New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Loop Design

by HHU3637kr in HHU3637kr/skills

帮助用户把一个重复性任务设计成一个有边界的 Loop（运行契约 + 预算），并产出一份可复用的 loop 定义文档. An agent skill from HHU3637kr/skills.

No licenceAuto-check passed

Install Loop Design

skills CLI
$ npx skills add HHU3637kr/skills --skill loop-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HHU3637kr/skills loop-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/loop-design .claude/skills/loop-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
loop-design
GitHub stars
145
Token cost
~857 tokens
SKILL.md length
234 words
Files
2 (incl. references)
Skills in repo
37
Repo updated
First seen
Licence
None found

At a glance

帮助用户把一个重复性任务设计成一个有边界的 Loop（运行契约 + 预算），并产出一份可复用的 loop 定义文档. An agent skill from HHU3637kr/skills.

  • Works in 5 steps: 先刹车，后循环：停止条件和升级条件是必填项，不是可选项。一个没有停止条件的… → 只产出定义，不驱动执行：loop-design… → 复用 intent-confirmation 做澄清：目标和边界的对齐交给… → …
  • SKILL.md covers 运行契约, 核心原则, Loop 的两种类型 and 工作流程, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Loop Design is an agent skill from HHU3637kr/skills. 帮助用户把一个重复性任务设计成一个有边界的 Loop（运行契约 + 预算），并产出一份可复用的 loop 定义文档。 触发条件：(1) 用户想为某类反复执行的任务建立一个受控循环（"每次都这样跑""反复打磨直到满足 X"）， (2) 用户想为某个 R&K Flow Spec 定制阶段路径或修复循环预算， (3) 用户问"帮我写一个 loop / 设计一个循环"。 本 Skill 只负责交互式产出 loop 定义，不负责驱动执行。执行由对应的工作流 Skill 或用户自己承担。 不要用于一次性任务、简单问答，或已有明确 Spec 可直接执行的场景。

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/loop-definition-template.md`).

Example prompts

  • “每次都这样跑”
  • “反复打磨直到满足 X”
  • “帮我写一个 loop / 设计一个循环”
  • “/loop-design”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 先刹车，后循环：停止条件和升级条件是必填项，不是可选项。一个没有停止条件的 loop 不允许产出。
  2. 只产出定义，不驱动执行：loop-design 的产物是一份"定义"，谁来跑、怎么跑由对应工作流 Skill 或用户决定。
  3. 复用 intent-confirmation 做澄清：目标和边界的对齐交给 intent-confirmation，本 Skill 专注把共识结构化成 loop 定义。
  4. 预算来自用户：循环次数、无进展轮数等上限不写死，由用户在定义时确认。
  5. 能复用 R&K 内核就复用：loop 定义骨架与各 Skill 头部的「运行契约」表同构，便于和 R&K Flow 衔接。

What it can do on your machine

Read from SKILL.md and the folder at commit a2cccf6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Loop Design loads about 857 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~857
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 234 words (~857 tokens).

name
loop-design
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in loop-design of HHU3637kr/skills.

  • SKILL.md
  • references/loop-definition-template.md

Open the folder on GitHubat commit a2cccf6

Compare with similar skills

Loop Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Loop Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Loop Design this skillHHU3637kr/skills145—~857Automated safety check: PassNone
Blueprintaffaan-m/ECC275k2 repos~604Automated safety check: PassMIT
Token Budget Advisoraffaan-m/ECC275k—~927Automated safety check: PassMIT
Logic Thinker Coachdigoal/blog8.6k—~941Automated safety check: PassGPL-2.0
Article Fact Checkerdigoal/blog8.6k—~956Automated safety check: PassGPL-2.0
Industry Insight Writerdigoal/blog8.6k—~578Automated safety check: PassGPL-2.0

Similar skills

  • Blueprint

    affaan-m/ECC

    将单行目标转化为多会话、多代理工程项目的分步构建计划。每个步骤包含独立的上下文简介，以便新代理能直接执行。包括对抗性审查门、依赖图、并行步骤检测、反模式目录和计划突变协议。触发条件：当用户请求复杂多PR任务的计划、蓝图或路线图，或描述需要多个会话的工作时。不触发条件：任务可在单个PR或少于3个工具调用中完成，或用户说“直接执行”时。

    275k GitHub starsUsed in 2 repos~604 tokens
    DevelopmentAuto-check passed

  • Token Budget Advisor

    affaan-m/ECC

    在回答前，为用户提供关于消耗多少响应深度的知情选择。当用户明确希望控制响应长度、深度或令牌预算时使用此技能。触发条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed…

    275k GitHub stars~927 tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed

  • Logic Thinker Coach

    digoal/blog

    通过持续的对话式提问，训练用户的逻辑思维与独立思考能力：给用户出思考题、用苏格拉底式追问引导用户自己发现漏洞、对用户的每次回复做点评并给出具体改进意见，同时把训练记录和薄弱点保存到 markdown，用于后续对话中做针对性、渐进式的训练。触发条件：用户提到"训练我的逻辑思维"、"锻炼独立思考"、"陪我练逻辑"、"logic…

