Extend Claude with skills changedskills
Nearest release: v2.1.283, published 5 hours before 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 26 Sep 2026 00:27 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 28 Sep 2026 23:37 UTC.
Upstream edited
Recorded here
Lines+80added
Lines−80removed
From line
34
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits80to this page, all time
The whole hunk
from line 34, old and new numbered
/
from line 34
3434
3535Three bundled skills work together to launch your app and confirm changes against the running app instead of just tests:
3636
37| Skill | Purpose |
38| :--------------------- | :---------------------------------------------------------------------------------------------------------------- |
39| `/run` | Launch and drive your app to see a change working |
40| `/verify` | Build and run your app to confirm a code change does what it should, without falling back to tests or type checks |
41| `/run-skill-generator` | Teach `/run` and `/verify` how to build and launch your project |
37| Skill | Purpose |
38| :- | :- |
39| `/run` | Launch and drive your app to see a change working |
40| `/verify` | Build and run your app to confirm a code change does what it should, without falling back to tests or type checks |
41| `/run-skill-generator` | Teach `/run` and `/verify` how to build and launch your project |
4242
4343`/run` and `/verify` work without setup. They infer the launch from your project type (CLI, server, TUI, browser-driven) and from what's in your README, `package.json`, or `Makefile`. That inference gets unreliable for projects that need anything beyond a standard launch: a database, an env file, a graphical session, a multi-step build.
4444
from line 110
110110
111111Where you save a skill decides which sessions load it. Save it under your home directory to get it in every project, commit it to a repository to share it with everyone who works there, or distribute it through a plugin or managed settings to reach a whole team.
112112
113| Location | Path | Loads in |
114| :------------------- | :------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
115| Enterprise | `.claude/skills/<skill-name>/SKILL.md` in the [managed settings directory](/docs/en/managed-settings#delivery-mechanisms) | All users on machines where your organization deploys it |
116| Personal | `~/.claude/skills/<skill-name>/SKILL.md` | All your projects on this machine, but not [Cowork or cloud sessions](#skills-in-cowork-and-cloud-sessions) |
117| Project | `.claude/skills/<skill-name>/SKILL.md` | Sessions in this repository. Commit it so your team gets it too |
118| Nested | `<subdir>/.claude/skills/<skill-name>/SKILL.md` | Sessions started in or below `<subdir>`. A session started above it loads the skill once Claude works on files there. See [monorepos and subdirectories](#discovery-from-parent-and-nested-directories) |
119| Additional directory | `.claude/skills/<skill-name>/SKILL.md` in a directory you pass with `--add-dir` | That session. See [directories outside the project](#skills-from-additional-directories) |
120| Plugin | `<plugin>/skills/<skill-name>/SKILL.md` | Wherever the [plugin](/docs/en/plugins/overview) is enabled, as `/plugin-name:skill-name` |
121| claude.ai account | Skills enabled for your claude.ai account | Cowork sessions, cloud sessions, and terminal sessions where you sign in with that account. See [Skills synced from claude.ai](#how-synced-skills-behave) |
113| Location | Path | Loads in |
114| :- | :- | :- |
115| Enterprise | `.claude/skills/<skill-name>/SKILL.md` in the [managed settings directory](/docs/en/managed-settings#delivery-mechanisms) | All users on machines where your organization deploys it |
116| Personal | `~/.claude/skills/<skill-name>/SKILL.md` | All your projects on this machine, but not [Cowork or cloud sessions](#skills-in-cowork-and-cloud-sessions) |
