Runs a local Python runtime to handle bulk file operations and return only summaries, cutting token use by 90%+.
A Russian-language copy-editing skill that fixes only the formulaic, machine-sounding parts of a text while preserving its meaning and authorial voice.
A surgical editing skill that strips formulaic, machine-sounding patterns from Russian prose while preserving meaning, hedging and authorial voice.
An operational cheat sheet that lets Claude run, regenerate, and debug the DailyBrief daily digest pipeline.
Writes copy-ready image prompts with the right model, quality level, and aspect ratio for your request.
A hands-on guide to nanoGPT: train a tiny Shakespeare model on CPU or reproduce GPT-2 (124M) on multi-GPU, step by step.
A zero-trust gatekeeper skill that scans every incoming file or URL and returns a pass/reject verdict plus a compliance scan report before any document processing happens.
A companion skill that chats with you while long background tasks run, generating scene-based "life photos" and warm messages delivered through Feishu.
An umbrella design skill with six modes: UX copy, design systems, design critique, WCAG accessibility audits, developer handoff specs, and user research synthesis.
Generates, audits and fixes dependency-free static HTML landing pages built for 100/100 PageSpeed with full JSON-LD markup.
Forces a probe → hypothesis → smoke → control → claim discipline when an ML training run fails, diverges, OOMs, hangs, or looks slow.
An architecture skill that audits your layers, boundaries and SOLID usage against the Dependency Rule and prescribes concrete inversions.
Reverse-engineers a researcher's publication strategy from PubMed into a CSV dataset, seven charts, and a strategy report.
Extracts journal metadata from an author-guidelines page and generates two canonical profiles — a detailed writing profile and a compact journal-matching profile.
Finds GitHub Actions workflows whose latest run failed on the staging branch, summarizes the error, and hands off the fix.
A structured Kubernetes skill that diagnoses manifests, Helm charts and Kustomize overlays through six failure modes and enforces validation plus rollback planning.
A skill that computes option delta, gamma, theta, vega and implied volatility via a Black-Scholes command-line script.
Builds a full market positioning package — Dunford's 5+1, Moore/Neumeier statements, alternatives map and category strategy — from a short intake.
Takes a raw startup idea through 8 phases — market research, competition, brand, product, financials, validation — and outputs a full set of decision-ready markdown docs.
Send screenshots, UI mockups, or diagrams to external vision models (Doubao, Qwen, DeepSeek, OpenAI, Claude) and get a text description back.