find-literature
This skill should be used when the user asks to "find papers", "search for papers", "what does the literature say", "find research on", "academic papers…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-19 00:11
Writing & research
13,690 results
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or…
plain-english
Tighten prose by stripping AI tics and applying Orwell/Gowers plain-English rules. Use when the user asks to rewrite, tighten, simplify, or detox writing —…
chinese-de-aigc
An AIGC detection rate reduction Skill for Chinese academic papers. Targeting the detection mechanisms of CNKI, Wanfang, VIP, and Turnitin Chinese Edition, it identifies and eliminates 17 categories of structured writing traces from Chinese large language models. It adopts "locate → diagnose → rewrite → self-evaluate →…
worldbuilding
This skill should be used when the user asks to "create a location", "add a location", "magic system", "political system", "build the world", "add culture",…
legal-verified-research-memo
Generate a legal research memo with claim-level source verification, confidence flags, and primary-authority priority.
cw-router
Quick guide to choosing the right creative writing skill. Use when you need help deciding which creative writing skill to use for a specific task -…
check-review-alignment
Use when the user explicitly requests "check/optimize review `{主题}_review.tex` body citations" or "run check-review-alignment". Verify item by item through the host AI's semantic understanding whether citations match the literature content, only perform minimal rewriting of "sentences containing citations" when fatal citation errors are found, and reuse…
get-review-theme
Use when the user explicitly requests "extract a review topic from a file/image/webpage/description" or "generate a structured output of topic + keywords + core questions". Supports multiple input sources such as files (PDF/Word/Markdown/Tex), folders, images, natural language descriptions, and webpage URLs; automatically identifies the input type and extracts content, generating output that can be used directly for systematic-literature-review…
nsfc-ref-alignment
Check the consistency and authenticity risks between in-text citations and references in an NSFC proposal (read-only): verify whether bibkeys exist, check BibTeX fields and formats such as DOI, and generate structured input for the host AI to evaluate one by one whether "the statement in the text is really citing that reference"; by default, only output an audit report and do not directly modify the proposal or the .bib (unless the user explicitly requests it).
cctv-news-fetcher
Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date.
lovstudio-translation-review
Review Chinese-to-English translations for accuracy, grammar, terminology, and consistency. Produces a structured review report with prioritized issues.…
research-claim-map
Systematically evaluates claims by triangulating sources, rating evidence quality (primary/secondary/tertiary), assessing source credibility, and reaching…
documentation-impact
Check documentation impact before completing a change or declaring it ready to ship. Use when a change may affect user, operator, or developer instructions,…
copywriting
Write compelling, persuasive marketing and sales copy using proven frameworks like AIDA, PAS, BAB, and 4Ps, with tone and voice customization, CTA…
knowledge-base-article-writing
Write clear, searchable help center articles and FAQ entries based on support data, product documentation, and common customer questions. Use when the user…
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
legal-element-extraction
This skill is triggered when legally significant facts need to be extracted from unstructured text such as case descriptions, party statements, chat records, and media reports. Typical trigger scenarios include but are not limited to: - The user provides a case description in everyday language and requests extraction of legal facts - The user requests conversion of a colloquial, emotional narrative into a factual structure usable for legal analysis - The user requests distinguishing "objective facts," "subjective judgments," and "legal evaluations" in a case narrative -…
rule-catalog
Browse hookify rule catalog. Use when installing pre-built rules or browsing categories. Do not use when writing custom rules; use hookify:writing-rules.
tutorial-updates
Generates or updates tutorials from VHS tapes and Playwright specs with dual-tone markdown and GIF recording. Use when tutorial assets need refreshing.
changelog
Creates, updates, and reviews product changelog entries for the Cloudflare documentation site. Load when generating changelog MDX files, editing existing…
Use Case Documentation
Write formal Use Cases with actors, preconditions, triggers, main flows, alternative flows, and postconditions
matlab-add-awgn
Read BEFORE writing any code that adds Additive White Gaussian Noise (AWGN) to signals and converts between SNR, Eb/No, Es/No, and per-subcarrier SNR for…
text-generate
Use meitu-cli to call an independent LLM to generate text/copy/storyboard scripts/video prompts from scratch. Triggered when the user mentions writing copy, polishing, rewriting, advertising slogans, product descriptions, social media copy, articles, storyboard scripts, storyboard, or prompt optimization. Disabled when the context already contains complete content; in that case, use write_file instead.