    8.6k GitHub stars~941 tokensUpdated 10 days ago
    Auto-check passed

  • Article Fact Checker

    digoal/blog

    逐段逐句鉴定一篇文章内容的真伪，拆解论证结构，对每个事实/推断节点做六维核查（逻辑正确性、结论可量化性、证据链完整性、证据是否捏造、证据可考证性、来源可信度），最后输出带原文定位的问题清单和置信度打分表。触发条件：用户提到"鉴别真伪"、"这篇文章可信吗"、"内容审查"、"事实核查"、"fact…

    8.6k GitHub stars~956 tokensUpdated 10 days ago
    Documents & OfficeAuto-check passed

  • Industry Insight Writer

    digoal/blog

    以第三方中立研究顾问身份，围绕某个行业近1个月内的最新动态，撰写适合公众号发布的简短深度文章（不超过4屏手机阅读）。触发条件：用户输入行业名称并希望生成行业洞察文章，提到"帮我写篇XX行业的文章"、"分析一下XX行业最近的动态"、"以顾问角度写XX"、"行业观察"、"行业跟踪"、"行业洞察"、"帮我写XX行业报告"、"XX行业近期发展"等。即使用户只说"帮我写一篇关于XX行业的文章"，只要意图是…

    8.6k GitHub stars~578 tokensUpdated 10 days ago
    Documents & OfficeAuto-check passed

  • Good Ask

    digoal/blog

    给定一个行业，围绕该行业提出若干个"好问题"（只提问、不给答案，但每个问题要配"为什么这是个好问题"的理由）。触发条件：用户提到"帮我想几个好问题"、"这个行业有什么值得问的问题"、"帮我出选题"、"行业狗皮膏药问题"、"行业老大难问题"、"近期热点问题"、"帮我策划几个话题"、"这个行业值得深挖的问题有哪些"、"good…

    8.6k GitHub stars~946 tokensUpdated 10 days ago
    Auto-check passed

More from HHU3637kr/skills

All 37 skills in this repo

  • Gif Sticker Maker

    HHU3637kr/skills

    Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions.

    145 GitHub starsUsed in 4 repos~1.3k tokens
    Auto-check passed

  • Agent Browser

    HHU3637kr/skills

    Headless browser automation for AI agents using agent-browser CLI.

    145 GitHub stars~1.9k tokensUpdated 15 days ago
    Auto-check passed

  • Darwin Skill

    HHU3637kr/skills

    Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch.

    145 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

  • Token Efficiency

    HHU3637kr/skills

    Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider).

    145 GitHub stars~842 tokensUpdated 15 days ago
    Auto-check passed

  • Guizang Ppt Skill

    HHU3637kr/skills

    生成横向翻页网页 PPT（单 HTML 文件），含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格：① "电子杂志 × 电子墨水"（衬线 + 流体背景 + 暖色） ② "瑞士国际主义"（无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮）。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT，或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss…

    145 GitHub starsUsed in 1 repo~4.7k tokens
    Auto-check passed

  • Huashu Nuwa

    HHU3637kr/skills

    女娲造人：输入人名/主题/甚至只是模糊需求，自动深度调研→思维框架提炼→生成可运行的人物Skill. An agent skill from HHU3637kr/skills.

    145 GitHub starsUsed in 1 repo~4k tokens
    Auto-check passed

Questions about Loop Design

What does Loop Design do?

帮助用户把一个重复性任务设计成一个有边界的 Loop（运行契约 + 预算），并产出一份可复用的 loop 定义文档. An agent skill from HHU3637kr/skills. Loop Design is an agent skill from HHU3637kr/skills.

How do I install Loop Design in Claude Code?

Run `npx skills add HHU3637kr/skills --skill loop-design -a claude-code`. Or copy the skill folder (loop-design in HHU3637kr/skills) into .claude/skills/loop-design in your project. Claude Code loads it when a task matches its description.

How do I install Loop Design in Codex?

Run `npx skills add HHU3637kr/skills --skill loop-design -a codex`. Or copy the skill folder (loop-design in HHU3637kr/skills) into .agents/skills/loop-design in your project. Codex loads it when a task matches its description.

Can I use Loop Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HHU3637kr/skills --skill loop-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loop-design, .gemini/skills/loop-design, .github/skills/loop-design and .opencode/skills/loop-design in your project.

What does Loop Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Loop Design is instructions for the agent only.

Does Loop Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Loop Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Loop Design use?

No licence was found for Loop Design or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Loop Design use?

About 857 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 791 tokens, read only when the agent opens those files.

What are the alternatives to Loop Design?

Skills that share tags, products or a category with Loop Design: Blueprint (affaan-m/ECC, 275k stars), Token Budget Advisor (affaan-m/ECC, 275k stars), Logic Thinker Coach (digoal/blog, 8.6k stars) and Article Fact Checker (digoal/blog, 8.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Loop Design?

HHU3637kr (a GitHub user) maintains it in HHU3637kr/skills, which has 145 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on September 23, 2026.

Source: HHU3637kr/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.