Showing 2311–2340 of 15647 skills
Full release lifecycle for Rossoctl — alpha, RC iteration loop, GA, and patch releases with multi-repo coordination
rossoctl/rossoctl
Replicate the 7 programmatic SEO plays that took Zapier, Clay, Composio, Gamma, Mintlify, HeyGen and HubSpot to
irinabuht12-oss/marketing-skills
Recreate a reference video (a link or file) as the user's own film with OpenMotion: rebuild it as an editable OpenMotion project and hand it over open in the editor, keeping the original content or swapping in the user's copy, brand and assets. This includes small edits to the user's own finished video when no editable project for it exists. "Make one like this" and "I want this feel" both count as recreation. In a workspace with the user's product material, a bare link alone means "make one like this for us". References that also contain portraits, product photography, live-action or AI footage, narration or music are in scope: those parts use configured media generation while the structure stays editable. Not for only analysing or discussing a video. Use openmotion-director when the reference is only inspiration for an original film, openmotion-template-to-video for an existing template, openmotion-production for edits to an existing editable OpenMotion project, and openmotion-video-to-template for a reusable template package.
nexu-io/openmotion
Run IV, DiD, and RDD analyses in R with proper diagnostics
brycewang-stanford/Auto-Empirical-Research-Skills
Generate publication-ready regression tables in LaTeX.
brycewang-stanford/Auto-Empirical-Research-Skills
Meta-analysis frameworks and methods for mediation studies
brycewang-stanford/Auto-Empirical-Research-Skills
Effective communication strategies for statistical methods
brycewang-stanford/Auto-Empirical-Research-Skills
Structure responses to referee reports for R&R submissions
brycewang-stanford/Auto-Empirical-Research-Skills
把文章或视频一键做成中文视觉内容的总入口:按推荐组合把 10 个可单独使用的能力串起来——文章抓取、视频转文字、改写(总结)、全文翻译、长图、卡片(小红书 3:4 / 4:5 / 1:1 / 9:16)、公众号排版、口播视频、白板论证、漫画。常用组合:原文→改写→长图(默认)、原文→改写→小红书卡片、原文→公众号排版、原文→总结→公众号、外文→翻译→公众号、原文长图 / 原文卡片(一字不改)、视频→逐字稿→改写→长图或卡片、一稿多发(长图 + 小红书 + 公众号)、文章→口播视频。输入:X/Twitter 长文与线程、网页、微信公众号、本地 Markdown、粘贴的正文;抖音、YouTube、B 站链接、本地视频/音频、.srt/.vtt。12 套主推主题,不指定时按内容选。Use when the user gives an article, URL, long post, video link or file and wants it turned into 总结图, 长图, 知识卡片, 小红书图文, 公众号排版, 口播视频, 原文排版, 白板, 漫画 — or wants several of them, or names a combo (一键、组合、全套、一稿多发) — e.g. "把这篇文章做成图/小红书/公众号/视频", "把这个抖音视频做成小红书", "翻译成中文发公众号".
threerocks/article2media
卡片:固定比例的图文卡片组——小红书 3:4(1080×1440)、Instagram 4:5、方图 1:1、竖屏 9:16,附总览图和发帖文案。两种输入:改写稿 content.json → 总结卡片(封面 + 每节一卡 + 清单 + 要点总结,12 套主推主题);文章 article.md(原文、译文、逐字稿)→ 原文卡片(整篇按顺序分页成卡片,一字不改,逐块校验)。可以单独用,也可以接在抓取、改写、翻译后面。Use when the user wants 小红书图文, 轮播卡片, 知识卡片, 3:4 / 4:5 / 1:1 / 9:16 cards, Instagram carousel, 朋友圈方图, or 原文卡片 / 全文卡片 / 把全文做成小红书 — from an article or an existing content.json.
threerocks/article2media
长图:两种输入,两种长图。改写稿 content.json → 1–4 张总结长图(手机宽度单栏,每节配图表和数据面板,附执行清单;--wide 出 1200 宽双栏杂志版;12 套主推主题);文章 article.md(原文、译文、逐字稿)→ 一字不改的原文长图(逐块读回校验,超长自动分张)。可以单独用(已有 content.json 或文章),也可以接在抓取、改写、翻译后面。Use when the user wants a 长图, 总结图, 杂志长图, infographic pages, or 原文长图 / 全文长图 / 原文排版 / 一字不改 / -f from an article or an existing content.json; also to re-render a content.json in another theme (换主题、换风格).
threerocks/article2media
公众号排版:把一篇文章(Markdown)排成能直接粘贴进公众号编辑器的图文——内联样式、图片内嵌、12 套主推主题配色,附 2.35:1 头图、1:1 封面和发布信息(标题、摘要、步骤);正文一字不改,逐块读回校验。只接受文章:原文(article.md)、译文(article.zh.md)或改写稿导出的文章(rewrite.md,即"总结后发公众号")。可以单独用,也可以接在抓取、翻译、改写后面。Use when the user wants 公众号排版, 微信公众号文章排版, 推文排版, gzh, mp.weixin formatting, "排成公众号/发公众号", or to paste a Markdown article into the WeChat editor.
threerocks/article2media
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
activeloopai/hivemind
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
activeloopai/hivemind
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
activeloopai/hivemind
Create, track and update team goals in Hivemind via the `hivemind` CLI. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
activeloopai/hivemind
Create, track, and read team goals via Hivemind from openclaw. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
activeloopai/hivemind
Friendly onboarding when users ask about capabilities
parcadei/Continuous-Claude-v3
Use when writing a PR body.
aws/graph-explorer
Use when writing a pull request body, or before `gh pr create` or `gh pr edit --body`.
kryptamine/herdr-auto-title
用 PAS、AIDA、BAB、STAR、SLAY 等经典框架将主题结构化为社媒帖子。 200-250 字、20 行以内、移动端友好排版。适用于公众号、知乎、微博、LinkedIn 等长文帖子。 当用户说"用 PAS 写"、"AIDA 框架"、"结构化帖子"、"套框架写"时使用。 和 social-content 的区别:post-formatter 严格套用营销框架,social-content 偏自由写作。
ZJU-REAL/Easel
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
michael-denyer/pstack-claude
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
michael-denyer/pstack-claude
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
michael-denyer/pstack-claude
Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work, and before telling the user that something was never recorded.
michael-denyer/pstack-claude
Create or redesign self-contained single-file HTML artifacts with a visual direction shaped by the user's brief, project, and subject. Use when HTML is the deliverable for a report, explainer, landing page, presentation, tool, mixed artifact, or broad request. This is the collection's only implicit router. Route clear wireframe, prototype, mockup, plan, or diagram requests to the matching direct-invocation specialist when available. Do not use for ordinary application implementation when a standalone HTML file is not the deliverable.
plannotator/effective-html
Publish and reload Kumo models through the Snowflake registry, reconstruct compatible scoring inputs, and retain or retrieve run diagnostics and output files through a Snowflake stage. Use for saved-model scoring and artifact retention without retraining by default.
NVIDIA/skills
Configure a Kumo model plan for a user-defined task, including encoders, run mode, bounded experiments, sampling, optimization, architecture, metrics and refits. Preserve target and evaluation constraints and use existing diagnostics for comparisons.
NVIDIA/skills
Check the local ApexYard environment before setup or when hooks fail.
me2resh/apexyard
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
backnotprop/pstack