117| Project | `.claude/skills/<skill-name>/SKILL.md` | Sessions in this repository. Commit it so your team gets it too |
118| Nested | `<subdir>/.claude/skills/<skill-name>/SKILL.md` | Sessions started in or below `<subdir>`. A session started above it loads the skill once Claude works on files there. See [monorepos and subdirectories](#discovery-from-parent-and-nested-directories) |
119| Additional directory | `.claude/skills/<skill-name>/SKILL.md` in a directory you pass with `--add-dir` | That session. See [directories outside the project](#skills-from-additional-directories) |
120| Plugin | `<plugin>/skills/<skill-name>/SKILL.md` | Wherever the [plugin](/docs/en/plugins/overview) is enabled, as `/plugin-name:skill-name` |
121| claude.ai account | Skills enabled for your claude.ai account | Cowork sessions, cloud sessions, and terminal sessions where you sign in with that account. See [Skills synced from claude.ai](#how-synced-skills-behave) |
122122
123123Skill folders also follow these rules:
124124
from line 157
157157
158158When two skills share a directory or file name, where each one came from decides which one `/name` runs. For a name set by the frontmatter `name` field, see [How a skill gets its command name](#how-a-skill-gets-its-command-name). The table covers the enterprise, personal, project, nested, plugin, and claude.ai locations, bundled skills, and command files:
159159
160| Same name in | Which one runs |
161| :------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
162| Two of enterprise, personal, and project | Enterprise over personal, and personal over project. With `deploy` in both `~/.claude/skills/` and the project's `.claude/skills/`, `/deploy` runs the personal one |
163| Any of those locations and a [bundled skill](#bundled-skills) | Your skill replaces the bundled command, but not its aliases. A project `code-review` skill replaces `/code-review`, and the bundled alias `/review` never runs your skill |
164| A skill and a file in `.claude/commands/` | The skill |
165| A project-root skill and a nested skill | Both load. See [monorepos and subdirectories](#discovery-from-parent-and-nested-directories) |
166| A plugin skill and a skill at any of the locations above | Both load, because plugin skills are namespaced as `/plugin-name:skill-name` |
160| Same name in | Which one runs |
161| :- | :- |
162| Two of enterprise, personal, and project | Enterprise over personal, and personal over project. With `deploy` in both `~/.claude/skills/` and the project's `.claude/skills/`, `/deploy` runs the personal one |
163| Any of those locations and a [bundled skill](#bundled-skills) | Your skill replaces the bundled command, but not its aliases. A project `code-review` skill replaces `/code-review`, and the bundled alias `/review` never runs your skill |
164| A skill and a file in `.claude/commands/` | The skill |
165| A project-root skill and a nested skill | Both load. See [monorepos and subdirectories](#discovery-from-parent-and-nested-directories) |
166| A plugin skill and a skill at any of the locations above | Both load, because plugin skills are namespaced as `/plugin-name:skill-name` |
167167| Any of the above and the short name of a skill [synced from your claude.ai account](#how-synced-skills-behave) | The other skill or command. The synced skill is then listed and runs only under its full name. See [When a synced skill name matches another command](#when-a-synced-skill-name-matches-another-command) |
168168
169169<h3 id="skills-in-cowork-and-cloud-sessions">
from line 345
345345
346346Boolean fields accept `yes`, `no`, `on`, `off`, `1`, and `0` in any letter case, in addition to `true` and `false`. Before v2.1.218, Claude Code recognized only `true` and `false`.
