Total 53,944 skills, Documentation & Writing has 1524 skills
Showing 12 of 1524 skills
Craft compelling narratives using story frameworks. Use when the user says "help me with storytelling" or "I want to create a narrative through storytelling"
Write internal company communications — 3P updates (Progress/Plans/Problems), company-wide newsletters, FAQ roundups, incident reports, leadership updates, status reports, project updates, and general internal comms. Use this skill any time the user asks to draft, edit, or format something meant for internal audiences. Trigger on keywords like "3P", "weekly update", "newsletter", "FAQ", "internal comms", "status report", "company update", "team update", "incident report", or any request to summarize work for leadership, teammates, or the broader company. Even casual requests like "write my update" or "summarize what my team did this week" should trigger this skill.
Add `///` doc strings to public objects in Motoko modules so that `mo-doc` produces useful HTML/Markdown documentation. Covers placement rules, formatting, code examples, common pitfalls, and a verification workflow.
Research and discovery workflow for document deliverables — competitive analyses, architecture comparisons, ADR scaffolding, literature reviews, vendor evaluations. No TDD requirement. Phases: gathering → synthesizing → completed. Triggers: 'discover', 'research', 'explore topic', or /discover.
Generate a SYSTEM_OVERVIEW.md that orients a senior engineer new to an unfamiliar codebase, with a Mermaid architecture diagram, a sequence diagram for data flow, and a legacy-pattern assessment. Use when user says 'give me a system overview', 'onboard me on this repo', 'walk me into this legacy codebase', 'document the high-level architecture', or 'create a SYSTEM_OVERVIEW.md'. Do NOT use for code walkthroughs (use explain), persistent architecture chapters (use arc42), or ADRs (use document-decision).
Vellum — Deep navy canvas with warm-yellow italic Cormorant serifs and a single dusty teal accent. A quiet, scholarly aesthetic. Anything that should feel scholarly, literary, and quietly intelligent: research synthesis, white papers, academic and policy briefs, advisory deliverables, longform editorial pieces, founder reflections.
Dada Writing Style Tool. Rewrite any text in Dada's voice and tone. Trigger methods: /dada-style, /style-rewrite, "Help me rewrite in Dada's style" Rewrite any text in Dada's voice and style. Trigger: /dada-style, "rewrite in my style", "change to my style"
Structured, reproducible analysis documentation. Use when documenting analysis findings, creating analysis notebooks, ensuring reproducibility, or building analysis archives for future reference.
Reverse-engineer a SPEC document from an existing project. Analyzes code, config, tests, and structure to produce a comprehensive specification. Triggers on: code-to-spec, reverse spec, generate spec, 逆向规格, 生成规格文档, 生成设计文档, 生成设计方案, extract spec, document this project, what does this project do.
Use when the user wants text to sound more human, says writing sounds "too AI" or "too ChatGPT," asks to humanize or rewrite a draft to feel natural, or shares content wanting it to feel authentic and less robotic. Also applies to LinkedIn posts, blog drafts, or emails where the user wants a more genuine voice.
Write professional press releases in Traditional Chinese (zh-TW) following inverted pyramid structure, 5W1H framework, and Taiwan media conventions. Use when the user wants to: (1) write a press release or news announcement, (2) draft corporate communications for media dissemination, (3) craft a lede or headline for a news release, (4) review or improve press release structure and newsworthiness, (5) write any 新聞稿 or 媒體通知, or (6) format announcements following journalistic standards.
Use when creating or revising model PR optimization history documents for SGLang, vLLM, or another serving framework that cite GitHub PRs. Requires manual, per-PR source-diff review and documentation of motivation, key implementation approach, most important code excerpts, reviewed files, and validation implications instead of generated or one-line summaries.