Check AI-generated claims against your approved Fact Sheet and flag changed quantities, expanded scope, dropped attribution, and unsupported mappings — deterministic, local, and no AI guessing.
Finds genuinely lesser-known, web-verified facts on any topic you choose, always with a cited source. Responds in your language.
日々AIの回答・ニュース・SNSの言説を実務で扱う中で、出典のない数値や「最新」を装った古い情報に何度も振り回された経験から、このSkillを設計しました。主張を安定/不安定に分類し、不安定な情報ほど一次ソースを最優先で確認、重要な主張は独立した複数ソースでクロスチェックする手順を体系化しています。AI生成記事が引用元の主張を実際には支持していないという罠も検出します。
Turn flat text into sharp satire. Add depth, double meanings, and that "laugh first, think second" quality — all while keeping your original story and characters intact. No need to write from scratch. Just paste what you have, and this system rewrites it with layered irony Works on any genre — fiction, essays, dialogue, even product descriptions.
Turns a specimen, field observation, or nature photo into a caption that reads like it was written by someone who did the research. Every claim is either backed by a real, cited source or flagged as a guess, no invented facts, no generic 'magical nature' filler.
This Skill is built on practical expertise in claim-evidence mapping, source authority labeling, quote verification, citation hygiene, recency checks, and hallucination-risk control. It helps AI agents turn research, reports, summaries, briefs, and marketing drafts into auditable claim ledgers where every important claim is matched to a source, date, quote/paraphrase boundary, and confidence label.
AI video and image models substitute a neighboring culture, approximate signature props into near-miss objects, and paint fake lettering onto signage. EraLock pins your prompts to one country and one year: a six-category era anchor, a culture-exclusion negative set naming the exact elements that bleed in, form locks that ban the wrong object by name, and an inspection checklist for the output. Built from a year of daily period-piece work — every rule traces to something that shipped wrong.
Consistency isn't a willpower problem — it's a systems problem. This skill builds YOUR self-running content engine: every morning, a draft in your voice is waiting in a folder before you wake up. You read it, you press publish. Built from a real engine running live daily, including the author's actual failure log — the path bug that killed his scheduler, the 3-day silent death he never noticed, and the data that made him ban generic how-to posts. Buy once, updates included.
As a finance content creator, I know the daily struggle of turning raw market data into engaging, compliant content across multiple platforms. I built this workflow to save hours of formatting. It strictly separates observed facts from interpretation, flags missing sources, and strictly avoids investment-advice language. This is the exact system designed to generate newsletters, X threads, and video scripts safely and efficiently every single day.