347347
348| Field | Required | Description |
349| :------------------------- | :---------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
350| `name` | No | Command name shown in the `/` menu. Defaults to the directory name. See [How a skill gets its command name](#how-a-skill-gets-its-command-name) for how the field interacts with the name you type to invoke the skill. |
351| `description` | Recommended | What the skill does and when to use it. Claude uses this to decide when to apply the skill. If omitted, uses the first non-empty line of the markdown content. Put the key use case first: the combined `description` and `when_to_use` text is truncated at 1,536 characters in the skill listing to reduce context usage. |
352| `when_to_use` | No | Additional context for when Claude should invoke the skill, such as trigger phrases or example requests. Appended to `description` in the skill listing and counts toward the 1,536-character cap. |
353| `argument-hint` | No | Hint shown during autocomplete to indicate expected arguments. Example: `[issue-number]` or `[filename] [format]`. |
354| `arguments` | No | Named positional arguments for [`$name` substitution](#available-string-substitutions) in the skill content. Accepts a space-separated string or a YAML list. Names map to argument positions in order. |
355| `disable-model-invocation` | No | Set to `true` to prevent Claude from automatically loading this skill. Use for workflows you want to trigger manually with `/name`. Also prevents the skill from being [preloaded into subagents](/docs/en/sub-agents#preload-skills-into-subagents). As of v2.1.196, also prevents the skill from running when a [scheduled task](/docs/en/scheduled-tasks) fires with the skill as its prompt. Default: `false`. |
356| `user-invocable` | No | Set to `false` when only Claude should invoke the skill: Claude Code hides it from the `/` menu and doesn't run it when you type `/name`. Use for background knowledge users shouldn't invoke directly. Default: `true`. |
357| `allowed-tools` | No | Tools Claude can use without asking permission during the turn that invokes this skill. The grant clears when you send your next message. Accepts a space- or comma-separated string, or a YAML list. See [Pre-approve tools for a skill](#pre-approve-tools-for-a-skill). |
358| `disallowed-tools` | No | Tools removed from Claude's available pool while this skill is active. Use for autonomous skills that should never call certain tools, such as `AskUserQuestion` for a background loop. Accepts a space- or comma-separated string, or a YAML list. The restriction clears when you send your next message. Like deny rules, the field can't remove [`EndConversation`](/docs/en/tools-reference#endconversation-tool-behavior) while any other tool remains. |
359| `model` | No | Model to use when this skill is active. The override applies for the rest of the current turn and isn't saved to settings. The session model resumes when you send your next prompt. Accepts the same values as [`/model`](/docs/en/model-config), or `inherit` to keep the active model. A value excluded by your organization's [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist isn't used, and the session keeps its current model. In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), and in [plan mode while the classifier reviews commands](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), a model that auto mode doesn't support also isn't used, and the session keeps its current model. With `context: fork`, the value sets the [forked subagent's model](#run-skills-in-a-subagent) instead, and an excluded value follows the [same rules as a subagent model override](/docs/en/model-config#restrict-model-selection). |
360| `effort` | No | [Effort level](/docs/en/model-config#adjust-effort-level) when this skill is active. Overrides the session effort level. Default: inherits from session. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. |
361| `context` | No | Set to `fork` to run in a forked subagent context. See [Run skills in a subagent](#run-skills-in-a-subagent). |
362| `agent` | No | Which subagent type to use when `context: fork` is set. |
363| `background` | No | Only applies with `context: fork`. Set to `false` to wait for the forked subagent's result in the turn that invoked the skill, instead of [running it in the background](#run-skills-in-a-subagent). Default: `true`. Requires Claude Code v2.1.218 or later. |
364| `hooks` | No | Hooks that Claude Code registers when the skill is invoked and keeps running for the rest of the session. See [Hooks in skills and agents](/docs/en/hooks#hooks-in-skills-and-agents) for the configuration format and the `once` option. |
