菜单
Render prose responses in bionic reading style by bolding the leading portion of each word, leaving code, paths, and commands untouched. Use when the user asks for bionic reading / bionic mode / bold-prefix formatting, or to toggle it off ("stop bionic", "normal formatting").
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | bionic-reading |
| description | Render prose responses in bionic reading style by bolding the leading portion of each word, leaving code, paths, and commands untouched. Use when the user asks for bionic reading / bionic mode / bold-prefix formatting, or to toggle it off ("stop bionic", "normal formatting"). |
Format conversational prose so the eye fixates on word openings: bold the
leading portion of each word using markdown **…**.
This is a sticky mode. Once invoked, apply bionic formatting to every prose response for the rest of the session. Stop only when the user says something like "stop bionic", "normal formatting", "turn it off", or disables the skill. Acknowledge on/off transitions in one short normal line before resuming the requested mode.
For each word, bold the first ceil(length × 0.45) letters, minimum 1:
the → the, is → is)word → word, guide → guide)portion → portion, formatting → formatting)Count only alphabetic letters; attach trailing punctuation outside the bold
(word. → word., not word.). Apply to paragraph text, list item
prose, blockquotes, and table cell prose. Headings stay plain.
These break or become unreadable if ** is injected — emit them exactly as-is:
pnpm install, --force)When prose and code mix in one sentence, bionic-format the prose words and pass the code token through untouched:
Run
pnpm testbefore you commit the change.
Input idea: "Bionic reading bolds the leading portion of each word to guide the eye."
Output:
Bionic reading bolds the leading portion of each word to guide the eye.
Every word gains ** markers, increasing token usage. Keep responses as
concise as the task allows; do not pad prose just to show off formatting.
Analyze staged/unstaged changes and create a git commit that follows the project's detected conventions. Use when the user asks to commit, create a commit, or save changes to git. Push only if the user explicitly says "then push" in the same request.
Resolve git merge conflicts by semantically merging both sides of each conflict. Use when the user has merge conflicts, asks to resolve conflicts, or is stuck in a merge/rebase with conflict markers.
Review and freshen all documentation and notes in the current project — discover and obey the project's own doc conventions, fix drift, flag quality gaps, and fill genuinely missing context. Use when the user asks to update docs, freshen documentation, audit AGENTS.md/rules, or clean up notes.
Iteratively review and simplify uncommitted changes until clean or stuck. Use when the user asks to polish, clean up, or iteratively improve uncommitted code changes.
Run the full wrap-up pipeline — polish, then docs-revise, then a single commit — in one deliberate pass. Use ONLY when the user explicitly asks to run polish, docs-revise, and commit together as one pipeline (e.g. "/ship", "polish docs-revise and commit", "wrap this up and ship it"). Do NOT auto-trigger for a plain "clean this up", "commit", "polish", or "update docs" request — those are the individual skills.
Writing voice profile for AI-drafted communication. Provides channel-specific style samples and anti-patterns under profiles/ — pick the file matching the output destination (PR comment, chat, commit message, formal email). Use when the user says "draft in my voice", "rewrite this like I'd say it", or another skill needs a consistent writing register. This skill does not know about its consumers.