create-skill
Helps you create new agent skills for Zed. Use this to create a skill, ask about SKILLs.md, or package reusable agent instructions.
What this skill does
# Creating a Zed Agent Skill
Use this skill when the user wants to create, edit, or understand agent skills in Zed.
## What is a Skill?
A skill is a reusable set of instructions that an agent can load on demand. Each skill lives in its own directory and is defined by a `SKILL.md` file with YAML frontmatter.
## Where Skills Live
Skills can be placed in two locations:
| Scope | Path | When to use |
|-------|------|-------------|
| Global | `~/.agents/skills/<skill-name>/SKILL.md` | Personal skills, available in all projects |
| Project-local | `<project>/.agents/skills/<skill-name>/SKILL.md` | Project-specific skills, shared with collaborators through version control |
Prefer project-local when the skill is specific to a repository. Prefer global when the skill is a personal workflow the user wants everywhere.
## SKILL.md Format
Every `SKILL.md` must start with YAML frontmatter between `---` delimiters:
```markdown
---
name: my-skill-name
description: A clear, specific description of what this skill does and when to use it.
---
# Skill Title
Instructions for the agent go here. Write them as if you're telling the agent
what to do when this skill is activated.
```
### Required Frontmatter Fields
- **`name`** (required): Must be 1–64 characters, lowercase alphanumeric with single-hyphen separators. Must match the containing directory name exactly. Regex: `^[a-z0-9]+(-[a-z0-9]+)*$`
- **`description`** (required): Must be 1–1024 characters. This is what the agent sees when deciding whether to use the skill — make it specific and actionable.
### Optional Frontmatter Fields
- **`disable-model-invocation`**: When set to `true`, the skill is hidden from the agent's automatic catalog. The user can still invoke it manually via the `/` slash command menu. Useful for skills that should only run when explicitly requested.
## Naming Rules
The skill name must:
- Be lowercase letters and numbers only, with single hyphens as separators
- Not start or end with `-`
- Not contain consecutive `--`
- Match the directory name that contains the `SKILL.md`
Good: `git-release`, `pr-review`, `rust-patterns`
Bad: `Git-Release`, `pr--review`, `-my-skill`, `my_skill`
## Writing Good Skill Instructions
The body of the SKILL.md (after the frontmatter) contains the instructions the agent will follow. Guidelines:
1. **Be direct**: Write instructions as if talking to the agent. "Do X", "Check Y", "Ask the user about Z".
2. **Be specific**: Include concrete file paths, commands, formats, and patterns.
3. **Include when-to-use guidance**: Help the agent understand the right context for this skill.
4. **Reference supporting files**: Skills can include additional files in their directory. Reference them with relative paths (e.g., `templates/component.tsx`). The agent can read these files when the skill is activated.
5. **Keep descriptions actionable**: The `description` field is the agent's primary signal for whether to load this skill. "Helps with code" is too vague. "Generate React components following the project's design system patterns" is specific.
6. **Keep instructions focused**: Limit instructions to those relevant to the skill itself. Avoid duplicating instructions from AGENTS.md and other skills in the current conversation if they are not relevant to the skill being created
## Supporting Files
A skill directory can contain additional files beyond `SKILL.md`:
```
~/.agents/skills/react-component/
├── SKILL.md
├── templates/
│ ├── component.tsx
│ └── test.tsx
└── examples/
└── button.tsx
```
Reference these in the skill body. The agent can read them using the file path shown in the `<directory>` tag of the skill envelope.
## Step-by-Step: Creating a Skill
1. Decide on scope (global vs project-local) based on the user's needs.
2. Choose a descriptive, hyphenated name.
3. Create the directory structure. The `create_directory` tool normally only creates directories inside the current project, but it has a special allow case for global skills under `~/.agents/skills`.
4. Write the `SKILL.md` with frontmatter and instructions. The `write_file` and `edit_file` tools also have a special allow case for creating or modifying files under `~/.agents/skills`.
5. Optionally add supporting files (templates, examples, references).
After creating the skill, it will be automatically discovered by Zed's agent on the next conversation (no restart needed for global skills if the `~/.agents/skills/` directory already exists).
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.