365| `paths` | No | Glob patterns that limit when this skill is activated. Accepts a comma-separated string or a YAML list. When set, Claude loads the skill automatically only when working with files matching the patterns. Uses the same format as [path-specific rules](/docs/en/memory#path-specific-rules). |
366| `shell` | No | Shell to use for `` !`command` `` and ` ```! ` blocks in this skill. Accepts `bash` (default) or `powershell`. Setting `powershell` runs inline shell commands via PowerShell when the [PowerShell tool](/en/tools-reference#powershell-tool) is enabled: it's on by default on Windows without Git Bash, on by default with Git Bash for claude.ai and Console accounts, and needs `CLAUDE_CODE_USE_POWERSHELL_TOOL=1` in Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry sessions and on macOS, Linux, and WSL. Set it to `0` to turn the tool off. |
367| `metadata` | No | Free-form YAML map for your own key-value data, such as entitlement or catalog fields, read by your own tooling from `SKILL.md`. Claude Code doesn't act on its contents, and drops a value that isn't a map. Don't reuse frontmatter field names such as `paths` as keys. |
368| `license` | No | License covering the skill. Part of the [Agent Skills](https://agentskills.io) spec; see [Using skill frontmatter outside Claude Code](#using-skill-frontmatter-outside-claude-code). Claude Code accepts the field but doesn't act on it. |
369| `compatibility` | No | Environment requirements for the skill, such as intended products or system prerequisites, as defined by the [Agent Skills](https://agentskills.io) spec; see [Using skill frontmatter outside Claude Code](#using-skill-frontmatter-outside-claude-code). Accepts a string of up to 500 characters. Claude Code accepts the field but doesn't act on it. |
348| Field | Required | Description |
349| :- | :- | :- |
350| `name` | No | Command name shown in the `/` menu. Defaults to the directory name. See [How a skill gets its command name](#how-a-skill-gets-its-command-name) for how the field interacts with the name you type to invoke the skill. |
351| `description` | Recommended | What the skill does and when to use it. Claude uses this to decide when to apply the skill. If omitted, uses the first non-empty line of the markdown content. Put the key use case first: the combined `description` and `when_to_use` text is truncated at 1,536 characters in the skill listing to reduce context usage. |
352| `when_to_use` | No | Additional context for when Claude should invoke the skill, such as trigger phrases or example requests. Appended to `description` in the skill listing and counts toward the 1,536-character cap. |
353| `argument-hint` | No | Hint shown during autocomplete to indicate expected arguments. Example: `[issue-number]` or `[filename] [format]`. |
354| `arguments` | No | Named positional arguments for [`$name` substitution](#available-string-substitutions) in the skill content. Accepts a space-separated string or a YAML list. Names map to argument positions in order. |
355| `disable-model-invocation` | No | Set to `true` to prevent Claude from automatically loading this skill. Use for workflows you want to trigger manually with `/name`. Also prevents the skill from being [preloaded into subagents](/docs/en/sub-agents#preload-skills-into-subagents). As of v2.1.196, also prevents the skill from running when a [scheduled task](/docs/en/scheduled-tasks) fires with the skill as its prompt. Default: `false`. |
356| `user-invocable` | No | Set to `false` when only Claude should invoke the skill: Claude Code hides it from the `/` menu and doesn't run it when you type `/name`. Use for background knowledge users shouldn't invoke directly. Default: `true`. |
357| `allowed-tools` | No | Tools Claude can use without asking permission during the turn that invokes this skill. The grant clears when you send your next message. Accepts a space- or comma-separated string, or a YAML list. See [Pre-approve tools for a skill](#pre-approve-tools-for-a-skill). |
358| `disallowed-tools` | No | Tools removed from Claude's available pool while this skill is active. Use for autonomous skills that should never call certain tools, such as `AskUserQuestion` for a background loop. Accepts a space- or comma-separated string, or a YAML list. The restriction clears when you send your next message. Like deny rules, the field can't remove [`EndConversation`](/docs/en/tools-reference#endconversation-tool-behavior) while any other tool remains. |
