AI & ML

talhamah56 Skill

Build and debug image preprocessing pipelines for deep learning when images are large, multi-channel, or scientifically calibrated - satellite/aerial GeoTIFF, Sentinel/Landsat multispectral stacks, whole-slide pathology (SVS/NDPI/OpenSlide), CT/MRI volumes, or any raster too big for the GPU. Use when the task mentions tiling, patching, sliding window, chip extraction, stride/overlap, seams when stitching predictions, reassembling tiles into a full-scene mask, normalization statistics, per-channel mean/std, percentile clipping, nodata poisoning stats, albumentations, image+mask augmentation, additional_targets, class imbalance in segmentation, empty/background tiles, slow DataLoader num_workers on Windows, worker seeding and reproducible augmentation, or converting a dataset to memmap numpy / WebDataset / LMDB / zarr. Also use when a segmentation or dense-prediction model trains fine but produces grid-shaped seams, all-background outputs, or scores far worse at inference than in validation.

talhamah56 Skill

Create a specialized CLAUDE.md (+ AGENTS.md symlink) inside a specific folder to give future agents folder-scoped context. Use when David asks to create a CLAUDE.md for a folder, write folder instructions, or add agent context to a directory.

mk-joshuajallen Bundle

Notion Design Context

mk-joshuajallen Skill

Regenerate the monthly commercial metrics Highs/Lows narrative for a run date. Use when someone asks to regenerate, write, refresh or redo the commercial metrics narrative, the country narrative, or narrative_country.json for a given run date or month. Triggers on "regenerate the narrative for run date X", "write the commercial metrics narrative", "redo the narrative for August".

diyiwuyan Bundle

Collect, complete, tailor, and track job applications from a user-provided resume and job links, using authorized browser or agent tools. Use for requests to auto-fill or submit applications; do not use for resume-only editing or generic job advice.

talhamah56 Skill

Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with a reviewer jury (self-review, with a much weaker guarantee, when no other model is configured — see below) and human approval at landing. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.

maybackcompany Skill

Pair a remote AI agent with your browser. One command generates a setup key and prints instructions the other agent can follow to connect. Works with OpenClaw, Hermes, Codex, Cursor, or any agent that can make HTTP requests. The remote agent gets its own tab with scoped access (read+write by default, admin on request). Use when asked to "pair agent", "connect agent", "share browser", "remote browser", "let another agent use my browser", or "give browser access". (gstack) Voice triggers (speech-to-text aliases): "pair agent", "connect agent", "share my browser", "remote browser access".

maybackcompany Bundle

Validate agent-built or bot-built code, plans, PRs, web app changes, automation, and release candidates. Use when the user invokes /bot-validator, /bv, or asks Codex to audit work produced by an AI agent or coding bot before accepting, merging, shipping, or building on it, including checks for correctness, tests, security, performance, maintainability, browser behavior, CI quality gates, and release readiness.

talhamah56 Bundle

Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring agent workflow or automation cadence, turn an outcome into a bounded copy-ready loop, or review an existing loop for weak checks, unsafe authority, unbounded repetition, stale state, or unclear stopping behavior.

talhamah56 Skill

Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via adversarial review (external cross-model reviewer backend when available, ultra reasoning; falls back to Claude self-review with no second model), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.

talhamah56 Skill

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.

talhamah56 Skill

Write a single-paragraph Deep Research prompt to hand to a human researcher (or a deep-research AI). Use when the user wants a research brief, a "deep research prompt", a one-paragraph task for a researcher, or asks "what should our researcher look for". Produces ONE tight paragraph with full context, numbered sub-questions, and per-finding output format.

talhamah56 Skill

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A fresh Claude self-review pass evaluates results against intended claims and routes to next action (pivot, supplement, or confirm) when no external reviewer model is available. Use after experiments finish — before writing the paper or running ablations.

