Showing 5881–5910 of 15647 skills
Generate a weekly X (Twitter) content plan from a theme, audience, and content pillars. Produces per-day recommendations (single tweet vs thread, X hook formula, angle, posting time, primary goal), a single-to-thread mix, daily reply and quote-tweet targets, and a goal-mix balance check across replies, reposts, likes, and bookmarks. Use when the user wants to plan a week of X content instead of ad-hoc posting. Not for drafting one tweet (use x-post-writer) or one thread (use x-thread-builder).
sergebulaev/x-skills
Reverse-engineer the hook from a viral X (Twitter) tweet or thread URL. Identifies which of the 10 canonical 2026 X formulas it uses (one-liner contrarian, data-point, build-in-public, quote-tweet, mini-list, relatable cold-open, listicle-thread, story thread, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal. Use to learn from a tweet you admire. Not for writing your own (use x-post-writer or x-thread-builder).
sergebulaev/x-skills
Draft a reply or a value-add quote tweet for a specific X (Twitter) tweet from its URL. Use to reply in a thread, answer a creator, or quote-tweet with added value. Parses the tweet URL, reads pasted context, decides reply vs quote tweet, and drafts 1-3 variants in your voice. X has no LinkedIn-style 2-level thread flattening, so a reply is just a tweet. Publora has no reply endpoint, so the draft is returned as a copy-paste block to post yourself. Not for top-level posts (use x-post-writer).
sergebulaev/x-skills
Add any of 51 video effects to a talking-head video (orbit, spotlight, glass widgets, timeline, checklist, headline wall, comment box, phone fan, liquid glass graph, match-cut, iPhone toggles, LED sign, over-the-shoulder zoom, iMessage pop-ups, place-in-grid and more). Effects track the speaker's face and can sit behind their head. Use when the user types /effects, names one of the effects, or asks to add an effect, zoom, grade, sticker or animation to their video.
Vibha-Ramprakash/claude-video-effects
Push a branch and open a PR with pre-flight checks
zmerlynn/manifold-csg
Read or maintain MotherDuck Guides for business definitions, join rules, and reusable warehouse conventions.
motherduckdb/agent-skills
Index of the Convex Architecture Documents (CADs), the normative specifications for Convex. Use to find which CAD governs a subsystem before changing protocol, encoding, consensus or economic behaviour.
Convex-Dev/convex
CAD3 encoding format — cells, embedded vs branch references, value IDs, validity rules. Use when working on encoders, decoders, serialisation, hashing or anything that reads or writes cell encodings.
Convex-Dev/convex
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
oedokumaci/gale-shapley-algorithm
Archive multiple completed changes at once. Use when archiving several parallel changes.
oedokumaci/gale-shapley-algorithm
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
oedokumaci/gale-shapley-algorithm
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
oedokumaci/gale-shapley-algorithm
Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.
oedokumaci/gale-shapley-algorithm
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
oedokumaci/gale-shapley-algorithm
自动验证 veRL + Megatron-core + vLLM 训推权重转换一致性(UWC)的 5 项检查:Bridge P0/P2、传输 P2_sender/P5、data_ptr 覆盖、G0/G1 前向、dummy vs safetensors 差分。注入采集钩子、采集权重/指针/日志,生成 report.md / report.html / report.json。当用户要验证 RL 训练与推理权重同步、排查 rollout 输出乱码/漏同步、或复现《RL 权重一致性验证》文档时使用。
kali20gakki/msAgent
为算子适配 msOpProf 范围级重放,在 C++ 或 PyTorch 调用入口添加 MSTX 范围及构建依赖,按需自动生成 custom-input 的 timeline_merge_config。适用于普通算子,也适用于多卡通算融合算子。用于接入 MSTX、生成 range 重放代码或补丁、配置多卡流水合并;默认直接修改原工程并仅生成代码,可选择编译验证及采集 Default 基础指标。不限定工程框架,需核验实际后端、芯片及工具支持范围。
kali20gakki/msAgent
Analyzes and optimizes costs for cloud data platforms
a5c-ai/babysitter
Enriches data catalog entries with automated metadata
a5c-ai/babysitter
Selects and configures optimal incremental model strategies
a5c-ai/babysitter
Use when 统计资产/做资产表/分析人物/场景/道具。产出暖金主题HTML资产分析报告。
hashgraph-online/awesome-codex-plugins
Product visuals must show the real product with real data. Use when building landing pages, hero sections, screenshots or demo panels.