359| `model` | No | Model to use when this skill is active. The override applies for the rest of the current turn and isn't saved to settings. The session model resumes when you send your next prompt. Accepts the same values as [`/model`](/docs/en/model-config), or `inherit` to keep the active model. A value excluded by your organization's [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist isn't used, and the session keeps its current model. In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), and in [plan mode while the classifier reviews commands](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), a model that auto mode doesn't support also isn't used, and the session keeps its current model. With `context: fork`, the value sets the [forked subagent's model](#run-skills-in-a-subagent) instead, and an excluded value follows the [same rules as a subagent model override](/docs/en/model-config#restrict-model-selection). |
360| `effort` | No | [Effort level](/docs/en/model-config#adjust-effort-level) when this skill is active. Overrides the session effort level. Default: inherits from session. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. |
361| `context` | No | Set to `fork` to run in a forked subagent context. See [Run skills in a subagent](#run-skills-in-a-subagent). |
362| `agent` | No | Which subagent type to use when `context: fork` is set. |
363| `background` | No | Only applies with `context: fork`. Set to `false` to wait for the forked subagent's result in the turn that invoked the skill, instead of [running it in the background](#run-skills-in-a-subagent). Default: `true`. Requires Claude Code v2.1.218 or later. |
364| `hooks` | No | Hooks that Claude Code registers when the skill is invoked and keeps running for the rest of the session. See [Hooks in skills and agents](/docs/en/hooks#hooks-in-skills-and-agents) for the configuration format and the `once` option. |
365| `paths` | No | Glob patterns that limit when this skill is activated. Accepts a comma-separated string or a YAML list. When set, Claude loads the skill automatically only when working with files matching the patterns. Uses the same format as [path-specific rules](/docs/en/memory#path-specific-rules). |
366| `shell` | No | Shell to use for `` !`command` `` and ` ```! ` blocks in this skill. Accepts `bash` (default) or `powershell`. Setting `powershell` runs inline shell commands via PowerShell when the [PowerShell tool](/en/tools-reference#powershell-tool) is enabled: it's on by default on Windows without Git Bash, on by default with Git Bash for claude.ai and Console accounts, and needs `CLAUDE_CODE_USE_POWERSHELL_TOOL=1` in Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry sessions and on macOS, Linux, and WSL. Set it to `0` to turn the tool off. |
367| `metadata` | No | Free-form YAML map for your own key-value data, such as entitlement or catalog fields, read by your own tooling from `SKILL.md`. Claude Code doesn't act on its contents, and drops a value that isn't a map. Don't reuse frontmatter field names such as `paths` as keys. |
368| `license` | No | License covering the skill. Part of the [Agent Skills](https://agentskills.io) spec; see [Using skill frontmatter outside Claude Code](#using-skill-frontmatter-outside-claude-code). Claude Code accepts the field but doesn't act on it. |
369| `compatibility` | No | Environment requirements for the skill, such as intended products or system prerequisites, as defined by the [Agent Skills](https://agentskills.io) spec; see [Using skill frontmatter outside Claude Code](#using-skill-frontmatter-outside-claude-code). Accepts a string of up to 500 characters. Claude Code accepts the field but doesn't act on it. |
370370
371371#### Using skill frontmatter outside Claude Code
372372
373373Claude Code accepts every field in the table above. Outside Claude Code, you can use only the fields in the [Agent Skills](https://agentskills.io) spec:
374374
375| Distribution path | Frontmatter fields you can use |
376| :-------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------- |
377| Claude Code skills at [any level](#where-skills-live), including [plugin](/docs/en/plugins/overview) skills | Every field in the table above |
375| Distribution path | Frontmatter fields you can use |
376| :- | :- |
377| Claude Code skills at [any level](#where-skills-live), including [plugin](/docs/en/plugins/overview) skills | Every field in the table above |
378378| claude.ai skill uploads, the Skills API, and packaging with `package_skill.py` from [anthropics/skills](https://github.com/anthropics/skills) | `name`, `description`, `license`, `compatibility`, `metadata`, `allowed-tools` |
379379
380380When you enable a personal skill for your claude.ai account, for example to use it in [Cowork and cloud sessions](#skills-in-cowork-and-cloud-sessions) and routines, you upload it to claude.ai, so the same rules apply.
