跳到正文
cccskills
免费在 GitHub 公开

readme-updater

Update the root README.md with entries for new or changed agent companies. Use when a new company has been added to the repo, when company details have changed (agents added/removed, skills added/removed), or when the user asks to refresh/sync the README. Triggers on: "update the readme", "add this company to the readme", "sync readme", "refresh readme", or after creating a new company with company-creator.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md4.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

README Updater

Update the root README.md to reflect all companies in the repo, matching the established format.

Workflow

1. Discover companies

List all top-level directories that contain a COMPANY.md file. Skip default/, skills/, and any dotfile directories.

2. Gather data for each company

For each company directory, collect:

  • Name and description — from COMPANY.md YAML frontmatter (name) and the prose body (first paragraph after the frontmatter closing ---)
  • Upstream source — from the Generated from [name](url) line at the bottom of COMPANY.md. Extract both the display name and the URL
  • Agents — list subdirectories under agents/. Count them. Format agent names by replacing hyphens with spaces and title-casing
  • Skills — list skills/*/SKILL.md files. Count them. Use the directory name as the skill name

3. Generate org chart image

For each company that does NOT already have an images/org-chart.png, generate one:

~/paperclip scripts/generate-company-assets.ts <company-directory>

If the image already exists and the company hasn't changed, skip regeneration. If the user explicitly asks to regenerate, run it again.

4. Write the README

Replace the ## Companies section in README.md with entries for every discovered company. Preserve all other sections (## Structure, ## Shared Skills, ## Usage, etc.) exactly as they are.

Entry format

Each company entry MUST follow this exact format:

### [Company Name](./<directory-name>)

```bash
npx companies.sh add paperclipai/companies/<directory-name>
```

<One-sentence description from COMPANY.md body. Keep it concise — one to two sentences max.> Built from [upstream name](upstream-url).

![Company Name Org Chart](./<directory-name>/images/org-chart.png)

> **Agents (N):** Agent One, Agent Two, Agent Three (limit to 25 "and N more")
>
> **Skills (N):** skill-one, skill-two, skill-three (limit to 25 "and N more")

Rules:

  • The heading links to the company directory
  • The description is a brief summary, NOT the full COMPANY.md body
  • The upstream source link comes from the "Generated from" line in COMPANY.md. Append it naturally to the description sentence (e.g., "Built from gstack.")
  • The org chart image path is always ./<dir>/images/org-chart.png
  • Agent names are title-cased with hyphens replaced by spaces
  • Skill names stay hyphenated (as directory names)
  • Agent and skill counts go in parentheses after the label
  • If a company has no skills directory or no skills, omit the Skills line

Index table

Before the ## Companies heading, include a summary index table:

| Company                         | Agents | Skills | Source        |
| ------------------------------- | ------ | ------ | ------------- |
| [Company Name](#heading-anchor) | N      | N      | [source](url) |
  • The Company column links to the heading anchor (lowercase, hyphens for spaces)
  • Skills column shows — if the company has no skills
  • Table order matches the company entry order below

Ordering

The first three companies are always GStack, Superpowers Dev Shop, and Agency Agents, in that order. Remaining companies follow alphabetically by directory name. Place default last if it is included.

Naming overrides

Some companies use a display name different from their COMPANY.md name field. Always apply these overrides:

  • agency-agents directory → display as Agency Agents (not "The Agency")

5. Verify

After writing, read back the README and confirm:

  • Every company directory with a COMPANY.md has an entry
  • No company entries exist for directories that were removed
  • All image paths point to files that exist
  • Agent and skill counts match actual directory contents

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

adaptyv

免费

Protein engineering and directed evolution analysis using Adaptyv Bio platform

中文简介正在准备中。当前显示原文说明。

paperclipai/companies9292026年3月24日 更新

aeon

免费

Time series analysis and temporal pattern detection for scientific data

中文简介正在准备中。当前显示原文说明。

paperclipai/companies9292026年3月24日 更新

Financial market data retrieval and analysis via Alpha Vantage API

中文简介正在准备中。当前显示原文说明。

paperclipai/companies9292026年3月24日 更新

Query AlphaFold protein structure predictions database

中文简介正在准备中。当前显示原文说明。

paperclipai/companies9292026年3月24日 更新

Generates Angular 17+ standalone components, configures advanced routing with lazy loading and guards, implements NgRx state management, applies RxJS patterns, and optimizes bundle performance.

中文简介正在准备中。当前显示原文说明。

paperclipai/companies9292026年3月24日 更新

anndata

免费

Annotated data matrix operations for single-cell genomics using AnnData

中文简介正在准备中。当前显示原文说明。

paperclipai/companies9292026年3月24日 更新

查看 paperclipai 的全部技能

报告此技能的问题