agentleFS
PierrickMartosPierrickMartos/Leadership-Skills/.claude/skills/update-plugin/SKILL.md

update-plugin

Skill4 starsChanged 7 months agoMITView on GitHub

Update a plugin's README.md and plugin.json after adding new skills or agents. Use when a skill or agent has been added to a domain plugin (e.g. decision-making, communication) and the plugin catalog needs to reflect it.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. odere-pro/claude-software-3-0-marketplace★ 2same name
    2. garbageek/claude-plugins★ 1same name
    3. marinvch/Cortex★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After adding a skill or agent to a domain plugin, update its README.md skills/agents table and bump the version in plugin.json.

    line 8
  2. Distinctive:

    Ask the user (or infer from context):

    line 14
  3. Very specific:

    Read <plugin>/skills/<skill-name>/SKILL.md and extract:

    line 21
  4. Distinctive:

    Read the current README.

    line 27
  5. Distinctive:

    Keep rows sorted alphabetically by name within each table.

    line 51
  6. Very specific:

    Read each file. Increment the patch version (e.g.

    line 55
  7. Very specific:

    Read .claude-plugin/marketplace.json and .cursor-plugin/marketplace.json to confirm the plugin is listed.

    line 59
  8. Very specific:

    Add the new skill row to the table inside the <details> block.

    line 64
  9. Distinctive:

    Write the updated README.md.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Update Plugin

After adding a skill or agent to a domain plugin, update its README.md skills/agents table and bump the version in plugin.json.

Steps

1. Identify what was added

Ask the user (or infer from context):

  • Which plugin? (e.g. decision-making, communication)
  • Was a skill or agent added?
  • What is its name and directory path?

2. Read the SKILL.md (or agent) frontmatter

Read <plugin>/skills/<skill-name>/SKILL.md and extract:

  • name (from frontmatter)
  • description (from frontmatter) — use only the first sentence, trimmed

3. Update <plugin>/README.md

Read the current README.

Update the intro description (the paragraph below the # <plugin> heading): rewrite it to reflect all skills and agents now present in the plugin — not just the one just added. Keep it concise (1–2 sentences), covering the full scope of the plugin.

Add a row to the relevant table:

For skills — update or create a ## Skills section:

## Skills

| Skill | Purpose |
|-------|---------|
| `skill-name` | First sentence of the skill description. |

For agents — update or create an ## Agents section:

## Agents

| Agent | Purpose |
|-------|---------|
| `agent-name` | First sentence of the agent description. |

Keep rows sorted alphabetically by name within each table.

4. Bump patch version in <plugin>/.claude-plugin/plugin.json and <plugin>/.cursor-plugin/plugin.json

Read each file. Increment the patch version (e.g. 1.0.0 → 1.0.1) to the same new value in both. Write both updated files.

5. Update top-level README.md

Read .claude-plugin/marketplace.json and .cursor-plugin/marketplace.json to confirm the plugin is listed. Then read the top-level README.md.

Find the plugin's <details> dropdown in the ## Plugins section. Update:

  • The skill count in the <summary> line — count all skills/*/SKILL.md files in the plugin directory. Use "1 skill" (singular) when count is 1, "N skills" (plural) otherwise.
  • The description in the <summary> line if the plugin's intro description (from step 3) changed.
  • Add the new skill row to the table inside the <details> block.

Also update the total skill count in the subtitle line (e.g. 11 leadership skills for Claude Code, Cursor, and Claude Cowork.). Count all skills/*/SKILL.md files across all plugin directories to get the new total.

Write the updated README.md.

6. Confirm

Report:

  • Updated intro description
  • Which README rows were added
  • New version in plugin.json
  • Whether top-level README.md was updated

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.