Loading...
Loading...
Found 111 Skills
Low-level agentic design patterns and cognitive reflexes across Depth, Breadth, Coil, and Mesh. Turns senior engineering wisdom into reflexes that remove bloat, preserve truth, prevent drift, and compound learning (re0, readchk, autobahn, ssotize, detool, feynman, debloat, sip, hate, macrothink, prism). Use when refactoring complex systems, stripping AI slop, rewriting drifted artifacts from clean v0, consolidating truth into single sources, or evaluating architectural decisions against contrarian counter-arguments.
Organize a sparse, mostly unconnected Markdown/Obsidian vault into a light topic hierarchy. Use when a user wants 5–10 topic root notes, a capitalized `Parents` list assigning notes to topic roots, an embedded Obsidian Base that lists each root's children, and meaningful body-level/`Related` wikilinks that make concept notes navigable without substantive rewriting.
【De-AI-Flavor】AI Flavor Detection — Scans copy sentence by sentence for machine traces (attitude, structure, wording, content, and private-domain mass-message flavor, 20 items total), produces a report in the original order, and by default only diagnoses without rewriting; when the user requests changes, it asks one by one what the sentence intended to accomplish, then rewrites in the user's own words. Covers short-video voice-overs, Moments posts, private messages, Xiaohongshu image-text, and WeChat official account long-form articles. Triggered by phrases like 'Does this have an AI flavor?', 'Does it sound machine-written?', 'Help me see if this passage feels too fake', 'Does this Moments post look like mass messaging?', 'Remove the AI flavor'. | Made by Xiaoye
Load when migrating or converting an entire Gradle Kotlin project (build.gradle(.kts), wrapper, libs.versions.toml, buildSrc) to the Kotlin Toolchain, including rewriting CI and replacing Gradle plugins that have no native Toolchain equivalent. Skip for porting one Gradle plugin or general Toolchain work once Gradle is gone.
Use this skill when Japanese wording itself is the task—drafting, translating, summarizing, proofreading, or rewriting text for its readers and context while preserving meaning, expertise, and voice. Do not use it solely because an unrelated coding, investigation, or operational request is written in Japanese.
This skill should be used when the user asks to "create a style sheet", "style guide", "house style", "keep the voice consistent", "voice drift", "British or American spelling", "character voices", "lint the prose", "prose check", "filter words", "said-bookisms", "overused words", "repeated phrases", "similar character names", "voice fingerprints", or wants to record and enforce the voice and surface conventions of a story project. NOT for rewriting dialogue to make the voices distinct when everyone sounds the same (use line-editing), or a character's profile or arc (use character-management).
Turn a task or prompt into a deeper version of itself, not a bigger one. Before rewriting, say what a top professional in the field would do that the user isn't asking for, the rawest source material they would start from, the specific methods and tools they would use, and what (other than the user or the model) would show the result is right. Then rewrite the prompt to ask for exactly that. USE WHEN: /be-ambitious, "be ambitious", "make this prompt deeper", "what would an expert do here", "raise the bar on this task", "rewrite my prompt like a pro would ask it". NOT FOR: expanding scope, adding features, or general prompt polishing for tone or length.
Produced by DuBaoYa, this **multi-platform copywriting rewriting** expert (seven platforms: WeChat Official Account / Channels / Douyin / Kuaishou / Bilibili / Xiaohongshu / Zhihu — a single source text is rewritten separately according to each platform's real character). Whatever copy you give, it can be converted into high-engagement expression for that platform — WeChat Official Account goes for high-traffic viral copy (catchphrases and hooks), Xiaohongshu needs emoji and a grass-planting tone, Zhihu needs an argumentative feel, and rules are never mixed across platforms. Trigger words: 公众号改写 (WeChat Official Account rewrite), 公众号文案 (WeChat Official Account copy), 公众号风格 (WeChat Official Account style), 微信改写 (WeChat rewrite), 爆款改写 (viral rewrite), 内容改写 (content rewrite), 小红书改写 (Xiaohongshu rewrite), 小红书文案 (Xiaohongshu copy), 小红书风格 (Xiaohongshu style), 笔记改写 (note rewrite), 种草文案 (grass-planting copy), 标题钩子 (title hooks), 抖音文案 (Douyin copy), 口播文案 (oral broadcast copy), 视频号文案 (Channels copy), 知乎风格 (Zhihu style), B站文案 (Bilibili copy), 多平台改写 (multi-platform rewrite), 一稿多发 (one draft multipost), 全平台改写 (all-platform rewrite), 跨平台适配 (cross-platform adaptation). This Skill package runs purely locally, no internet, no external API calls, no key required.
Write prose clean of AI texture, or audit a draft through two gates: source fidelity (every quoted or attributed line verified against primary sources, four verdicts, correction log) and taste (mechanical tell scan plus a nine-dimension scorecard). Use when the user says "de-slop this", "slop check", "AI smell", "sounds like ChatGPT", "make it human", "humanize this", "sounds robotic", "reads like AI", "kill the em dashes", "verify the quotes", "fidelity check", "run the audit", or "taste pass", and when writing or rewriting X posts, threads, articles, essays, fiction scenes, book chapters, or landing copy that must not read AI-generated. Works at any length; the fidelity gate activates whenever quotes or attributions are present. Do not use for voice imitation (use a style-converter skill), UI design, or proving a text was AI-written: the banned list is house style, not a detector.
Audits and fixes both halves of being found — classic search and AI answers. Search side: rankings, site structure, page speed, titles and descriptions, and content that answers what customers search for. AI side: whether assistant crawlers can reach the site, pages render without JavaScript, an llms.txt file, schema.org data, and presence in the directories assistants read. For online stores it also runs a bulk catalog cleanup, rewriting product titles, descriptions, alt text, and SEO fields in approved batches. Works on any public website with no connector. Use this whenever the owner talks about being found online, including "nobody finds us on Google," "how do I show up in ChatGPT," "make my website AI friendly," "SEO audit," "GEO," "AEO," "AI search visibility," "my competitor ranks above me," "fix my product listings," or "I asked an AI about my industry and we weren't in the answer."
When a task is blocked by missing or unverified information (an undocumented protocol, an unknown API shape, a value only real hardware/prod can confirm), build everything that does NOT depend on the unknown right now, and quarantine the unknown behind a single adapter boundary — best-guess defaults + a verified flag + a conformance/adapt kit — so adapting later means editing one file, not rewriting the project. Trigger when the user says "làm những gì có thể trước", "build what we can now", "wrap the unknowns", "isolate/quarantine the unknown parts", "don't block on missing info", "adapter so we can swap later", "ready to adapt", or invokes /build-now-adapt-later. Also applies whenever a spec has ⚠️ "to be verified" items but most of the work doesn't actually depend on them.
Selection and writing methods for short-form video hooks (openings), Chinese name: 「钩子」. Use when creating a hook, writing a hook, figuring out how to write a hook, running out of ideas for a hook, designing a hook for the first 5 seconds, or writing a video opening or spoken-script opening; also use when the user asks how to start a video, requests an opening template, asks about hook types, or asks for help creating a hook, including during ra-洗稿 script rewriting and topic ideation. Provides a scenario-based taxonomy of 7 hook types with a decision flow, prerequisites, sentence templates, and common mistakes. To diagnose and optimize an existing hook draft, use dbs-hook instead; this skill chooses the type, while dbs-hook refines the execution.