Recently Added
Fresh skills just added to the collection. Be the first to try them out!
gradle-sandbox-daemons
by rock3r
Use proactively before every Gradle invocation, and whenever a Gradle run behaves unexpectedly because of daemon, cache, filesystem, lock, permission, worktree, or sandbox-boundary behaviour. Isolate Gradle daemon registries by a stable execution boundary, retain reuse only within that boundary, and clean up selected homes at the end of their lifecycle.
ce-brainstorm
by EveryInc
'Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning. Also use when the user must scope work in territory they say they do not know ("I know nothing about X but need to...") or asks for a blindspot pass — mapping the decision surface before questions begin. Not for executing already-specified work — direct implementation, debugging, or code review where no product scope is left to decide. Not for a decisive verdict on whether to adopt or switch to a specific external technology, library, or platform — brainstorming scopes what to build, not whether to commit to an outside option.'
lfg
by EveryInc
"Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green. Use only when the user explicitly asks to build or ship something autonomously all the way to an open PR, or invokes lfg directly — it pushes and opens a PR without stopping. Not for in-the-loop work where the user reviews each step: use ce-plan to plan, ce-work to implement a plan, ce-debug to fix a bug, or ce-commit-push-pr to commit and open a PR for existing changes."
ce-plan
by EveryInc
"Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing."
ce-ideate
by EveryInc
"Generate and evaluate grounded ideas. Use when the user asks for ideas, improvements, surprising options, or AI-generated directions before choosing one to develop; use ce-brainstorm to refine the user's own idea."
graphkit
by levi-qiao
Run a long-horizon coding task as a small graph of agent nodes instead of one drifting loop. Generates an executor node (works against a single-source-of-truth ledger) and a clean-context supervisor node that watches from outside the executor's context — checkpoint-committing clean work and correcting drift through a one-way directives file. Use for multi-round tasks where an agent tends to scope-creep, fake "done", or quietly lower the bar. Nodes share no context, so the executor runs on a cheap/fast model while a strong model supervises.
ce-code-review
by EveryInc
"Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked for review; report-only by default, with explicit local apply available for user-directed fix workflows."
ce-doc-review
by EveryInc
Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.
ce-setup
by EveryInc
"Check Compound Engineering health and repo-local config."
ce-work
by EveryInc
Execute a plan or concrete work prompt end-to-end. Use when implementing from docs/plans, a spec path, or a clear build request; use ce-debug for open-ended bugs. Standalone use owns the shipping tail; outer orchestrators pass mode:return-to-caller [implementation_engine:<compact-json>] [implementation_run:<safe-id>] <plan path> for implementation, recovery, and local verification only.
ce-explain
by EveryInc
"Create a durable, visual teaching artifact — plus an optional check-in (predict-then-reveal for diffs, corrected exercises) that makes it stick — for something worth learning: a concept, a diff, an idea, or a window of your own recent work. Use when the user wants to be taught, wants a deep explainer, wants to understand a substantial change, or wants a work recap built for retention. Not for ordinary Q&A, brief 'why?' follow-ups, operational diagnosis, status updates, or a concise trade-off answer that belongs inline in chat. For learning, not repo docs or verdicts."
google-trends-scraper
by judicael-s
Use the free standalone Playwright Google Trends scraper for slow SEO ideation, seasonality checks, region insights, related-query discovery, and cron-based query monitoring from Hermes, Open Claw Agent, Claude Code, Codex, or similar agent runners.
unb-consultant
by freddyeleazar
Universal NotebookLM-Based Consultant. Create and query AI experts via NotebookLM (Gemini Notebook). Activates on explicit user request or when the agent detects a domain that could benefit from an expert.
xhs-mini-tool
by Janlaywss
小红书小工具开发规则与容器能力约束。当用户要求生成、开发、调试小红书小工具（vibecoding 作品）时使用此技能，确保产出代码严格符合小红书小工具容器的能力边界与限制。
domain-knowledge
by LujhCoconut
个人领域知识库路由 skill。支持四轮递进阅读 (R1-R4) + JSON 结构化元数据 + 技术倒排索引。 支持命令: 解析一下这篇论文 [URL] 润色一下 [语句] 评价一下这篇论文 了解一下 [主题] [方向]有什么最新进展 我读过 [论文名] 吗 哪些论文能直接用到工业代码里 哪些论文用了 [技术名] [主题] 应该怎么归档 更多见请求类型表。
lasso
by 52labs
Discover and act on your own identity when you are an agent running inside a lasso-managed terminal. Use when you need your own agent id, want to close yourself when your work is done (close_agent), fetch your own record (whoami / get_agent), or reference the workspace/repo/branch you were spawned into. Your pane id is exported as $HERDR_PANE_ID, so you never need to enumerate list_repos / list_agents to find yourself.