from line 393
393393
394394The table below shows where the command name comes from for each layout:
395395
396| Skill location | Command name source | Example |
397| :----------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------- |
398| Skill directory under `~/.claude/skills/` or `.claude/skills/` | Frontmatter `name` or the directory name | `.claude/skills/deploy-staging/SKILL.md` → `/deploy-staging`, or `/deploy` with `name: deploy` |
399| [Nested](#where-skills-live) `.claude/skills/` directory, when the directory name clashes with another skill | Subdirectory path relative to the working directory, then the skill directory name | `apps/web/.claude/skills/deploy/SKILL.md` → `/apps/web:deploy` |
400| File under `.claude/commands/` | File name without extension | `.claude/commands/deploy.md` → `/deploy` |
401| File in a subdirectory of `.claude/commands/` | Subdirectory path relative to `commands/` with each `/` replaced by `:`, then the file name without extension | `.claude/commands/frontend/component.md` → `/frontend:component` |
402| Plugin `skills/` subdirectory | Frontmatter `name` or the directory name, namespaced by plugin | `my-plugin/skills/review/SKILL.md` → `/my-plugin:review`, or `/my-plugin:fancy` with `name: fancy` |
403| Plugin root `SKILL.md` | Frontmatter `name`, with the plugin directory name as a fallback | `my-plugin/SKILL.md` with `name: review` → `/my-plugin:review`. See [a single skill at the plugin root](/docs/en/plugins/components#skills) |
404| Skill [synced from claude.ai](#how-synced-skills-behave) | The skill's name on your claude.ai account, prefixed with `anthropic-skills:` | Account skill `deploy` → `/anthropic-skills:deploy`, or `/deploy` while no other command uses that name |
396| Skill location | Command name source | Example |
397| :- | :- | :- |
398| Skill directory under `~/.claude/skills/` or `.claude/skills/` | Frontmatter `name` or the directory name | `.claude/skills/deploy-staging/SKILL.md` → `/deploy-staging`, or `/deploy` with `name: deploy` |
399| [Nested](#where-skills-live) `.claude/skills/` directory, when the directory name clashes with another skill | Subdirectory path relative to the working directory, then the skill directory name | `apps/web/.claude/skills/deploy/SKILL.md` → `/apps/web:deploy` |
400| File under `.claude/commands/` | File name without extension | `.claude/commands/deploy.md` → `/deploy` |
401| File in a subdirectory of `.claude/commands/` | Subdirectory path relative to `commands/` with each `/` replaced by `:`, then the file name without extension | `.claude/commands/frontend/component.md` → `/frontend:component` |
402| Plugin `skills/` subdirectory | Frontmatter `name` or the directory name, namespaced by plugin | `my-plugin/skills/review/SKILL.md` → `/my-plugin:review`, or `/my-plugin:fancy` with `name: fancy` |
403| Plugin root `SKILL.md` | Frontmatter `name`, with the plugin directory name as a fallback | `my-plugin/SKILL.md` with `name: review` → `/my-plugin:review`. See [a single skill at the plugin root](/docs/en/plugins/components#skills) |
404| Skill [synced from claude.ai](#how-synced-skills-behave) | The skill's name on your claude.ai account, prefixed with `anthropic-skills:` | Account skill `deploy` → `/anthropic-skills:deploy`, or `/deploy` while no other command uses that name |
405405
406406In a plugin skill, the frontmatter `name` replaces the directory name in the last segment of the command, so `my-plugin/skills/review/SKILL.md` with `name: fancy` becomes `/my-plugin:fancy`. The bare `/fancy` also invokes the skill unless another command already uses that name. If the `name` you write already starts with the plugin's own prefix, Claude Code doesn't add the prefix again on v2.1.246 or later. For example, `name: my-plugin:fancy` still becomes `/my-plugin:fancy`. From v2.1.216 through v2.1.245, Claude Code doubled the prefix when the `name` already carried it.