talhamah56 Skill

Audit experiment integrity before claiming results. Uses adversarial review (external cross-model reviewer backend when available, Claude self-review otherwise) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

talhamah56 Skill

Chart and plot data — pick the right chart type for the data shape, then generate Chart.js config or Plotly code. Use when asked to visualize a dataset, plot results, build a chart, or choose between chart types/libraries for quantitative data (as opposed to structural/technical diagrams — see technical-diagrams for those).

maybackcompany Skill

Scrape, crawl, map, search, or extract structured data from web pages using the local self-hosted Firecrawl API at http://localhost:3022. Use when the user asks to scrape a URL, crawl a site, extract structured data from web pages, map a sitemap, get markdown from a webpage, or fetch web content for an AI agent. Auto-trigger on phrases like "scrape this", "crawl that site", "get markdown of", "extract data from", "firecrawl".

roche-k Bundle

Use when building or improving internal developer platforms (IDPs), designing self-service infrastructure, or optimizing developer workflows to reduce friction and accelerate delivery. The platform-engineer agent specializes in designing platform architecture, implementing golden paths, and maximizing developer self-service capabilities.

maybackcompany Bundle

Use whenever the user wants to make a video, short, reel, or piece of content about a niche, topic, industry, trend, business, product, personal story, or content idea, and turn it into a complete creator execution plan. Trigger on prompts like "I need to make a video on this niche", "I need to make a video on this", "give me content ideas for this niche", "how do I start content in this market", "make me a video plan for this topic", "I want to go viral with X", "what should I post about", "help me start a TikTok/YouTube/Reels channel about X", or "I have a video idea but no angle". Produces a sharpened position, creator model, audience diagnosis, hook bank, video ideas, a full script, production notes, and a 7-day test plan. Defaults to founder-led content when the user is building a business, product, course, or community, but adapts to educators, entertainers, and personal brands. Trigger even when the user names only the topic and not the word "video".

ctaxnagomi Bundle

Few-shot sentiment analysis prompt.

ctaxnagomi Bundle

Senior code reviewer persona prompt.

ctaxnagomi Bundle

Meeting notes summarization prompt.

roche-k Bundle

Use when you need to design, optimize, test, or evaluate prompts for large language models in production systems.

wyattjy Bundle

Notion API via curl: pages, databases, blocks, search.

huangyuchuh Bundle

Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities. **Use this Skill when:** (1) The user requests to "generate an image", "draw a picture", or "execute a ComfyUI workflow". (2) The user has specific stylistic, character, or scene requirements for image generation. (3) The user asks you to import, register, sync, or configure saved ComfyUI workflows for later reuse.

starchild-ai-agent Skill

Director-level Seedance 2 video prompt maker for 15-second cinematic multi-shot CGI animation prompts.

soloduist-pixiv Bundle

Scores, critiques, revises, and writes Chinese Gaokao English 小作文 (应用文, typically 15 marks, about 80–120 words per the prompt): letters, emails, notices, invitations, speeches, and similar short practical writing. Use whenever the user asks to 打分, 评分, 批改, 评判, 润色, 升档, 写范文, or mentions 高考英语作文, 小作文, 应用文, 书信, 通知, or a short model essay — even if they only paste a prompt or a student draft. If the user provides both a prompt and their own essay, mark spelling, revise point by point, assemble a corrected draft, then write a deeper ~150-word model essay. Do not use for 读后续写, continuation writing, 概要写作, or other 大作文.

josstei Skill

Agent delegation best practices for constructing effective subagent prompts with proper scoping

zcweah1981 Bundle

负责把页面需求转成数据结构和 API 合同。

ctaxnagomi Bundle

Fitness training data integration via MCP.

ctaxnagomi Bundle

Video editing automation with DaVinci Resolve.

ctaxnagomi Bundle

Optimize token usage and reduce API costs.

ctaxnagomi Bundle

Web scraping and crawling via MCP.

ctaxnagomi Bundle

Multi-agent optimization workflows.

humaisali Skill

Use when working with performance testing review multi agent review

ctaxnagomi Bundle

Meta-prompt for improving prompts.

ctaxnagomi Bundle

User intent classification prompt.