geist-nuxt
by abel-2333-org
geist-nuxt 是基于 Nuxt UI v4（Vue）的 Geist 风格 Source-first 设计系统。用于在本仓库或消费 Nuxt 项目中设计、实现、预览、安装、更新和评审页面、布局、表单、导航、反馈、覆盖层、主题、通用组件与 API Docs 组件；触发词包括 geist-nuxt、Geist、Nuxt UI、registry、copy-in、gallery、playground。视觉参考 Vercel Geist，组件方法论参考 Adobe Spectrum；不用 React。
repo-dojo
by alpardmason
Create and resume staged, persistent learning tracks for one existing local open-source project checkout. Use when the user invokes $repo-dojo, explicitly requests staged or durable project learning, requests numbered stages, status, refresh, or learning outputs, or ambiguously asks to learn a repository and needs the one-off-versus-workspace routing question. Do not use for one-off explanations, debugging, implementation, review, or contribution execution.
ce-babysit-pr
by EveryInc
"Babysits or watches an open GitHub PR until merge-ready, continuously reacting to review comments, CI failures, and routine base movement throughout the PR's life. Use when asked to 'babysit the PR', 'watch the PR', monitor, or keep an eye on a PR over time — not a one-shot request to resolve review comments or debug one CI failure (those are separate skills). GitHub only, including GitHub Enterprise."
whoop-copilot
by YunhaoDou
Read real WHOOP recovery/strain/sleep/workout data via the official WHOOP developer API (OAuth 2.0) and reason about it directly — training advice, recovery trends, sleep debt, whether today is a good day to push hard. Can also act on that reasoning by writing to macOS Calendar/Reminders (adjust today's training, block recovery time, log a note) via AppleScript. Triggered when the user asks about their WHOOP data, recovery score, strain, sleep, wants training/schedule advice grounded in it, or wants today's calendar/reminders adjusted based on it (e.g. "我今天recovery怎么样", "该不该练", "帮我看看这周睡眠趋势", "根据我的恢复情况调整今天安排").
lyskill
by ly9374-web
"根据聊天记录、笔记、描述、截图文本和其他来源材料，生成轻量的个人专属 Codex 技能。用于把关于某个人的材料通过 personabuilder.md、relationshipbuilder.md、memorybuilder.md、thinslicebuilder.md 转成 persona.md、relationship.md、memory.md、thinslice.md，以及可调用的 /{slug} 技能；适用于创建、配置、更新或验证人物侧写技能。"
dioxus-element-plug
by pauljohn21
Rust library for using Element Plus components with Dioxus 0.7 framework - 107+ components, pure Rust CSS generation, controlled component pattern, ClassBuilder utilities
read-paper
by LuoHaomin
精读并拆解学术论文（以 PDF 为主），自动适配论文类型（理论证明 / 实验方法 / 综述 / 系统）。把一篇或多篇论文整理成一套详细、可教学的分析条目（每个承重结果 / 方法 / 实验一个 markdown 文件）外加一份导航总览：含形式陈述或问题动机、大白话直觉、分步推导或实验解读、非平凡之处、以及它在全局里的角色；公式用规范 LaTeX，关系图用 mermaid、几何图用内联 SVG。当用户要求 读论文 / 解读 / 拆解 / 整理 / 分析 / 精读 / summarize / analyze / digest 一篇或多篇论文、PDF、或要把论文变成学习笔记时使用。
slidecraft
by zyuuryuu
Author polished PowerPoint (.pptx) decks from Markdown via SlideCraft's MCP server. Use when the user wants slides/a presentation built or edited from text, with a company template's fonts, colours and layouts preserved. You write Markdown + pick diagram types; SlideCraft's deterministic engine fills the template, keeps everything on-budget, and exports native (editable) PPTX shapes.