AI & ML

jakoerror Skill

Use when the user asks to download, fetch, or parse an academic paper into readable markdown, or references a paper by short-name/code-dir that isn't yet under ./papers/. Covers arXiv, HuggingFace Papers, OpenReview, ACL/CVF, and DOI sources; uses mineru for PDF→markdown.

yz5e Bundle

Write or refine prompts specifically for GPT-5.5, including Codex CLI runs and Responses API agentic workflows. Use when Claude or another harness needs a high-performance OpenAI-style GPT-5.5 prompt with reasoning.effort, text.verbosity, XML block contracts, persistence, decision rules, completeness contracts, verification loops, tool-use parallelism, and outcome-first acceptance criteria.

yz5e Bundle

Write or refine prompts specifically for Claude Opus 4.7, especially for long-horizon coding, repo implementation, debugging, migrations, tool use, and validation-heavy execution. Use when Codex needs a high-performance Anthropic-style Opus 4.7 prompt with adaptive-thinking, effort, tool-use, XML structure, persistence, concrete acceptance criteria, and local verification guidance.

techiejd Bundle

Use when the user invokes /steelman or when a high-stakes decision is detected in context (architecture choices, technology selections, business model decisions, strategic pivots). Not for routine planning or implementation tasks.

bekhruztursunboev Skill

Professional web design skill for AI coding agents. Overrides LLM default UI biases. Non-generic, minimalist, animated frontends. Framework-agnostic. Web / SaaS / Product / Portfolio / Editorial.

zhuguang-zfg Bundle

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, debugging, or refactoring code to avoid hidden assumptions, overengineering, broad unrelated edits, and vague success criteria. Trigger this skill for implementation planning, code review, bug fixes, and any task where simple, surgical, verifiable changes matter.

tomasblatak Skill

Creates and launches Leadspicker robots (automations) that scrape LinkedIn data and deposit leads into projects, through the Leadspicker MCP server. Supports 4 robot types: scraping likers and commenters from specific LinkedIn posts, monitoring new posts by LinkedIn profiles or companies, searching LinkedIn posts by keywords, and LinkedIn people search via Sales Navigator URLs, normal LinkedIn people search, or event attendees. Use whenever the user wants to create, launch, or start a robot or automation in Leadspicker — in any language. Triggers on scraping LinkedIn posts, extracting post likers or commenters, monitoring posts from profiles or companies, searching LinkedIn content by keywords or topics, LinkedIn people search, Sales Navigator search, event attendees scraping, or pasting LinkedIn URLs with a request to scrape, monitor, or search. Triggers on direct robot type references: li_posts_extract, li_posts_monitor, li_posts_feed, salesnav_monitor.

tomasblatak Skill

Generates short personalization hooks, icebreakers, salutations, and vocatives for cold email campaigns in Leadspicker projects through the Leadspicker MCP server, using GPT-4o-Mini behind the scenes. Use whenever the user wants to create personalized opening lines, hooks, greetings, salutations, vocative forms, or any short text fragment for outreach — for example "create a website hook", "write an icebreaker from LinkedIn posts", "generate Czech salutation", "personalize the opening line", "create vocative from first name", "napiš oslovení", "vytvoř personalizaci", "úvodní věta", "hook z webu", "icebreaker z příspěvků", or any request to add a personalization column. Triggers on personalization, opening lines, hooks, icebreakers, greetings, formal address, vocative case, name declension, or multi-language salutations in the context of Leadspicker.

tomasblatak Skill

Creates AI-powered classification and data processing magic columns in Leadspicker projects through the Leadspicker MCP server, using GPT-4o-Mini behind the scenes. Use whenever the user wants to classify, score, label, tag, clean, or transform contact / company data in Leadspicker — for example "classify companies as SaaS", "is this person a decision maker", "determine company industry", "clean job titles", "create an icebreaker from LinkedIn posts", "is the company B2B or B2C", "classify leads as relevant", "chci klasifikovat firmy", "urči odvětví", "vyčisti název firmy", "je ten člověk relevantní", or any request to add an AI-powered magic column. Triggers on AI classification, lead scoring, contact tagging, data cleaning, or personalization columns in the context of Leadspicker.

kitephp Bundle

Dual-runtime companion skill for Hermes and OpenClaw. Adds heartbeat-driven life logs, moods, relationship evolution, daily planning, and independent memory. Use when building a persistent digital companion or automating companion-style outreach.

zllovesuki Skill

Apply Cloudflare reference architecture patterns for CRUD SaaS, collaboration, async exports, AI assistants, RAG, media, webhook ingestion, and migration. Use to turn requirements into an implementation pattern and primitive map.

dylan-buck Bundle

Local video clipping automation for /clippos requests, attached video files, video links, social clip generation, captioned shorts, crop/framing, and rendered 9:16, 1:1, or 16:9 exports. Use this skill whenever the user wants an agent to turn a video into high-potential clips, score clips with the current harness model, approve selected clips, and render final MP4 outputs.

zllovesuki Skill

Write Cloudflare Workers AI and AI Gateway code for model inference, prompts, streaming, token budgets, model selection, observability, and fallback design. Use when adding LLM, embeddings, summarization, classification, or generation to Workers.

samyakjain0606 Bundle

Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM programmatically, including: creating/managing notebooks, adding sources (URLs, YouTube, text, Google Drive), generating content (podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, data tables), conducting research, chatting with sources, or automating NotebookLM workflows. Triggers on mentions of "nlm", "notebooklm", "notebook lm", "podcast generation", "audio overview", or any NotebookLM-related automation task.