407407
from line 413
413413
414414Skills support string substitution for dynamic values in the skill content:
415415
416| Variable | Description |
417| :---------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
418| `$ARGUMENTS` | All arguments passed when invoking the skill. When no placeholder receives an argument, Claude Code appends them as `ARGUMENTS: <value>`. See [Pass arguments to skills](#pass-arguments-to-skills). |
419| `$ARGUMENTS[N]` | Access a specific argument by 0-based index, such as `$ARGUMENTS[0]` for the first argument. |
420| `$N` | Shorthand for `$ARGUMENTS[N]`, such as `$0` for the first argument or `$1` for the second. |
421| `$name` | Named argument declared in the [`arguments`](#frontmatter-reference) frontmatter list. Names map to positions in order, so with `arguments: [issue, branch]` the placeholder `$issue` expands to the first argument and `$branch` to the second. |
422| `${CLAUDE_SESSION_ID}` | The current session ID. Useful for logging, creating session-specific files, or correlating skill output with sessions. |
423| `${CLAUDE_EFFORT}` | The current effort level: `low`, `medium`, `high`, `xhigh`, or `max`. Ultracode is not a distinct level and reports as `xhigh`. Use this to adapt skill instructions to the active effort setting. |
424| `${CLAUDE_SKILL_DIR}` | The directory containing the skill's `SKILL.md` file. For plugin skills, this is the skill's subdirectory within the plugin, not the plugin root. Use this in bash injection commands to reference scripts or files bundled with the skill, regardless of the current working directory. |
416| Variable | Description |
417| :- | :- |
418| `$ARGUMENTS` | All arguments passed when invoking the skill. When no placeholder receives an argument, Claude Code appends them as `ARGUMENTS: <value>`. See [Pass arguments to skills](#pass-arguments-to-skills). |
419| `$ARGUMENTS[N]` | Access a specific argument by 0-based index, such as `$ARGUMENTS[0]` for the first argument. |
420| `$N` | Shorthand for `$ARGUMENTS[N]`, such as `$0` for the first argument or `$1` for the second. |
421| `$name` | Named argument declared in the [`arguments`](#frontmatter-reference) frontmatter list. Names map to positions in order, so with `arguments: [issue, branch]` the placeholder `$issue` expands to the first argument and `$branch` to the second. |
422| `${CLAUDE_SESSION_ID}` | The current session ID. Useful for logging, creating session-specific files, or correlating skill output with sessions. |
423| `${CLAUDE_EFFORT}` | The current effort level: `low`, `medium`, `high`, `xhigh`, or `max`. Ultracode is not a distinct level and reports as `xhigh`. Use this to adapt skill instructions to the active effort setting. |
424| `${CLAUDE_SKILL_DIR}` | The directory containing the skill's `SKILL.md` file. For plugin skills, this is the skill's subdirectory within the plugin, not the plugin root. Use this in bash injection commands to reference scripts or files bundled with the skill, regardless of the current working directory. |
425425| `${CLAUDE_PROJECT_DIR}` | The project root directory. This is the same path [hooks](/docs/en/hooks#reference-scripts-by-path) and MCP servers receive as `CLAUDE_PROJECT_DIR`. Use this to reference project-local scripts or files, such as `${CLAUDE_PROJECT_DIR}/.claude/hooks/helper.sh`, independent of where the skill is installed. |
426| `${CLAUDE_PLUGIN_ROOT}` | The plugin's installation directory. Substituted only in plugin skills. Use this to reference scripts or files bundled anywhere in the plugin, including resources shared between the plugin's skills. See [plugin environment variables](/docs/en/plugins/manifest-reference#environment-variables). |
427| `${CLAUDE_PLUGIN_DATA}` | The plugin's [persistent data directory](/docs/en/plugins/components#path-variables-and-persistent-data), which survives plugin updates. Substituted only in plugin skills. Use this to reference installed dependencies, generated files, or caches that must outlive an update. |
426| `${CLAUDE_PLUGIN_ROOT}` | The plugin's installation directory. Substituted only in plugin skills. Use this to reference scripts or files bundled anywhere in the plugin, including resources shared between the plugin's skills. See [plugin environment variables](/docs/en/plugins/manifest-reference#environment-variables). |