dembrandt/dembrandt-skills
Builds or fixes a stylised-realism rendered image on a physically based renderer, and decides where a change to the look belongs, when grass reads too dark, a frame looks flat or grey, a colour cast covers everything, the distance is too clear or too milky, or a new material does not sit with the rest. Keeps materials at physically plausible values, puts the style in three places only (the content chosen, global lighting parameters per weather and time of day, post-processing), works in the order content, materials, lighting, atmosphere, exposure, tone mapping, colour grading, and sends a wrong look to the earliest layer that can cause it. Use with three.js WebGPU renderers, or any physically based renderer, whenever a material, the lighting, the haze or fog, the exposure, the tone mapping or the colour grade is changed to improve or fix the look.
HuberyLL/ponlai
Finds the values of a physically based renderer's lighting, atmosphere and post-processing parameters (exposure, tone mapping, sun and sky light, ambient balance, haze and fog, white balance, colour grading) that bring a rendered frame close to the reader's own reference images, when the render's lighting, colour or fog differs from them. Gets still, lossless, unfiltered reference images with their sun position and time of day recorded, diagnoses where each gap comes from before changing anything, measures by region class with each measurement's view geometry, works upstream first, checks a function's form before fitting its parameters, fits many points numerically after a short trial run, stops when a fit does not converge, and judges good enough on the whole frame. Use with three.js WebGPU renderers, or any renderer with tunable look parameters, whenever a look is matched to reference images or photographs by changing lighting, atmosphere or post-processing values.
HuberyLL/ponlai
根据题目、建模分析和真实代码结果生成完整 Word 数学建模论文,用户显式要求时同时生成 LaTeX 论文。
XiaoMaColtAI/math-modeling-skill
Rossoctl issue templates - bug reports, feature requests, epics
rossoctl/rossoctl
Autonomously work a `.pm` workstream to completion — pick the next pending milestone, implement every task end to end, /ship it, then move to the next until none remain. Use when the user asks to "loop", drain, or work through a whole workstream's backlog (e.g. `/loop-worker w1`). Sequential, not interval-based; for a timed poll use /loop.
bex-co/bex-security
端到端分析两侧 msprobe PyTorch statistics 原始 dump 数据(dump.json + stack.json + construct.json)与精度问题现象(loss / grad norm / 输出不一致等),按「确定性预处理 → 多视角候选发现 → 汇总排序 → 分级定向验证 → 报告校验」流程识别可疑候选节点并构建到目标异常现象的因果链,交付主分析报告与结构化证据记录。当用户提供两侧 dump 目录并需要定位训练精度问题根因时使用。侧别判定:用户指定 target(待分析侧)/ golden(参考侧)优先;未指定时按目录名与数据内容推断(npu/gpu 等仅为软线索,不作硬性假设);不可靠时询问用户。
kali20gakki/msAgent
在用户的 PyTorch 动态图(eager)训练/推理代码或 vLLM 推理服务(vllm-ascend、社区原生 vLLM eager)中使能 msProbe 精度调试工具的 PrecisionDebugger 数据采集功能,检查 msProbe 安装与环境、确认纯 eager 场景、与用户逐项确认采集配置、插入打点代码(vllm-ascend 场景免插桩,经 --additional-config 传配置;其余场景先展示 diff 经确认后修改)、验证并交付开启/关闭说明。用于“帮我使能 dump / 给训练代码接入精度数据采集”这类请求;不负责精度问题定位分析。
kali20gakki/msAgent
当首次使用 msmodeling optix 的用户需要根据硬件、模型、负载和优化目标推荐 MindIE/vLLM 寻优参数、搜索范围、benchmark 侧字段或 config.toml 片段时使用。
kali20gakki/msAgent
昇腾AscendC算子调试工具(msDebug)技能,含两大流程:①上板调试——算子加 -g -O0 编译后由 msdebug 拉起,支持断点、单步、变量/内存打印、核切换、寄存器读取;②coredump解析——用户指定 core 文件路径后,msdebug 加载解析挂掉代码行/异常调用栈/现场变量。触发关键词:msdebug、算子调试、上板调试、断点、单步调试、打印变量、读内存、核切换、寄存器、coredump、core文件、调用栈、崩溃解析
kali20gakki/msAgent