并入指定分支（未指定时默认为主干）。当用户要求「合并到主干」「合并到某个分支」「线性化合并」「rebase 到 main/master」「整理/压缩/squash 提交历史」「分支合并前清理历史」时必须加载；纯整理不带合并时同样加载——如「整理一下这个分支的提交」「重写某个 hash 之后的历史」「squash 最近几个提交」「整理已经推送的分支（可 force-push）」；即使用户只说「把这个分支合到 main / 合回主干」也应加载，因为历史整理是合并前的必要步骤。普通单次提交、只读 log 查询不触发。
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
happyplumlong-running-process
当确认当前运行环境是 Windows + PowerShell，且需要启动或排查长运行进程、等待端口/health endpoint、按 RunId 停止残留、或执行可能超时的构建命令时使用。
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
happyplumopencode-subagent-log-triage
当 OpenCode 子代理、子会话、工具调用、后台任务或 Playwright 浏览器检查看起来卡住时使用——尤其是用户提供 session ID、子会话标题、工具描述、worktree 路径，或要求在决定是否终止进程前检查 OpenCode 本地日志/会话数据时。也用于执行会话审计与追溯：某次开发「费时费钱」、统计成本与 token、重建父子会话树、盘点某计划派了哪些子代理、找出最贵/最慢的会话时。
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
happyplumvue-standards
lzy 的 Vue 工程规范（自包含 canon，蒸馏自 vue-vite-cli 法典模板与 group-web 生产实态，不依赖通用版 skill）。当用户要求按其 Vue 工程习惯搭建、评审或改造 Vue 项目，把个人规范快速转成项目 AGENTS.md，或当用户要求复用 DMTable/TableLayout/请求层/表单协议等既有范式时使用。以手动/显式加载为主。
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
happyplumweekly-report-generator
- Generate a Chinese weekly work report from Git history and verified project evidence. Use this skill whenever the user asks for 周报、周工作总结、本周工作、提交汇报、迭代总结、工作量汇报, or wants to turn their commits into a leader-readable report. The default period is last Sunday through today, not a completed Sunday-to-Sunday week; if today is Monday–Saturday, do not snap the end date back to last Sunday. If the user gives an explicit date range, always use that range instead. Write professional written Chinese: not c
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
terrylicaclickhouse-pydantic-config
Generate DBeaver config from Pydantic ClickHouse models. TRIGGERS - DBeaver config, ClickHouse connection, database client config.
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
terrylicacrucible-investigation-methodology
actively investigating a hypothesis — running a sweep, dispatching multi-agent analysis, designing serial adversarial gates,
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
terrylicacrucible-navigator
starting a new research campaign, entering a new Claude Code session on a research repo, or when unsure which methodology.
- 1h installs
- 1
- GitHub stars
- 1
- Updated
- Oct 8
lvtd-llcai-steering-files
Use when creating, auditing, or updating AI steering files such as AGENTS.md, CLAUDE.md, GEMINI.md, .github/copilot-instructions.md, .cursor/rules/.mdc, PRODUCT.md, ANALYTICS.md, TECH.md, STRUCTURE.md, VISION.md, or DESIGN.md in a software repository.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 24
lzhang10loop-me
Grill me about specs for the workflows I want to build, within this workspace.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 3
lzhang10setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 3
media-iomediaio-generate
Generate images and videos through the currently installed Media.io CLI. Use for text-to-image, image-to-image, text-to-video, image-to-video, reference-to-video and published workflows. Select the model from the bundled static catalog (references/model-catalog.md), which is generated from the production registry; only fall back to mediaio model list on the triggers listed in the discovery guardrail. Copy every jobtype byte for byte — some contain a literal space, and display names often do not
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Sep 22
securityskillsssrf-hunting
Find and exploit Server-Side Request Forgery across URL-fetching features, including cloud metadata bypasses and blind SSRF techniques. Use during web assessments and bug bounty hunting.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Aug 26
spacezephyrmap-motion
地图动效视频：用高德地图（真实路线、行政区边界、标准/卫星瓦片底图）做旅行与解说视频里的地图动画，出竖屏/横屏 MP4 和 GIF。十一种镜头：地球俯冲定位（从地球放大到某地）、Vlog「我在这里」瞄准锁定＋坐标卡、落点标注、公园/景区/校园地块轮廓描边与绕行、路线描线（驾车/步行/骑行/GPX，车随线走、里程表滚动、镜头跟车、海拔剖面）、飞线航线、行政区描边高亮、一对多辐射飞线、多站旅程（路线+邮戳+照片+返程）、全景收束、标题卡；十二种样式（高德标准、高德暗色、高德灰、高德复古、卫星、暗色科技、极简白、水彩手账、复古纸、赛博霓虹、国风水墨、工程蓝图）。当用户说「地图动画」「地图动效」「轨迹动画」「出行轨迹视频」「旅行路线动图」「从地球放大到」「定位到某地」「飞线」「航线动画」「行政区高亮」「门店分布动画」「Vlog 地图片头」「标出某个公园/景点」「徒步/登山/骑行轨迹」「海拔剖面」「我在这里坐标卡」，或要把行程、GPX、照片位置做成地图视频时使用。
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 7
stshowask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 8
stshowcodebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
- 1h installs
- 1
- GitHub stars
- 0
- Updated
- Oct 8