Shayan Rais
25b573944c
Settings (claude-settings.md): - add autoMode, disableAutoMode, auto permission mode - add sandbox.failIfUnavailable, disableDeepLinkRegistration - add CLAUDE_CODE_SUBPROCESS_ENV_SCRUB env var - add managed-settings.d/ drop-in directory - fix Windows registry path to SOFTWARE\Policies\ClaudeCode - add opus[1m] model alias - fix broken claudelog.com link - update badge/version to v2.1.83 Other workflows: commands, skills, subagents, concepts, dev-workflows badge/changelog updates Co-Authored-By: Claude <noreply@anthropic.com>
2.7 KiB
2.7 KiB
Skills Best Practice
Claude Code skills — frontmatter fields and official bundled skills.
| ← Back to Claude Code Best Practice |  |
Frontmatter Fields (11)
| Field | Type | Required | Description |
|---|---|---|---|
name |
string | No | Display name and /slash-command identifier. Defaults to the directory name if omitted |
description |
string | Recommended | What the skill does. Shown in autocomplete and used by Claude for auto-discovery |
argument-hint |
string | No | Hint shown during autocomplete (e.g., [issue-number], [filename]) |
disable-model-invocation |
boolean | No | Set true to prevent Claude from automatically invoking this skill |
user-invocable |
boolean | No | Set false to hide from the / menu — skill becomes background knowledge only, intended for agent preloading |
allowed-tools |
string | No | Tools allowed without permission prompts when this skill is active |
model |
string | No | Model to use when this skill runs (e.g., haiku, sonnet, opus) |
effort |
string | No | Override the model effort level when invoked (low, medium, high, max) |
context |
string | No | Set to fork to run the skill in an isolated subagent context |
agent |
string | No | Subagent type when context: fork is set (default: general-purpose) |
hooks |
object | No | Lifecycle hooks scoped to this skill |
(5)
| # | Skill | Description |
|---|---|---|
| 1 | simplify |
Review changed code for reuse, quality, and efficiency — refactors to eliminate duplication |
| 2 | batch |
Run commands across multiple files in bulk |
| 3 | debug |
Debug failing commands or code issues |
| 4 | loop |
Run a prompt or slash command on a recurring interval (up to 3 days) |
| 5 | claude-api |
Build apps with the Claude API or Anthropic SDK — triggers on anthropic / @anthropic-ai/sdk imports |
See also: Official Skills Repository for community-maintained installable skills.