Create custom skills changedskills/how-to
Nearest release: v2.1.284, published 16 hours after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 28 Sep 2026 00:41 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 22 Oct 2026 18:07 UTC.
Upstream edited
Recorded here
Lines+6added
Lines−6removed
From line
17
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits7to this page, all time
The whole hunk
from line 17, old and new numbered
/
from line 17
1717A skill isn't the right tool for everything:
1818
1919* **A one-off task**: describe what you want in the conversation instead
20* **Live data from another service**: that's what an [MCP connector](/docs/connectors/getting-started) provides. A skill can tell Claude how to use a connector, but it can't reach the service itself
20* **Live data from another service**: that's what an [MCP connector](/docs/connectors/getting-started.md) provides. A skill can tell Claude how to use a connector, but it can't reach the service itself
2121* **Instructions for every conversation**: put those in your [personal preferences or project instructions](https://support.claude.com/en/articles/10185728-understanding-claude-s-personalization-features) rather than a skill, which loads only when a task matches
2222
2323To start, write down the task in one sentence and what a good result looks like. That sentence becomes the skill's `description`, and the rest becomes the instructions. If you'd rather have Claude draft the skill with you, ask it to use the [skill-creator skill](#measure-whether-the-skill-improves-the-output), then edit what it produces.
from line 199
199199
200200In Claude Code, running a script is a Bash tool call, so it needs your permission. When you test with [`claude -p`](https://code.claude.com/docs/en/headless), which can't stop to ask, allow the script on the command line, for example `--allowedTools "Bash(python3 /path/to/my-plugin/skills/render-chart/scripts/render.py *)"`, using the script's absolute path. Claude runs the script by its absolute path, and `Bash()` rules match the whole command line, so a rule that names the exact path approves only that script; a wildcard before the path would approve more than you intend.
201201
202Don't put API keys, passwords, or other credentials in a script or anywhere else in the skill: everyone you share the skill with receives its files. When a script needs to reach an outside service, have Claude use a [connector](/docs/connectors/getting-started) for that service instead, so each person signs in with their own account.
202Don't put API keys, passwords, or other credentials in a script or anywhere else in the skill: everyone you share the skill with receives its files. When a script needs to reach an outside service, have Claude use a [connector](/docs/connectors/getting-started.md) for that service instead, so each person signs in with their own account.
203203
204204## Package your skill
205205
from line 328
328328
329329After your skill works, you can give it to other people on its own or as part of a plugin. People you share it with should be able to read what it does, so keep the instructions and scripts plain enough to review.
330330
331* **Share or publish one skill**: on Team and Enterprise plans, open the skill from **Customize > Skills** and use the same **Share** and **Publish to org** controls that a plugin has. They work the way [sharing a plugin with specific people](/docs/plugins/share#share-a-plugin-with-specific-people) and [publishing a plugin to your organization](/docs/plugins/share#publish-a-plugin-to-your-organization) describe
332* **Package skills and connectors together**: when you want several skills, or a skill plus the connector it uses, installed together, [build a plugin](/docs/plugins/build) that contains them
331* **Share or publish one skill**: on Team and Enterprise plans, open the skill from **Customize > Skills** and use the same **Share** and **Publish to org** controls that a plugin has. They work the way [sharing a plugin with specific people](/docs/plugins/share.md#share-a-plugin-with-specific-people) and [publishing a plugin to your organization](/docs/plugins/share.md#publish-a-plugin-to-your-organization) describe
332* **Package skills and connectors together**: when you want several skills, or a skill plus the connector it uses, installed together, [build a plugin](/docs/plugins/build.md) that contains them
333333
334334## Next steps
335335
336336* [Skills in Claude Code](https://code.claude.com/docs/en/skills): create and test skills from the Claude Code CLI, including the `/skills` manager
337* [Plugin structure and testing](/docs/plugins/build): package your skill as a plugin so other people can install it
338* [Submit your plugin](/docs/plugins/submit): submit the plugin to the directory, where Anthropic reviews it before it's listed
337* [Plugin structure and testing](/docs/plugins/build.md): package your skill as a plugin so other people can install it
338* [Submit your plugin](/docs/plugins/submit.md): submit the plugin to the directory, where Anthropic reviews it before it's listed
339339
No line in this hunk matches that.