xanticious Bundle

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

xanticious Skill

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions 'domain model' or 'DDD'.

lennith Bundle

Optimize context control for complex index-based skills without changing business scoring semantics. Use when a skill has large retrieval payloads, context explosion, unstable agent retries, or oversized search responses. Trigger for requests about response-profile/fields/limit/payload budget, oversize hints, staged payload breakdown, and benchmark comparison between full and compact outputs. Do not use for scoring-threshold changes, label policy changes, schema migrations, or non-index feature design.

lennith Skill

Validate and publish a TemplateBundle inside the current EasyAgentTeam template workspace with retry-friendly reports. Use before submission and whenever check or publish needs to run through the local template bundle guard commands.

zllovesuki Skill

Build retrieval augmented generation on Cloudflare with AI Search, Vectorize, Workers AI embeddings, chunking, metadata filters, citations, ingestion pipelines, reranking, and grounded answer generation. Use when implementing RAG, semantic search, or document QA.

veselyvaclavcz Bundle

Set up and operate a cost-aware Codex workflow using Codex custom subagents and RTK. Use when the user wants the main Codex model to stay the senior orchestrator while cheaper Codex subagents handle bounded exploration, small implementation tasks, reviews, summaries, logs, and extraction work with explicit routing rules in AGENTS.md.

shire31 Bundle

用于指导“任意 Agent”的迭代方法论技能。凡是用户要求你总结迭代原则、减少补丁式改动、强调 Why、应用奥卡姆剃刀/第一性原理、或要求以产品负责人视角做取舍时，必须触发本技能。适用于任意 agent，不绑定单一业务域。

sudotsu Bundle

The primary orchestrator for complex projects. Use at the start of a task to analyze requirements, generate a multi-agent execution plan, and coordinate specialists.

i-am-shuan Bundle

Summarize Skill

theaisingularity Skill

Natural language smart home control — parses commands and invokes Home Assistant via MCP, learns your routines and auto-creates cron skills for them

agent-skills Skill

帮助用户发现并安装 Agent 技能。当用户询问“我该如何做 X”、“寻找关于 X 的技能”、“是否有技能可以...”或表现出扩展能力的兴趣时，应使用此技能。当用户寻找可能以安装技能形式存在的功能时，此技能非常有用。

jlindstrom21 Bundle

Jeremy Haynes' verbatim revenue plateau diagnostic framework. Runs a 7-step structural audit across offer structure, delivery model, acquisition method, owner bottlenecks, and systems maturity to diagnose why revenue has stalled and prescribe a specific rebuild plan with an Impact List ranked by probability of impact. Covers the staircase model, addition vs amplification vs efficiency paths, the Attention Pyramid, churn equation for recurring models, Jeremy's amplification sequence, qualification ratio fixes, and 90-day execution sequencing. Trigger when the user says "revenue plateau", "stuck at X per month", "revenue gone sideways", "hit a ceiling", "nothing I try moves the needle", "agency stalled", "need to break through", or any diagnostic on why an info-product or agency client has flatlined. Part of the jl- library (Jeremy Haynes' verbatim skills).

jaxchen29 Bundle

Review a single git commit or the latest fresh commit with findings-first feedback. Use when the user asks to review a commit, provides a SHA, asks to review the latest commit or `HEAD`, shares `git show` output, or when post-commit context indicates a new commit was created. Focus on correctness, regression risk, missing tests, and aiter SP3/HIP/CUDA concerns.

jlindstrom21 Bundle

Jeremy Haynes' verbatim framework for building an upsell and ascension system that adds profit without acquiring new leads. Covers mapping the value ladder, designing order bumps and one-time offers, building 30-90 day post-purchase email sequences, segmenting customers by engagement, and architecting tag-based automation for ascension. Trigger when the user asks about "value ladder", "ascension path", "upsells", "order bumps", "one-time offers", "OTO", "post-purchase sequence", "increase LTV", "increase AOV", "continuity / membership model", or "profit without new leads". Use when diagnosing a single-offer business with flat LTV or designing a multi-tier revenue expansion plan. Part of the jl- library (Jeremy Haynes' verbatim skills).

jlindstrom21 Bundle

Jeremy Haynes' verbatim framework for designing a coaching delivery model that scales without burning coaches out. Covers the time-for-money ceiling, auditing current delivery and coach dependency ratio, identifying binding constraints (calendar, energy, quality, team), designing group structure with the 80/20 delivery split, peer accountability pods, building a prioritized content library (onboarding, FAQs, core modules, templates, case studies), AI integration for FAQ chatbots and personalization, capacity systems with group size caps and response SLAs, async buffer architecture, and a 3-month phased implementation plan with delivery metrics. Trigger when the user asks about scaling coaching or info-product delivery, breaking a one-on-one ceiling, designing group coaching, building a content library for clients, integrating AI into client support, setting coach capacity limits, transitioning existing clients into a group model, or diagnosing why a delivery model is breaking. Part of the jl- library (Jeremy

wimblerobotics Bundle

<!--

tungcorn Bundle

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

tungcorn Bundle

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

tungcorn Bundle

Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.

tungcorn Bundle

Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.

heldinhow Bundle

Build high-quality MCP (Model Context Protocol) servers for LLM tool integration.

heldinhow Skill

Use when building Retrieval-Augmented Generation (RAG) systems, chatbots with document context, semantic search, or AI apps that query a knowledge base before generating responses.