What does this skill do, and when should you use it?
Example Command is a user-invoked reference skill showing the `skills/<name>/SKILL.md` layout and its frontmatter options. When invoked, it parses the supplied arguments, performs the requested action with approved tools, and reports the results. It is functionally equivalent to the legacy `commands/example-command.md` format. Its primary value is demonstrating Claude Code plugin structure rather than providing a defined production workflow.
Reads and parses the user-supplied $ARGUMENTS; uses the approved Read, Glob, Grep, or Bash tools to perform the requested action; and reports the results to the user. The specific action is determined by the request and is not fixed by the source file.
- A Claude Code plugin developer referencing the `skills/<name>/SKILL.md` directory layout.
- A plugin author demonstrating frontmatter fields such as `name`, `description`, `argument-hint`, and `allowed-tools`.
- A developer validating how arguments are passed into a user-invoked skill.
How do you install this skill?
- This is a format-demonstration skill, not a fully specified production capability; its actual results cannot be determined from the file.
- The pre-approved Bash permission is broad; confirm the exact commands, file scope, and possible external effects before use.
- Error handling, rollback, sensitive-data, and network-dependency guidance are absent; this review did not execute the skill or run tests.
- Shell / CLI
- Local filesystem
Install the target plugin from the official plugin directory in Claude Code with /plugin install example-plugin@claude-plugins-official. The source does not document separate installation steps for this individual skill or for other clients.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/anthropics/claude-plugins-official.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/plugins/example-plugin/skills/example-command" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Invoke it in Claude Code with /example-command my-argument or /example-command arg1 arg2. It parses the arguments, performs the requested action, and reports the result. The source does not define a specific action.
What are this skill's strengths and limitations?
- Provides a clear reference layout for a user-invoked skill.
- Explicitly lists the approved Read, Glob, Grep, and Bash tools.
- Includes an argument hint and copyable invocation examples.
- It is a demonstration skill, not a defined domain-specific workflow.
- The actual operation depends on the user's request; no tests or success criteria are provided.
- It uses Claude Code-oriented `$ARGUMENTS`, slash-command behavior, and `allowed-tools`, so other clients would require adaptation.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Example Command Skill this page ✓ Anthropic · Official | 32 · Not recommended | ★ 38k | 11d ago | Apache-2.0 |
| Git Worktree Parallel Environment Skill | 57 · Use with care | ★ 1.5k | 8mo ago | — |
| Azure Persistent Agents for .NET ✓ Microsoft · Official | 48 · Use with care | ★ 2.7k | 3mo ago | MIT |
| Claude Code Command Builder ✓ Anthropic · Official | 46 · Use with care | ★ 38k | 11d ago | Apache-2.0 |
| Claude Code Command Development ✓ Anthropic · Official | 46 · Use with care | ★ 151k | 11d ago | — |
The source explicitly compares it with the legacy commands/example-command.md format: both load and function the same way, with the difference limited to file layout.
How did FollowSkills review this skill?
The skill is explicitly user-invoked and limits access to Read, Glob, Grep, and Bash; however, Bash is broad, and there are no rules for least privilege, confirmation, data flows, sensitive data, external effects, or rollback, so points are deducted.
The file structure, argument placeholder, and invocation steps are internally understandable on the happy path; however, argument parsing, abnormal-input handling, dependency checks, failure feedback, and reproducible tests are absent, and static calibration limits the score.
It identifies a user-invoked scenario, provides an argument hint, and includes two basic examples; however, the requested action is undefined, with no input/output contract, non-fit boundaries, precise trigger conditions, or evidence of Chinese-language or mainland-China network fit.
Frontmatter, layout guidance, help description, and examples are clear, while repository context supplies an Apache-2.0 license and official maintenance provenance; the skill lacks installation notes, versioning, changelog, known limitations, FAQ, and an explicit update path.
It can demonstrate skill formatting and a generic invocation flow, but the actual capability is reduced to performing an unspecified user-requested action; there is no concrete usable output, so substantial user rework remains.
The source is auditable and its frontmatter and examples can be checked; however, there are no skill-specific tests, CI coverage, third-party execution evidence, or corroborating sources, so static calibration keeps this below6.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →