Enables a concise reply mode that limits responses to five units when explicitly requested.
- GitHub stars
- 72
- Files
- 13
- Last commit
- Nov 10, 2026
- License
- MIT
- Allowed tools
- —
What does the lov-five skill do?
lov-five enables a concise reply mode that limits responses to five units when explicitly requested.
Summary generated from the skill's SKILL.md.
About the lov-five skill
Developers who need extremely brief interactions can use this skill to restrict an agent's responses to five units or fewer. When a user explicitly requests this concise mode, the agent switches its communication style to provide short, understandable phrases while avoiding unnecessary decorations, preambles, or repetitive summaries. This mode is temporary and applies only to the current session, automatically reverting to standard length responses when the user asks to cancel or provides incompatible requests.
The skill calculates length by counting each Chinese character and punctuation mark as one unit, while continuous English words count as a single unit. It is designed to prioritize essential information, ensuring that tool parameters, code snippets, or critical safety details are never truncated just to meet the length constraint. It relies on Python 3.8+ and PyYAML for profile management and works alongside the lov-branding-consistency dependency to maintain context within the host environment.
What an agent can do with it
- 1Enable ultra-short responsesAsk the agent to switch to a five-unit concise reply mode for quick status updates.
- 2Revert to standard communicationInstruct the agent to stop using the short mode and return to normal length replies.
- 3Summarize information brieflyRequest a summary of a task that stays within the five-unit limit using complete phrases.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the lov-five skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the lov-five skill in Plugin
/plugin marketplace add lovstudio/skills /plugin install general@lovstudio
Install the lov-five skill in Claude Code
~/.claude/skills/lov-five/SKILL.md
$ npx degit lovstudio/skills/skills/five ~/.claude/skills/lov-fiveInstall the lov-five skill in Claude Code (project)
.claude/skills/lov-five/SKILL.md
$ npx degit lovstudio/skills/skills/five .claude/skills/lov-fiveInstall the lov-five skill in Codex
~/.agents/skills/lov-five/SKILL.md
$ npx degit lovstudio/skills/skills/five ~/.agents/skills/lov-fiveInstall the lov-five skill in Gemini CLI
~/.gemini/skills/lov-five/SKILL.md
$ npx degit lovstudio/skills/skills/five ~/.gemini/skills/lov-fiveInstall the lov-five skill in Claude.ai
npx degit lovstudio/skills/skills/five lov-five && zip -r lov-five.zip lov-five # claude.ai → Customize → Skills → + → Create skill → Upload a skill → lov-five.zip
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work · What to fix for more points
- Source repository linked and reachablelovstudio/skills/skills/five is public and reachablegithub.com/lovstudio/skills/tree/HEAD/skills/five ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-10github.com/lovstudio/skills/commits ↗Pass
- No download-and-run or credential theft in scripts2 scripts read; no download-and-run, remote eval, base64 execution or credential uploadPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/lovstudio/skills/blob/HEAD/skills/five/SKILL.md ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/lovstudio/skills/blob/HEAD/skills/five/SKILL.md ↗Pass
- SKILL.md follows the Agent Skills formatname "lov-five" differs from the folder "five"github.com/lovstudio/skills/blob/HEAD/skills/five/SKILL.md ↗Finding
SKILL.md
View on GitHub五字答 · Five-Unit Replies
在明确要求时使用五单位以内的简短回复,并支持随时恢复正常。
Triggers
Activate when
- “在明确要求时使用五单位以内的简短回复,并支持随时恢复正常。”
- “Use a five-unit concise reply mode.”
Do not activate when
- 只是查询本 Skill 的说明,或请求与上述结果无关的任务;不执行实际业务操作。
- 用户仅要预览或审查时,不进入修改、提交或发布分支。
Execution boundary
自然语言请求即可触发;无需旧 slash 路径、参数插值或指定助手。明确解析当前请求中的 项目、目标文件、选项与输出位置;用当前宿主实际提供的文件、搜索、CLI 和浏览器能力。 项目依赖版本与外部 API 在执行时核实,不能假设示例是现行配置。随包脚本从 Skill 根解析, 业务文件从目标项目根解析。先读当前状态,保护已有未提交内容与其他任务的暂存区。 分析、预览请求保持只读;修改、提交、推送、部署和发布各依当前请求的明确范围执行。 不绕过保护、自动发送消息、强制结束用户进程或抢前台。失败保留可诊断原始错误。
Workflow
-
仅用户明确请求五字模式时开启,范围默认当前会话;取消、正常模式或后续不兼容要求即时恢复,不能自动持久化为全局偏好。
-
中文每个字符、标点各计一单位,连续英文单词各计一单位,回复不超过五单位;以完整可理解的短语概括。
-
不截断工具参数、代码、用户原文、必需安全信息或完整交付物以凑字数。必要事实无法容纳时遵循更高优先级的完整沟通要求。
-
工具操作保持原任务范围,五字模式不新增授权。检查最终简答长度,避免装饰、前言与重复总结。
Composition
执行前读取 能力组合,按明确制品交接相邻能力。
Runtime context (shared)
运行前读取本包 skill.yaml 与 Profile 合同。优先级为当前请求、
项目上下文、本 Skill records、共享 preferences、brand/user Profile、安全默认值。
只读取声明字段;没有专用运行时的宿主可使用 scripts/profile_store.py 读取共享 Profile。
配置缺失只问影响结果的一个问题。用户明确要求长期保存的值通过该脚本原子写入,
报告实际路径;不保存推断、凭据或其他任务的资料。
Files in this skill
13lov-five skill questions
How do I install the lov-five skill in Claude Code?
Run npx degit lovstudio/skills/skills/five ~/.claude/skills/lov-five. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the lov-five skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How is the five-unit limit calculated?
In Chinese, each character and punctuation mark counts as one unit, while continuous English words count as one unit per word.
Does this mode affect tool parameters or code?
No, the skill will not truncate tool parameters, code, user original text, or essential security information to meet the character limit.
Is the five-unit mode permanent?
No, it only activates when explicitly requested for the current session and restores to normal mode immediately upon cancellation or incompatible requests.