bushiershi: 对抗模型输出不良表达习惯的 Agent Skill

How to install bushiershi

npx skills add jinhanbuilds/bushiershi --skill bushiershi -y

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 53/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

About bushiershi

不是而是 是一个对抗模型输出不良表达习惯的 Agent Skill。 它仅在明确调用 时生效。 它从哪里来 我用了三年多 GPT。过去几个月，我把真实任务里反复纠正的表达问题整理成了这个 Skill。 阅读「不是而是」的由来 人话的底层思路 人话感来自内容本身：具体对象、真实动作、清楚的关系和有依据的判断，比模仿口语、短句或某种“像人”的语气更重要。 AI 味常常是一种写作动作：问题不只出在某几个词，还出在模型怎样组织结论、制造完整感、补意义和结束一段话。 改得顺不能以失真为代价：更短、更直接的文字，如果改变了事实、程度、归因或不确定性，只是更自信的误写。 只控制最终成稿：这个 Skill 处理读者实际看到的文字，不承担 Agent 全部思维、协作和任务推进方式。 快速使用 一键安装 在希望使用该 Skill 的 Git 项目目录中执行： 该命令会把 Skill 安装到当前项目的 。...

Compatible Skills

These tools work well together with bushiershi for enhanced workflows:

• writing-agent — semantic(0.55)+complementary+shared_fw(openai)+rare_topics+similar_pop (67%)
• clarity — semantic(0.68)+complementary+rare_topics+similar_pop (63%)
• chinese-longnovel-skill — semantic(0.54)+complementary+rare_topics+similar_pop+shared_platform (63%)
• ZeroSlop — semantic(0.48)+complementary+rare_topics+similar_pop+shared_platform (61%)

bushiershi alternative? Top 6 similar tools

Looking for a bushiershi alternative? If you're comparing bushiershi with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

• sun-style-writing by KKKKhazix · ⭐ 248

  从孙割19年白月光的痛彻心扉中蒸馏出来的无上心法

• claudepro-directory by JSONbored · ⭐ 217

  HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

• notion-mcp-server by awkoy · ⭐ 177

  Notion MCP server with token auth: connect Claude Code, Claude Desktop, Cursor, VS Code and Codex to Notion pa

• agent-designer by appautomaton · ⭐ 130

  Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor

• zh-humanizer-literary by mengke-wang · ⭐ 81

  中文去 AI 味与文采增强 Codex Skill，汲取 Mengke / 好事风格，让中文草稿更像人写。

• deepcontext-mcp by Wildcard-Official · ⭐ 278

  DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

More Codex Skill Tools

Explore other popular codex skill tools:

• superset ⭐ 15.5k
• humanizer ⭐ 57.5k
• refly ⭐ 7.5k
• nano-banana-pro-prompts-recommend-skill ⭐ 1.9k
• pi-skills ⭐ 2.5k
• skillkit ⭐ 1.5k
• ai-maestro ⭐ 831
• upskill ⭐ 762
• Claude-to-IM-skill ⭐ 2.9k
• learning-opportunities ⭐ 2.4k

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

• SlowMist agent-security taxonomy
• Liu et al., An Empirical Study of Agent Skill Security (2026)
• Our census dataset (DOI 10.5281/zenodo.21292799) · Hugging Face mirror
• How we grade: all 42 rules, the source tiers and known limits
• Full methodology & who runs this