From writing-and-design
Use by default for any user-facing writing, including answers to users, emails, documents, formal correspondence, reports, proposals, landing-page copy, social posts, essays, commentary, explanations, summaries, product copy, internal updates, and other prose intended to be read by people. Apply it whenever the output contains human-readable text, unless another skill explicitly owns the writing style or the output is purely code, structured data, or a command. Supports Chinese and English.
How this skill is triggered — by the user, by Claude, or both
Slash command
/writing-and-design:human-writingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Treat this as the default prose skill for anything a person will read, including every user-facing answer and any formal or informal document.
Treat this as the default prose skill for anything a person will read, including every user-facing answer and any formal or informal document.
Use it for both rewrite and generate tasks. Aim for writing that sounds like someone meant it, not like a model averaged it.
Apply it by default when the output contains prose intended for a person. Do not force it onto purely technical output such as source code, JSON, SQL, shell commands, or other structured data. If another skill explicitly owns the output's domain structure or style, let that skill drive the content plan and use this skill to shape the final prose.
This file only defines the process. The actual rules live in the reference files, and each workflow step names the file to read at that stage. Read the file at that step and follow it. Do not substitute a remembered summary for the file's content.
Route the task.
Read references/mode-selection-and-language-rules.md.
Decide rewrite or generate, identify the audience and what the text must do, settle language handling, and pick grounded or voiced. The same file then gives the working rules for the mode and style you picked.
Draft or rewrite. Read references/human-writing-principles.md and write under all of its principles. They cover specificity, anchoring actions and objects, zero shared reader context, abstract adjectives and adverbs, argument structure, vocabulary, rhythm, tone, and punctuation.
Calibrate against examples. While drafting or rewriting, consult references/human-writing-examples.md to see what each principle looks like when applied to real sentences, including cases where a first rewrite is still not concrete enough. The scenarios in the examples are only sentence content, not a limit on when this skill applies.
Run a cleanup pass. Read references/ai-writing-patterns.md and remove every artifact it lists from the draft, keeping the meaning, facts, and intent intact.
Final check. Read references/final-checklist.md and run every item against the finished text. Fix whatever fails, then run it again until everything passes.
Use $human-writing to write or rewrite human-facing text so it reads naturally, credibly, and like a person actually meant it.
npx claudepluginhub timlai666/skills --plugin writing-and-designGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.