Loading...
Loading...
Found 46 Skills
Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.
Remove AI-generated tone from NSFC grant proposals, making the text read as if written by a senior domain expert (Not applicable: non-proposal content/format modification required/new content supplementation required)
Triggered when users need to learn a certain style, extract writing formulas, build a style library, or imitate a specific author. Deconstruct text in 15 dimensions in depth, including author profile, core thinking, creative path, interactive design, etc., and model it into an accurately replicable style file. Trigger words: style modeling, style extraction, style learning, imitative writing, article deconstruction, writing formula, style library.
Full workflow for official account/self-media creation. Automatically match tasks based on user input: article writing, cover image, body illustration, style extraction. Supports multiple writing styles. It is used when users mention writing official account posts, technical blogs, official account covers, body illustrations, step diagrams, demo diagrams, flowcharts, writing style analysis, style cloning, imitating viral content, style extraction. See the reference directory for details.
Humanize text: strip AI-isms and add real voice.
You MUST use this when writing or editing prose anywhere in a project (docs, READMEs, marketing copy, commit messages) and when asked to audit, score, or clean up negative parallelism, the "it's not just X, it's Y" construction. It bans defining things by negation-plus-contrast in favor of direct positive statements and grades a project's compliance on a 0-100 scale.
Use whenever the user asks to "humanize", "make this sound more human", "rewrite to avoid AI detection", "make this less AI-sounding", "add a human voice", or "write like a person". Also use when the user pastes text and asks why it reads as robotic, generic, flat, or AI-like, or when generating new text in a register where AI tells (em dashes, semicolons, hedges, banned vocabulary like "delve", "leverage", "robust") would damage credibility.
A skill for writing and revising Japanese business documents to make them easy to read and understand. It can be used for creating and proofreading business documents such as meeting minutes (including transcribing to minutes), research/analysis reports, internal guides/manuals, research notes, discussion papers, proposals, reports, emails, and slide outlines, as well as following instructions like 'write from the conclusion', 'clarify the argument', 'keep headings concise', and 'explain technical terms in an easy-to-understand way'. It also supports removing AI-like tones (direct, indirect, or colloquial feedback such as 'AI-like', 'unnatural', 'make it more natural Japanese', 'mechanical', 'make it sound human', 'monotonous', or phrasing like 'it would be possible to...', as well as cases where the document was said to be written by AI or suspected of being so), improving hard-to-read or unclear sentences (such as incorrect word order, long sentences, unclear meaning, incorrect comma placement, etc.), writing new note articles, blog posts, and essays (including requests to write from scratch on any topic), rewriting and polishing existing sentences, diagnosing and scoring AI-like tones (requests without rewriting, such as 'Did AI write this?', 'Score the AI-like tone', 'Judge how AI-like this is'), and requests to learn and profile one's own writing style (including requests to write in one's own style by reading past sentences). It also addresses readability principles such as removing forbidden words, avoiding monotonous rhythm, homogeneous paragraph structure, literal translation of English syntax, as well as word order, commas, one meaning per sentence, and the distance between subject and predicate. The structuring of technical documents or formatting of Markdown itself (such as one sentence per line, quote blocks, footnote notation, etc.) is not covered—this falls under another skill, and this skill specializes in the naturalness, readability, and comprehensibility of text.
When the user wants to define their brand voice, create tone guidelines, build a writing style guide, audit existing content for voice consistency, or asks about brand personality, tone of voice, writing standards, or content guidelines. Reads .agents/product-marketing-context.md for product positioning and audience.
Write prose with craft and a real voice, and edit flat or AI-flavored prose to find it. Two modes: `draft` (write from scratch) and `edit` (bring voice to existing text against a pattern catalog). Adopt any voice or persona: `--voice <name>` from a library, `--persona <name|desc>` (voice plus worldview), or `--like <sample>` to clone one. Backed by a deduped craft canon (Strunk, Zinsser, Orwell, Williams, Lanham, Clark, Pinker, Le Guin, McPhee, Provost) plus the full AI-tell catalog. The core idea is positive: great writing has a person behind it, and the so-called AI tells are just the absence of voice. Use when DRAFTING or EDITING fiction, blog posts, essays, marketing copy, newsletters, or any long-form prose. NOT for code, technical docs, or chat replies. Trigger: 'write this', 'draft this', 'make this better', 'give this voice', 'in the voice of', 'does this sound like AI', 'humanize', 'apply my style'.