427| `${CLAUDE_PLUGIN_DATA}` | The plugin's [persistent data directory](/docs/en/plugins/components#path-variables-and-persistent-data), which survives plugin updates. Substituted only in plugin skills. Use this to reference installed dependencies, generated files, or caches that must outlive an update. |
428428
429429Claude Code substitutes `${CLAUDE_SKILL_DIR}` and `${CLAUDE_PROJECT_DIR}` in two places: the skill's markdown content, and Bash rules in the [`allowed-tools`](#frontmatter-reference) frontmatter. In a plugin skill, Claude Code substitutes `${CLAUDE_PLUGIN_ROOT}` and `${CLAUDE_PLUGIN_DATA}` in the same two places. Using the same variable in both places lets a skill run a bundled script without a permission prompt. The following skill shows the pattern:
430430
from line 516
516516
517517Here's how the two fields affect invocation and context loading:
518518
519| Frontmatter | You can invoke | Claude can invoke | When loaded into context |
520| :------------------------------- | :------------- | :---------------- | :----------------------------------------------------------- |
521| (default) | Yes | Yes | Description always in context, full skill loads when invoked |
522| `disable-model-invocation: true` | Yes | No | Description not in context, full skill loads when you invoke |
523| `user-invocable: false` | No | Yes | Description always in context, full skill loads when invoked |
519| Frontmatter | You can invoke | Claude can invoke | When loaded into context |
520| :- | :- | :- | :- |
521| (default) | Yes | Yes | Description always in context, full skill loads when invoked |
522| `disable-model-invocation: true` | Yes | No | Description not in context, full skill loads when you invoke |
523| `user-invocable: false` | No | Yes | Description always in context, full skill loads when invoked |
524524
525525<Note>
526526 In a regular session, skill descriptions are loaded into context so Claude knows what's available, but full skill content only loads when invoked. [Subagents with preloaded skills](/docs/en/sub-agents#preload-skills-into-subagents) work differently: the full skill content is injected at startup.
from line 722
722722
723723Skills and [subagents](/docs/en/sub-agents) work together in two directions:
724724
725| Approach | System prompt | Task | Also loads |
726| :--------------------------- | :----------------------- | :-------------------------- | :------------------------------------------------------------------------------------------------------- |
727| Skill with `context: fork` | From agent type | SKILL.md content | CLAUDE.md, per the agent's [startup context](/docs/en/sub-agents#what-loads-at-startup) |
725| Approach | System prompt | Task | Also loads |
726| :- | :- | :- | :- |
727| Skill with `context: fork` | From agent type | SKILL.md content | CLAUDE.md, per the agent's [startup context](/docs/en/sub-agents#what-loads-at-startup) |
728728| Subagent with `skills` field | Subagent's markdown body | Claude's delegation message | Preloaded skills + CLAUDE.md, per the subagent's [startup context](/docs/en/sub-agents#what-loads-at-startup) |
729729
730730With `context: fork`, you write the task in your skill and pick an agent type to execute it. The built-in Explore and Plan agents [skip CLAUDE.md and git status](/docs/en/sub-agents#what-loads-at-startup) to keep their context small, so a forked skill using `agent: Explore` sees only the SKILL.md content and the agent's own system prompt. For the inverse, where you define a custom subagent that uses skills as reference material, see [Subagents](/docs/en/sub-agents#preload-skills-into-subagents).
from line 801
801801
802802Each key is a skill name and each value is one of four states:
803803
804| Value | Listed to Claude | In `/` menu |
805| :---------------------- | :------------------- | :---------- |
806| `"on"` | Name and description | Yes |
807| `"name-only"` | Name only | Yes |
808| `"user-invocable-only"` | Hidden | Yes |
809| `"off"` | Hidden | Hidden |
804| Value | Listed to Claude | In `/` menu |
805| :- | :- | :- |
806| `"on"` | Name and description | Yes |
807| `"name-only"` | Name only | Yes |
808| `"user-invocable-only"` | Hidden | Yes |
809| `"off"` | Hidden | Hidden |
810810
811811The `/skills` menu labels the `"user-invocable-only"` state `user-only`.
812812
No line in this hunk matches that.