# Custom slash commands and skills

*Claude Certified Architect - Foundations Study Guide · Claude Code Configuration & Workflows · Last updated October 22, 2026 · https://www.certifyforce.com/study-guide/claude-certified-architect-foundations/claude-code-configuration-and-workflows/custom-slash-commands-and-skills*

How .claude/commands/ files and SKILL.md skills create the same /name commands, where project and personal skills live and which wins a name clash, and what argument-hint, context: fork, allowed-tools, disallowed-tools and disable-model-invocation actually do. Also when a workflow belongs in a skill rather than CLAUDE.md.

- Certification: Claude Certified Architect - Foundations
- Exam section: Claude Code Configuration & Workflows
- Study guide: https://www.certifyforce.com/study-guide/claude-certified-architect-foundations

**Official exam objective:**

> Create and configure custom slash commands and skills

## What the exam expects

- Create a team-wide slash command by committing a `.claude/commands/<name>.md` file or a `.claude/skills/<name>/SKILL.md` skill, and a personal variant under `~/.claude/skills/` with a different name.
- Configure SKILL.md frontmatter: `argument-hint` for expected parameters, `context: fork` for isolation, `allowed-tools` and `disallowed-tools` for tool access, and `disable-model-invocation` for side-effect workflows.
- Use `context: fork` for verbose or exploratory task skills, and recognize when it breaks a reference-only skill.
- Choose skills (on-demand, task-specific) over CLAUDE.md (always loaded, universal standards).
- Make an Agent SDK agent discover project skills.

Key terms: **skill** (a directory with a `SKILL.md` file that Claude or a person can invoke as `/name`); **frontmatter** (YAML between `---` markers that configures the skill); **forked skill** (a skill run as an isolated subagent via `context: fork`); **progressive disclosure** (description always in context, body on invoke, supporting files when needed); **pre-approval** (tools usable without a permission prompt).

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Commands and skills | `.claude/commands/deploy.md` and `.claude/skills/deploy/SKILL.md` both create `/deploy` | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| Command files still work | No forced migration; same frontmatter except `name` and `paths` | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| Same-name precedence | Enterprise > personal > project; skill beats a command file | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| Always-loaded skill cost | Name and description, about 100 tokens per skill | [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) |
| Skill body after invocation | Enters as one message, stays across turns, not re-read | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| `allowed-tools` | Pre-approves for the invoking turn; does not restrict | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| `disallowed-tools` | Removes tools while the skill is active | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| `context: fork` input | Skill content as prompt; no conversation history | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| `argument-hint` | Autocomplete hint only | [Extend Claude with skills](https://code.claude.com/docs/en/skills) |
| SDK skill discovery | Filesystem only, via `settingSources`; no registration API | [Extend agents with skills (Agent SDK)](https://code.claude.com/docs/en/agent-sdk/skills) |

## Check yourself

- Why does a personal `~/.claude/skills/deploy/SKILL.md` hide the team's `/deploy` from its author?
- When should a skill use `context: fork`?
- Why can many skills be installed without a large context penalty?
- Which frontmatter field removes Bash while a skill is active?
- What must an SDK agent's `setting_sources` include to discover `.claude/skills/`?

## Sources

- [Extend Claude with skills](https://code.claude.com/docs/en/skills)
- [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview)
- [Extend agents with skills (Agent SDK)](https://code.claude.com/docs/en/agent-sdk/skills)
- [Use Claude Code features in the SDK](https://code.claude.com/docs/en/agent-sdk/claude-code-features)
- [Best practices for Claude Code](https://code.claude.com/docs/en/best-practices)
- [How Claude remembers your project](https://code.claude.com/docs/en/memory)
- [Explore the .claude directory](https://code.claude.com/docs/en/claude-directory)
- [Equipping agents for the real world with Agent Skills](https://www.anthropic.com/research/equipping-agents-for-the-real-world-with-agent-skills)
- [Claude Certified Architect – Foundations Exam Guide v1.0](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542750%2FClaude+Certified+Architect+%E2%80%93+Foundations+Exam+Guide.pdf)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 10 linked practice questions, and unlimited timed mock exams are included with the Claude Certified Architect - Foundations pack (USD $19): https://www.certifyforce.com/practice-exams