qi-maintenance
Load on agents that make durable changes to a project's files, so the colocated AGENTS.md and .context/ docs stay true for the next cold agent.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
Writing & research
14,484 results
story-workflow
Load to carry story work with an author from what they want to a page they accept: reading their intent, setting direction, producing and critiquing the prose,…
writing-sync
Load when syncing selected local files to a remote reading copy, or bringing remote edits back into those files. Google Drive/Docs only.
hello-write
Use when writing documents, READMEs, technical proposals, analysis reports, user guides, email replies, Q&A explanations, wording rewrites, or any task requiring professional text output.
private-company-research
Deep research framework for pre-IPO / private companies (Ant Group, SpaceX, Stripe, ByteDance...). Six analyst lenses — business model, financial forensics,…
research-discipline
A short self-bias checklist to run at the START of any investment research task (stock screen / sector study / company deep-dive). Four biases that…
flutter-localization
Add Flutter translation assets, locale initialization, localized strings, locale switching, and plurals with easy_localization and CSV or JSON files. Use for…
swift-best-practices
Apply Guard, Value Types, Immutability, and Naming conventions in Swift. Use when writing idiomatic Swift with guard, value types, immutability, or naming…
sub-cli
Manage posts on your Substack publication and read other people's newsletters from the command line. Use when creating, listing, updating, scheduling,…
zh-en-translation-polish
Translate Chinese into natural English or polish an English translation against its Chinese source; supports bilingual output. Excludes English-to-Chinese,…
zh-article-analyzer
Traditional Chinese article deep-analysis skill. Performs multidimensional scientific dissection of any Chinese article, producing an analysis report precise down to line numbers and paragraphs. Covers: Stylometrics, linguistic rhythm, lexical richness, citation and allusion mapping, thematic dynamics, emotional arcs, rhetorical force, classical-vernacular ratio, idiom density, etc. Combines Python quantitative scripts with LLM qualitative analysis to produce a complete "article fingerprint report".…
celpip-writing-coach
Use when coaching CELPIP Writing Task 1 emails or Task 2 survey responses, scoring drafts, comparing revisions, building short recall drills, or preparing for…
ielts-writing-coach
Use when coaching IELTS Academic or General Training Writing Task 1 or Task 2, estimating bands, comparing revisions, creating targeted drills, or validating…
init-physics-intern
Scaffold a PhysicsIntern research workspace in the current folder. Run only when the user explicitly invokes it to set up a new physics/maths research…
human-writing
Edit, review, audit, or draft standalone prose while preserving the writer's meaning and voice. Use for documentation, markdown, emails, blog posts, PRDs, and…
zmm-concept
📐 Zhan Mingming · Re-explaining a concept — Re-explain a concept everyone uses (pricing / topic selection / demand / conversion / customer acquisition…) — break it open, and grow a ruler out of the cracks. Lock the four items first, then write the draft; the final version is dictated by the person himself. Trigger: /zmm-concept, /重讲概念, 「把 XX 这个概念讲清楚」「XX 到底是什么」「为什么 XX 越 YY 越…
zmm-flow
📐 Zhan Mingming · Where viewers get pulled away — spoken-script 「drop-off points」 special. Listen to the script on the audience's behalf: at every beat, what the audience has in hand, what they're waiting for, which beat it breaks at — what they're waiting for doesn't come, they already have it but you keep giving, what's being given can't be heard clearly. After diagnosing, by default proactively ask whether to do a marked-up revision. Trigger: /zmm-flow, /will-they-drop-off, /smooth-the-script, /zmm-smooth-the-script, 「is this script smooth」「where will they drop off」「is the logic broken」「reading it…
zmm-hook
📐 Zhan Mingming · The First Five Seconds — a specialized skill for short-video openings. First diagnose whether the content has substance (gatekeeping), then compare the real-material entry point against the mass-suspense entry point, and combine openings and negative space to produce candidates, labeling which principle each candidate uses. Trigger methods: /zmm-hook, /hook, /opening, /zmm-opening, "how do I write an opening", "can't grab people in the first five seconds", "help me think of a few hooks", "is this opening okay" Opening-hook…
zmm-post
📐 Zhan Mingming · WeChat Official Account short-post — WeChat Official Account image-text short-post skill. Turn validated content / fragments into a WeChat Official Account "short post": title ≤20 Chinese characters + body ≤1000 Chinese characters + one banner image. Positioning = lightweight image-text, not the long-form deep-dive of article-pipeline. Title goes through /zmm-title, opening line through /zmm-hook…
zmm-resonate
📐 Zhan Mingming · Does it hit? — Resonance diagnosis skill. Not starting from theory, but from the audience: what did this piece of content leave the audience with (so that's how it is / I knew it / he said it for me), and will they take action (save / share / comment / follow); every judgment points to the original text and marks whether it is evidence, inference, or pending verification. Mode A diagnoses your own draft; Mode B breaks down someone else's hit to reverse-engineer an angle you can borrow; Mode C…
zmm-retro
📐 Zhan Mingming · Post-publish Retrospective — short-video retrospective skill. After publishing, pull back the real platform data, run an attribution discussion against the pre-publish predictions, and write the validated patterns into skill memory — so the system learns "why this one took off." Trigger methods: /zmm-retro, /data is out, /retro, /zmm-retro, "this one's data is out," "why did this one take off," "why didn't this one take off," "let's do a retrospective" Post-publis…
zmm-review
📐 Zhan Mingming · Review before publishing — pre-publish review skill for spoken-word scripts. Review by the audience's four decisions: will they click in · will they stay · will they remember you · will they do something. Sentence-by-sentence information density scoring (60/80 threshold) + eleven questions + five red-line checks (fixes given in a safe version and a preserve-the-force version) + machine signal layer (traffic diversion / ad shape /...
zmm-script
📐 Zhan Mingming · Koubo Script Writing — A collaborative koubo script writing skill (primarily knowledge-paid koubo). Three types of script selection + assembly from content units + paragraph-by-paragraph co-creation; no one-click finished drafts. Trigger: /zmm-script, /写口播, /写稿, /zmm-写稿, 「写个口播稿」「帮我把这个题写出来」「知识付费口播」「写条视频文案」 Collaborative koubo…
zmm-title
📐 Zhan Mingming · Titles & Covers — multi-platform titles and covers. Choose the structure according to the shape of the content itself (a list of 12 structures), pass the red lines of over-selling / prohibited words / no naming / jargon, and for each title explain clearly what structure was used and why it fits this piece of content. **No "universal viral formulas" — empirical evidence shows title structures are not interchangeable across accounts; a script is included so you can work out the patterns of your own account.** Trigger: /zmm-title, /cover…