Escrita e Conteúdo

当用户在科研写作过程中踩到一个本系列 paper-* skill 没覆盖的新坑、 并表示"以后...我都要这样做"、"下次记得..."、"这种情况要先..."、"加一条新规则"时， 帮用户把这条新规则按 4 个判断题筛过，合格则按本 skill 提供的模板提炼成一个新的 paper-* skill 落盘。 Use when 用户说"以后...都要..."、"下次记得..."、"这种情况要先..."、 "帮我把这个习惯固化下来"、"加一条新规则"。

Apply consistent, professional Markdown formatting rules whenever producing or reformatting Markdown output. Use this skill when generating any Markdown document, when the user asks to reformat or clean up existing Markdown, when producing README files, technical docs, notes, or any other content that will be rendered as Markdown. Trigger even when the request seems simple -- any Markdown output s

Natural-language editor for .claude/quality/schedule-config.json. Users talk about maintenance scheduling in everyday language ("run audit twice a week", "turn off deep daydream", "switch dispatcher to 08:30") — this skill parses intent, validates against the schema, shows a concrete diff, asks for confirmation, and writes the change. WHEN TO USE: - User wants to change how often a job runs - User

Periodic maintenance of institutional knowledge. Analyzes lessons for staleness, overlaps, and gaps. Keeps lessons.json healthy.

Single-task dispatcher for CLEAR Context OS scheduled maintenance. Runs from the daily scheduled task, reads schedule-config.json, determines which jobs are due today, runs them in sequence, appends to the diary, writes a consolidated morning digest, and surfaces any frequency-tuning suggestions. WHEN TO USE: - Invoked automatically each morning by the `bcos-{PROJECT}` scheduled task - User says "

Detecta e corrige padrões de escrita gerados por IA (slop) com detecção abrangente de mais de 45 padrões, sistema de pontuação e modo de edição para correção direta, ideal para auditar rascunhos ou humanizar textos de IA.

Load this skill whenever writing, editing, or reviewing any web content, copy, headings, labels, error messages, or instructions. Under no circumstances write inaccessible content — every piece of text must be clear, structured, and usable by people with cognitive, visual, and language differences. Absolutely always apply plain language, logical heading hierarchy, and meaningful link text.

Language coaching for every prompt. Use when the user runs /language-coach with any sub-command (setup, native, target, style, response, goal, mode, focus, band, level, status, off, on). Routes to the correct action based on the argument provided.

Audit project configuration and documentation for drift, staleness, and broken references. Use when user asks for 'config audit', 'docs audit', 'check setup', 'audit configs', 'review CLAUDE.md files', or at session start when audit cadence is exceeded. Also invoked as '/config-audit'. (Code port — ADR-094.)

Use when editing or reviewing text to remove AI-generated patterns and make writing more natural and human. Use when the user provides text and asks to remove AI tone, humanize, rewrite naturally, or polish. Also use when text is clearly AI-generated Chinese content. 適用於使用者要求「去 AI 味」、「人性化」、「改寫得更自然」、「潤稿」、「改得像人寫的」時。

Use for ML content creation — Instagram carousels, 3Blue1Brown-style explainer videos, infographics, posters, paper figures, blog headers, or any visual or written deliverable explaining an ML paper or concept to a public audience. Trigger on "make a carousel about [paper]", "explain [concept] in 3B1B style", "video on [ML topic]", "infographic for [paper]", "research thumbnail", "ML one-pager", "

Audit project configuration and documentation for drift, staleness, and broken references. Use when user says "/aria-cowork:audit-config", "/aria-cowork:config-audit", "config audit", "docs audit", "check setup", "audit configs", "review CLAUDE.md files", or at the first aria-cowork skill invocation when audit cadence is exceeded. (Cowork variant — namespaced-only.)