Demands your real textbook/slides/syllabus, extracts likely exam topics, then tutors you with Socratic questions instead of handing over answers.
Generates UX microcopy — button labels, error messages, empty states, toasts — in a casual-but-polite voice with per-context formats and do/don't guidance.
Turns "denser", "bolder", or "sharper corners" into exactly one step on one design axis, applied system-wide with guardrails and a quality re-gate.
Audits a screen against Nielsen's 10 usability heuristics plus mobile UX and dark-pattern checks, returning a grade and severity-ranked fixes.
A three-phase Russian-language editor that strips AI tells, bureaucratic filler, and fluff while restoring a human voice.
A persona skill that forces the laziest solution that actually works — stdlib and native features first, shortest diff, no unrequested abstractions.
Drives the Compass CLI's local code knowledge graph so Claude answers architecture, dependency, and change-impact questions with cited evidence.
Give it the URL of an underperforming page and it fetches, researches the SERP, and rewrites the whole thing under a strict anti-AI-slop plus on-page SEO ruleset.
Scores any page across Experience, Expertise, Authoritativeness and Trustworthiness, then tells you exactly what to add.
Interviews you with sharp, one-at-a-time questions to extract first-party experience, numbers and failures, then packages them into a structured knowledge document.
Rewrites the answer section of a page you already rank with so it matches the exact snippet format Google pulls.
Runs a full codebase hygiene scan for dead code, tech debt, outdated dependencies and code smells, then writes a prioritized report.
Runs a deep security audit across OWASP Top 10, secrets, and dependency CVEs, then writes a dated report with an approval verdict.
An editing skill that finds and rewrites 24 tell-tale AI writing patterns, based on Wikipedia's "Signs of AI writing" guide.
Reads dashboard screenshots, CSVs, or public links to validate content performance per post, week, or month, attribute causes, and design the next single experiment.
Turns a confirmed theme and evidence pack into truly platform-native drafts for X, Xiaohongshu, WeChat and short video.
An end-to-end creator workflow that runs topic planning, evidence research, platform-native drafts, short-video packages, publishing kits, and performance reviews as one resumable loop.
Models the true margin and TCO of each go-to-market channel and designs partner tiers, rebates, and channel-conflict rules.
A SaaS retention playbook that designs cancel flows, reason-based save offers, dunning sequences for failed payments, and win-back campaigns.
A production-grade competitor analysis framework: 6 intelligence sources, a 12-dimension scorecard, feature/pricing matrices, SWOT, UX audit, action plan, and a sales-ready battle card.